Skip to content

agentic-evolution/awesome-agentic-evolution

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Awesome Agentic Evolution

Awesome PRs Welcome

A curated and continuously updated collection of research papers on agentic evolution — persistent, system-level change in agentic systems through autonomous or human-involved selective pressure.

Some papers appear under multiple substrates when they contribute to more than one.

This paper list accompanies a survey paper on agentic evolution.

Legend

Evolutionary Substrate — what component of the agentic system evolves:

  • Cortex (Π): The deliberative substrate — base LLM weights, prompts, decoding strategies, and inference-time procedures
  • Action (A): The executive substrate — toolset, execution logic (workflow graphs, control flow), and multi-agent orchestration
  • Memory & Sense (M): The epistemic substrate — episodic/semantic/procedural memory, retention and retrieval policies, perception encoders, and world models

Consolidation Pathway — how experience becomes persistent change:

  • Δ Structural: discrete, symbolic edits to non-parametric artifacts (prompts, workflow graphs, memory indices, tool configurations, or code)
  • Parametric: continuous updates to model weight parameters
  • Δ+∇ Hybrid: both structural and parametric consolidation within a single system

Selective Pressure — what drives evolution:

  • H=0 Autonomous: selective pressure from environmental experience (including formal verification) and self-generated signals (self-play and self-rewarding)
  • H≠0 Human-involved: human input shapes the evolutionary trajectory (prescriptions, demonstrations, evaluative feedback, interactive collaboration, or implicit signals)

Table of Contents

Cortex (Π) Evolution

Δ, H=0 (Structural, Autonomous)

Prompt optimization

  • "Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs"
    Liu et al. arXiv 2026. [paper]
  • "Self-Optimizing Multi-Agent Systems for Deep Research"
    Câmara et al. arXiv 2026. [paper]
  • "Combee: Scaling Prompt Learning for Self-Improving Language Model Agents"
    Li et al. arXiv 2026. [paper]
  • "Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks"
    Yang et al. arXiv 2026. [paper]
  • "Evolutionary Context Search for Automated Skill Acquisition"
    Sun et al. arXiv 2026. [paper]
  • "Understanding the Challenges in Iterative Generative Optimization with LLMs"
    Nie et al. arXiv 2026. [paper]
  • "JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents"
    Ghoshal et al. arXiv 2026. [paper]
  • "Optimizing Generative AI by Backpropagating Language Model Feedback"
    Yuksekgonul et al. Nature 2025. [paper]
  • "REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization"
    Zhang et al. ICML 2025. [paper]
  • "Large Language Models as Optimizers"
    Yang et al. ICLR 2024. [paper]
  • "Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers"
    Guo et al. ICLR 2024. [paper]
  • "Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution"
    Fernando et al. ICML 2024. [paper]
  • "DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines"
    Khattab et al. ICLR 2024. [paper]
  • "Large Language Models Are Human-Level Prompt Engineers"
    Zhou et al. ICLR 2023. [paper]

Reflection-driven

  • "Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models"
    Zhang et al. ICLR 2026. [paper]
  • "Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills"
    Ni et al. arXiv 2026. [paper]
  • "Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts"
    Li et al. arXiv 2026. [paper]
  • "Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning"
    Zhuang et al. arXiv 2026. [paper]
  • "AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents"
    Wang et al. arXiv 2026. [paper]
  • "Harnessing Pre-Resolution Signals for Future Prediction Agents"
    Wei et al. arXiv 2026. [paper]
  • "ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace Analysis"
    Rishav et al. arXiv 2026. [paper]
  • "AEL: Agent Evolving Learning for Open-Ended Environments"
    Xu et al. arXiv 2026. [paper]
  • "Discovering Agentic Safety Specifications from 1-Bit Danger Signals"
    Gallego ALA Workshop @ AAMAS 2026. [paper]
  • "EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale"
    Zhu et al. arXiv 2026. [paper]
  • "Can AI Scientist Agents Learn from Lab-in-the-Loop Feedback? Evidence from Iterative Perturbation Discovery"
    Wainrib et al. arXiv 2026. [paper]
  • "STELLA: Self-Evolving LLM Agent for Biomedical Research"
    Jin et al. arXiv 2025. [paper]
  • "Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization"
    Zhang et al. ACL 2024. [paper]
  • "Reflexion: Language Agents with Verbal Reinforcement Learning"
    Shinn et al. NeurIPS 2023. [paper]

Configurations & architectures

  • "Evolving Interpretable Constitutions for Multi-Agent Coordination"
    Kumar et al. arXiv 2026. [paper]
  • "SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering"
    Gong et al. arXiv 2026. [paper]
  • "Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization"
    Huang et al. arXiv 2026. [paper]
  • "A Self-Evolving Agentic Framework for Metasurface Inverse Design"
    Huang et al. arXiv 2026. [paper]
  • "Prompt Optimization Enables Stable Algorithmic Collusion in LLM Agents"
    Tian arXiv 2026. [paper]
  • "MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games"
    Xie et al. arXiv 2026. [paper]
  • "EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms"
    Yuan et al. NAACL 2025. [paper]
  • "Evolving Excellence: Automated Optimization of LLM-based Agents"
    Brookes et al. arXiv 2025. [paper]

Code-level

  • "Meta-Harness: End-to-End Optimization of Model Harnesses"
    Lee et al. arXiv 2026. [paper]
  • "M★: Every Task Deserves Its Own Memory Harness"
    Pan et al. arXiv 2026. [paper]
  • "AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering"
    Zhang arXiv 2026. [paper]
  • "Autogenesis: A Self-Evolving Agent Protocol"
    Zhang et al. arXiv 2026. [paper]
  • "Automated Design of Agentic Systems"
    Hu et al. ICLR 2025. [paper]
  • "A Self-Improving Coding Agent"
    Robeyns et al. arXiv 2025. [paper]
  • "Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents"
    Zhang et al. arXiv 2025. [paper]
  • "Symbolic Learning Enables Self-Evolving Agents"
    Zhou et al. AI Open 2025. [paper]

Multi-agent structural

  • "LangMARL: Natural Language Multi-Agent Reinforcement Learning"
    Yao et al. arXiv 2026. [paper]
  • "Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization"
    He et al. arXiv 2026. [paper]
  • "EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines"
    Zhang et al. arXiv 2026. [paper]

Δ, H≠0 (Structural, Human-involved)

  • "Prompt Optimization with Human Feedback"
    Lin et al. arXiv 2024. [paper]

∇, H=0 (Parametric, Autonomous)

Iterative self-improvement

  • "ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution"
    Huang et al. arXiv 2026. [paper]
  • "Agentic Critical Training"
    Liu et al. arXiv 2026. [paper]
  • "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"
    Lu et al. arXiv 2026. [paper]
  • "RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems"
    Qu et al. ICLR 2026. [paper]
  • "Expanding the Capabilities of Reinforcement Learning via Text Feedback"
    Song et al. arXiv 2026. [paper]
  • "Temporal Self-Rewarding Language Models: Decoupling Chosen-Rejected via Past-Future"
    Wang et al. arXiv 2025. [paper]
  • "Process-based Self-Rewarding Language Models"
    Zhang et al. Findings of ACL 2025. [paper]
  • "Language Models that Think, Chat Better"
    Bhaskar et al. arXiv 2025. [paper]
  • "The Art of Scaling Reinforcement Learning Compute for LLMs"
    Khatri et al. arXiv 2025. [paper]
  • "Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning"
    Hübotter et al. arXiv 2025. [paper]
  • "SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data"
    Fang et al. arXiv 2025. [paper]
  • "Co-Alignment: Rethinking Alignment as Bidirectional Human-AI Cognitive Adaptation"
    Li et al. arXiv 2025. [paper]
  • "Self-Rewarding Language Models"
    Yuan et al. ICML 2024. [paper]
  • "STaR: Bootstrapping Reasoning With Reasoning"
    Zelikman et al. NeurIPS 2022. [paper]

Multi-role self-play

  • "SAGE: Multi-Agent Self-Evolution for LLM Reasoning"
    Peng et al. arXiv 2026. [paper]
  • "MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data"
    Li et al. arXiv 2026. [paper]
  • "SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments"
    Li et al. arXiv 2026. [paper]
  • "One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence"
    Jiang et al. arXiv 2026. [paper]
  • "SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning"
    Liu et al. ICLR 2026. [paper]
  • "Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation"
    Sui et al. arXiv 2026. [paper]
  • "Vision-Zero: Scalable VLM Self-Evolution via Multi-Agent Self-Play"
    Wang et al. ICLR 2026. [paper]
  • "Dr. Zero: Self-Evolving Search Agents without Training Data"
    Yue et al. arXiv 2026. [paper]
  • "The Alignment Waltz: Jointly Training Agents to Collaborate for Safety"
    Zhang et al. ICLR 2026. [paper]
  • "SELF-EMO: Emotional Self-Evolution from Recognition to Consistent Expression"
    Zhang et al. arXiv 2026. [paper]
  • "Multi-Agent Evolve: LLM Self-Improve through Co-evolution"
    Chen et al. arXiv 2025. [paper]
  • "R-Zero: Self-Evolving Reasoning LLM from Zero Data"
    Huang et al. arXiv 2025. [paper]
  • "MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning"
    Chen et al. arXiv 2025. [paper]
  • "CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards"
    Xue et al. arXiv 2025. [paper]
  • "MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs"
    Yuan et al. arXiv 2025. [paper]
  • "Toward Training Superintelligent Software Agents through Self-Play SWE-RL"
    Wei et al. arXiv 2025. [paper]
  • "Absolute Zero: Reinforced Self-play Reasoning with Zero Data"
    Zhao et al. arXiv 2025. [paper]
  • "Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning"
    Xia et al. arXiv 2025. [paper]

Adversarial auditing

  • "Adversarial Reward Auditing for Active Detection and Mitigation of Reward Hacking"
    Beigi et al. arXiv 2026. [paper]

Data synthesis & self-training

  • "AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis"
    Chen et al. ICLR 2026. [paper]
  • "Diving into Self-Evolving Training for Multimodal Reasoning"
    Liu et al. ICML 2025. [paper]
  • "MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct"
    Luo et al. Findings of ACL 2025. [paper]
  • "Skill-Targeted Adaptive Training"
    He et al. arXiv 2025. [paper]
  • "ALAS: Autonomous Learning Agent for Self-Updating Language Models"
    Atreja arXiv 2025. [paper]
  • "NExT: Teaching Large Language Models to Reason about Code Execution"
    Ni et al. ICML 2024. [paper]

Tool-integrated

  • "SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents"
    Feng et al. arXiv 2026. [paper]
  • "Computer Environments Elicit General Agentic Intelligence in LLMs"
    Cheng et al. arXiv 2026. [paper]
  • "GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning"
    Li et al. arXiv 2026. [paper]
  • "TRACE: Capability-Targeted Agentic Training"
    Kang et al. arXiv 2026. [paper]
  • "Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning"
    Dong et al. arXiv 2025. [paper]
  • "ReTool: Reinforcement Learning for Strategic Tool Use in LLMs"
    Feng et al. arXiv 2025. [paper]
  • "VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use"
    Jiang et al. arXiv 2025. [paper]
  • "ToolRL: Reward is All Tool Learning Needs"
    Qian et al. arXiv 2025. [paper]
  • "START: Self-taught Reasoner with Tools"
    Li et al. arXiv 2025. [paper]
  • "rStar2-Agent: Agentic Reasoning Technical Report"
    Shang et al. arXiv 2025. [paper]
  • "Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning"
    Zhang et al. arXiv 2025. [paper]
  • "Tool-R1: Sample-Efficient Reinforcement Learning for Agentic Tool Use"
    Zhang et al. arXiv 2025. [paper]
  • "ACECODER: Acing Coder RL via Automated Test-Case Synthesis"
    Zeng et al. ACL 2025. [paper]
  • "One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents"
    Zhang et al. arXiv 2025. [paper]
  • "ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs"
    Qin et al. ICLR 2024. [paper]
  • "ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving"
    Gou et al. ICLR 2024. [paper]
  • "StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback"
    Dou et al. ACL 2024. [paper]

Interactive environments

  • "Safe and Scalable Web Agent Learning via Recreated Websites"
    Chae et al. arXiv 2026. [paper]
  • "UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience"
    Lin et al. arXiv 2026. [paper]
  • "Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence"
    Dong et al. arXiv 2026. [paper]
  • "Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning"
    Qin et al. ICLR 2026. [paper]
  • "Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents"
    Cai et al. arXiv 2026. [paper]
  • "CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection"
    Liu et al. arXiv 2026. [paper]
  • "WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model"
    Fang et al. EMNLP 2025. [paper]
  • "WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning"
    Qi et al. ICLR 2025. [paper]
  • "Reinforcement Learning for Long-Horizon Interactive LLM Agents"
    Chen et al. arXiv 2025. [paper]

Multi-turn RL

  • "RAGEN-2: Reasoning Collapse in Agentic RL"
    Wang et al. arXiv 2026. [paper]
  • "Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis"
    Zhai et al. arXiv 2026. [paper]
  • "On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM Agents"
    Zou et al. arXiv 2026. [paper]
  • "When Reward Hacking Rebounds: Understanding and Mitigating It with Representation-Level Signals"
    Wu et al. arXiv 2026. [paper]
  • "Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning"
    Yang et al. arXiv 2026. [paper]
  • "MemoBrain: Executive Memory as an Agentic Brain for Reasoning"
    Qian et al. arXiv 2026. [paper]
  • "A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning"
    Wang et al. arXiv 2025. [paper]
  • "RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning"
    Wang et al. arXiv 2025. [paper]
  • "WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning"
    Wei et al. EMNLP 2025. [paper]
  • "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning"
    Xi et al. arXiv 2025. [paper]
  • "MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent"
    Yu et al. arXiv 2025. [paper]
  • "MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents"
    Zhou et al. arXiv 2025. [paper]
  • "CollabLLM: From Passive Responders to Active Collaborators"
    Wu et al. ICML 2025. [paper]
  • "AgentGym: Evolving Large Language Model-based Agents across Diverse Environments"
    Xi et al. arXiv 2024. [paper]

Continual/personalized

  • "SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation"
    Kim et al. arXiv 2026. [paper]
  • "PersonaVLM: Long-Term Personalized Multimodal LLMs"
    Nie et al. arXiv 2026. [paper]
  • "Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning"
    Hu et al. arXiv 2026. [paper]
  • "PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory"
    Jiang et al. arXiv 2025. [paper]
  • "Fed-SE: Federated Self-Evolution for Cross-Environment Knowledge Transfer in Privacy-Constrained LLM Agents"
    Chen et al. arXiv 2025. [paper]
  • "Self-Updatable Large Language Models by Integrating Context into Model Parameters"
    Wang et al. ICLR 2025. [paper]

Multi-LLM collaborative

  • "ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference Evolution"
    Jeon et al. arXiv 2026. [paper]
  • "CoLa: Learning to Interactively Collaborate with Large Language Models"
    Sharma et al. arXiv 2025. [paper]
  • "AutoFlow: Automated Workflow Generation for Large Language Model Agents"
    Li et al. arXiv 2024. [paper]

Meta-learning

  • "End-to-End Test-Time Training for Long Context"
    Tandon et al. arXiv 2025. [paper]
  • "Self-Adapting Language Models"
    Zweiger et al. arXiv 2025. [paper]

Neuroevolutionary hybrid

  • "Discovering Novel LLM Experts via Task-Capability Coevolution"
    Dai et al. ICLR 2026. [paper]
  • "Evolutionary Policy Optimization"
    Wang et al. arXiv 2025. [paper]

Domain-specific

  • "EVA: Efficient Reinforcement Learning for End-to-End Video Agent"
    Zhang et al. CVPR 2026. [paper]
  • "FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing"
    Zhang et al. arXiv 2026. [paper]
  • "Co-Evolution of Policy and Internal Reward for Language Agents"
    Wang et al. arXiv 2026. [paper]
  • "FinEvo: From Isolated Backtests to Ecological Market Games for Multi-Agent Financial Strategy Evolution"
    Zou et al. arXiv 2026. [paper]
  • "Meta-Reinforcement Learning with Self-Reflection for Agentic Search"
    Xiao et al. arXiv 2026. [paper]
  • "MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems"
    Ye et al. ICML 2025. [paper]
  • "Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback"
    Yang et al. arXiv 2025. [paper]
  • "π0: A Vision-Language-Action Flow Model for General Robot Control"
    Black et al. RSS 2025. [paper]
  • "Towards Agentic Self-Learning LLMs in Search Environment"
    Sun et al. arXiv 2025. [paper]
  • "Scaling Agent Learning via Experience Synthesis"
    Chen et al. arXiv 2025. [paper]
  • "OMNI: Open-endedness via Models of human Notions of Interestingness"
    Zhang et al. ICLR 2024. [paper]
  • "Agent Lumos: Unified and Modular Training for Open-Source Language Agents"
    Yin et al. ACL 2024. [paper]
  • "Open-Ended Learning Leads to Generally Capable Agents"
    Team et al. arXiv 2021. [paper]

World-model-based

  • "Mastering Diverse Control Tasks through World Models"
    Hafner et al. Nature 2025. [paper]
  • "EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks"
    Feng et al. arXiv 2025. [paper]
  • "Recurrent World Models Facilitate Policy Evolution"
    Ha et al. NeurIPS 2018. [paper]

∇, H≠0 (Parametric, Human-involved)

  • "Learning to Summarize User Information for Personalized Reinforcement Learning from Human Feedback"
    Nam et al. ICLR 2026. [paper]
  • "Pioneer Agent: Continual Improvement of Small Language Models in Production"
    Atreja et al. arXiv 2026. [paper]
  • "Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback"
    Yang et al. arXiv 2025. [paper]
  • "Personalized Language Modeling from Personalized Human Feedback"
    Li et al. arXiv 2024. [paper]
  • "Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback"
    Abramson et al. arXiv 2022. [paper]
  • "Interactive Learning from Policy-Dependent Human Feedback"
    MacGlashan et al. ICML 2017. [paper]
  • "Learning Preferences for Manipulation Tasks from Online Coactive Feedback"
    Jain et al. The International Journal of Robotics Research 2015. [paper]
  • "Coactive Learning"
    Shivaswamy et al. Journal of Artificial Intelligence Research 2015. [paper]

Δ+∇, H=0 (Hybrid, Autonomous)

Experience consolidation

  • "Memory Intelligence Agent"
    Qiao et al. arXiv 2026. [paper]
  • "Experiential Reinforcement Learning"
    Shi et al. arXiv 2026. [paper]
  • "VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction"
    Liao et al. arXiv 2026. [paper]
  • "Evaluation-driven Scaling for Scientific Discovery"
    Ye et al. arXiv 2026. [paper]
  • "DeltaMem: Towards Agentic Memory Management via Reinforcement Learning"
    Zhang et al. arXiv 2026. [paper]
  • "Self-Consolidation for Self-Evolving Agents"
    Yu et al. arXiv 2026. [paper]
  • "Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization"
    Shi et al. arXiv 2025. [paper]

Jointly evolving auxiliary structures

  • "SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning"
    Xia et al. arXiv 2026. [paper]
  • "SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training"
    Wang et al. arXiv 2026. [paper]
  • "CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution"
    Yang et al. arXiv 2026. [paper]
  • "RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback"
    Zhang et al. arXiv 2026. [paper]
  • "Evolutionary System Prompt Learning for Reinforcement Learning in LLMs"
    Zhang et al. arXiv 2026. [paper]
  • "SkillOS: Learning Skill Curation for Self-Evolving Agents"
    Ouyang et al. arXiv 2026. [paper]
  • "SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations"
    Ali et al. arXiv 2026. [paper]
  • "SEVerA: Verified Self-Evolving Agents"
    Banerjee et al. arXiv 2026. [paper]
  • "SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology"
    Nie et al. arXiv 2026. [paper]
  • "EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering"
    Huang et al. arXiv 2026. [paper]
  • "AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization"
    Yuan et al. arXiv 2026. [paper]
  • "HELIX: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving"
    Su et al. ICLR 2026. [paper]
  • "Reinforcement Learning for Self-Improving Agent with Skill Library"
    Wang et al. arXiv 2025. [paper]
  • "EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle"
    Wu et al. arXiv 2025. [paper]
  • "AgentEvolver: Towards Efficient Self-Evolving Agent System"
    Zhai et al. arXiv 2025. [paper]
  • "EvolveSearch: An Iterative Self-Evolving Search Agent"
    Zhang et al. arXiv 2025. [paper]
  • "Agentic Policy Optimization via Instruction-Policy Co-Evolution"
    Zhou et al. arXiv 2025. [paper]
  • "InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios"
    Yu et al. arXiv 2025. [paper]

Memory/planning joint evolution

  • "PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor"
    Yang et al. arXiv 2026. [paper]
  • "Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks"
    Wu et al. arXiv 2026. [paper]
  • "S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research"
    Team arXiv 2026. [paper]
  • "Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration"
    Zhang et al. arXiv 2026. [paper]
  • "Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning"
    Yan et al. arXiv 2025. [paper]

Action (A) Evolution

Δ, H=0 (Structural, Autonomous)

Tools & skills

  • "Optimizing Agentic Workflows using Meta-tools"
    Abuzakuk et al. arXiv 2026. [paper]
  • "Mem^2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation"
    Cheng et al. arXiv 2026. [paper]
  • "Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks"
    Li et al. arXiv 2026. [paper]
  • "RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning"
    Liu et al. ICLR 2026. [paper]
  • "OpenGame: Open Agentic Coding for Games"
    Jiang et al. arXiv 2026. [paper]
  • "GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)"
    Liang et al. arXiv 2026. [paper]
  • "SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support"
    Liu et al. arXiv 2026. [paper]
  • "Memento-Skills: Let Agents Design Agents"
    Zhou et al. arXiv 2026. [paper]
  • "CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery"
    Qu et al. arXiv 2026. [paper]
  • "SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources"
    Shen et al. arXiv 2026. [paper]
  • "Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning"
    Shen et al. arXiv 2026. [paper]
  • "SkillX: Automatically Constructing Skill Knowledge Bases for Agents"
    Wang et al. arXiv 2026. [paper]
  • "El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation"
    Zhang et al. arXiv 2026. [paper]
  • "AgentFactory: A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse"
    Zhang et al. arXiv 2026. [paper]
  • "CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification"
    Zhang et al. arXiv 2026. [paper]
  • "STELLA: Self-Evolving LLM Agent for Biomedical Research"
    Jin et al. arXiv 2025. [paper]
  • "From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions"
    Qu et al. ICLR 2025. [paper]
  • "Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution"
    Qiu et al. arXiv 2025. [paper]
  • "Alita-G: Self-Evolving Generative Agent for Agent Generation"
    Qiu et al. arXiv 2025. [paper]
  • "Voyager: An Open-Ended Embodied Agent with Large Language Models"
    Wang et al. TMLR 2024. [paper]

Program search

  • "AVO: Agentic Variation Operators for Autonomous Evolutionary Search"
    Chen et al. arXiv 2026. [paper]
  • "PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs"
    Gungordu et al. arXiv 2026. [paper]
  • "AIRA_2: Overcoming Bottlenecks in AI Research Agents"
    Hambardzumyan et al. arXiv 2026. [paper]
  • "Digital Red Queen: Adversarial Program Evolution in Core War with LLMs"
    Kumar et al. arXiv 2026. [paper]
  • "OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery"
    Liu et al. arXiv 2026. [paper]
  • "AdaptEvolve: Improving Efficiency of Evolutionary AI Agents through Adaptive Model Selection"
    Ray et al. arXiv 2026. [paper]
  • "Evaluation-driven Scaling for Scientific Discovery"
    Ye et al. arXiv 2026. [paper]
  • "AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models"
    Gautam et al. arXiv 2026. [paper]
  • "AlphaEvolve: A Coding Agent for Scientific and Algorithmic Discovery"
    Novikov et al. arXiv 2025. [paper]
  • "AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization"
    Zhang et al. arXiv 2025. [paper]
  • "Mathematical Discoveries from Program Search with Large Language Models"
    Romera-Paredes et al. Nature 2024. [paper]
  • "Evolution through Large Models"
    Lehman et al. arXiv 2022. [paper]

Workflow & orchestration

  • "Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization"
    He et al. arXiv 2026. [paper]
  • "Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization"
    Huang et al. arXiv 2026. [paper]
  • "Meta-Harness: End-to-End Optimization of Model Harnesses"
    Lee et al. arXiv 2026. [paper]
  • "Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses"
    Lin et al. arXiv 2026. [paper]
  • "Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts"
    Li et al. arXiv 2026. [paper]
  • "HyEvo: Self-Evolving Hybrid Agentic Workflows for Efficient Reasoning"
    Xu et al. arXiv 2026. [paper]
  • "Autogenesis: A Self-Evolving Agent Protocol"
    Zhang et al. arXiv 2026. [paper]
  • "EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines"
    Zhang et al. arXiv 2026. [paper]
  • "Automated Design of Agentic Systems"
    Hu et al. ICLR 2025. [paper]
  • "SwarmSys: Decentralized Swarm-Inspired Agents for Scalable and Adaptive Reasoning"
    Li et al. arXiv 2025. [paper]
  • "AFlow: Automating Agentic Workflow Generation"
    Zhang et al. ICLR 2025. [paper]
  • "Symbolic Learning Enables Self-Evolving Agents"
    Zhou et al. AI Open 2025. [paper]

Whole-system

  • "AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents"
    Wang et al. arXiv 2026. [paper]
  • "Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing"
    Weng et al. arXiv 2026. [paper]
  • "ASI-Evolve: AI Accelerates AI"
    Xu et al. arXiv 2026. [paper]
  • "Learning to Continually Learn via Meta-learning Agentic Memory Designs"
    Xiong et al. arXiv 2026. [paper]
  • "AgentDevel: Reframing Self-Evolving LLM Agents as Release Engineering"
    Zhang arXiv 2026. [paper]
  • "A Self-Improving Coding Agent"
    Robeyns et al. arXiv 2025. [paper]
  • "Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents"
    Zhang et al. arXiv 2025. [paper]

Domain-specific

  • "Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC"
    Yu et al. arXiv 2026. [paper]
  • "Self-Evolving Recommendation System: End-To-End Autonomous Model Optimization With LLM Agents"
    Wang et al. arXiv 2026. [paper]

Configuration

  • "JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents"
    Ghoshal et al. arXiv 2026. [paper]
  • "Symphony-Coord: Emergent Coordination in Decentralized Agent Systems"
    Guan et al. arXiv 2026. [paper]
  • "Evolving Excellence: Automated Optimization of LLM-based Agents"
    Brookes et al. arXiv 2025. [paper]

Framework & analysis

  • "Position: Agentic Evolution is the Path to Evolving LLMs"
    Lin et al. arXiv 2026. [paper]
  • "Understanding the Challenges in Iterative Generative Optimization with LLMs"
    Nie et al. arXiv 2026. [paper]

Δ, H≠0 (Structural, Human-involved)

Tools & skills

  • "SkillClaw: Let Skills Evolve Collectively with Agentic Evolver"
    Ma et al. arXiv 2026. [paper]
  • "EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation"
    Zhang et al. arXiv 2026. [paper]
  • "Leveraging LLMs for Dynamic IoT Systems Generation through Mixed-Initiative Interaction"
    Adnan et al. ICSA-C 2025. [paper]
  • "Democratizing AI scientists using ToolUniverse"
    Gao et al. arXiv 2025. [paper]

∇, H=0 (Parametric, Autonomous)

  • "Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning"
    Jiang et al. arXiv 2026. [paper]
  • "π0: A Vision-Language-Action Flow Model for General Robot Control"
    Black et al. RSS 2025. [paper]
  • "RouteLLM: Learning to Route LLMs with Preference Data"
    Ong et al. ICLR 2025. [paper]

Δ+∇, H=0 (Hybrid, Autonomous)

  • "SEVerA: Verified Self-Evolving Agents"
    Banerjee et al. arXiv 2026. [paper]
  • "Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence"
    Dong et al. arXiv 2026. [paper]
  • "SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents"
    Feng et al. arXiv 2026. [paper]
  • "EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering"
    Huang et al. arXiv 2026. [paper]
  • "SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology"
    Nie et al. arXiv 2026. [paper]
  • "HELIX: Evolutionary Reinforcement Learning for Open-Ended Scientific Problem Solving"
    Su et al. ICLR 2026. [paper]
  • "Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks"
    Wu et al. arXiv 2026. [paper]
  • "SkillOS: Learning Skill Curation for Self-Evolving Agents"
    Ouyang et al. arXiv 2026. [paper]
  • "Reinforcement Learning for Self-Improving Agent with Skill Library"
    Wang et al. arXiv 2025. [paper]
  • "InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios"
    Yu et al. arXiv 2025. [paper]
  • "AutoFlow: Automated Workflow Generation for Large Language Model Agents"
    Li et al. arXiv 2024. [paper]

Memory & Sense (M) Evolution

Δ, H=0 (Structural, Autonomous)

Accumulation:Task-oriented

  • "AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents"
    Bao et al. arXiv 2026. [paper]
  • "Mem^2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation"
    Cheng et al. arXiv 2026. [paper]
  • "KernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning"
    Dong et al. arXiv 2026. [paper]
  • "Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement"
    Fang et al. arXiv 2026. [paper]
  • "AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models"
    Gautam et al. arXiv 2026. [paper]
  • "OpenGame: Open Agentic Coding for Games"
    Jiang et al. arXiv 2026. [paper]
  • "Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents"
    Kim et al. arXiv 2026. [paper]
  • "Experience Transfer for Multimodal LLM Agents in Minecraft Game"
    Li et al. arXiv 2026. [paper]
  • "Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts"
    Li et al. arXiv 2026. [paper]
  • "Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates"
    Li et al. arXiv 2026. [paper]
  • "Learning to Commit: Generating Organic Pull Requests via Online Repository Memory"
    Li et al. arXiv 2026. [paper]
  • "Towards Self-Improving Error Diagnosis in Multi-Agent Systems"
    Li et al. arXiv 2026. [paper]
  • "GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)"
    Liang et al. arXiv 2026. [paper]
  • "Position: Agentic Evolution is the Path to Evolving LLMs"
    Lin et al. arXiv 2026. [paper]
  • "EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery"
    Lyu et al. arXiv 2026. [paper]
  • "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory"
    Ouyang et al. ICLR 2026. [paper]
  • "MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning"
    Bai et al. ALTA 2025. [paper]
  • "Building Self-Evolving Agents via Experience-Driven Lifelong Learning: A Framework and Benchmark"
    Cai et al. arXiv 2025. [paper]
  • "FLEX: Continuous Agent Evolution via Forward Learning from Experience"
    Cai et al. arXiv 2025. [paper]
  • "Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution"
    Cao et al. arXiv 2025. [paper]
  • "MDTeamGPT: A Self-Evolving LLM-based Multi-Agent Framework for Multi-Disciplinary Team Medical Consultation"
    Chen et al. arXiv 2025. [paper]
  • "Memp: Exploring Agent Procedural Memory"
    Fang et al. arXiv 2025. [paper]
  • "Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks"
    Sarukkai et al. arXiv 2025. [paper]
  • "Agent Workflow Memory"
    Wang et al. ICML 2025. [paper]
  • "Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory"
    Wei et al. arXiv 2025. [paper]
  • "Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents"
    Li et al. arXiv 2024. [paper]
  • "ToolChain: Efficient Action Space Navigation in Large Language Models with A Search"**
    Zhuang et al. ICLR 2024. [paper]

Accumulation:Embodied

  • "Evolvable Embodied Agent for Robotic Manipulation via Long Short-Term Reflection and Optimization"
    Wang et al. arXiv 2026. [paper]
  • "ELITE: Experiential Learning and Intent-Aware Transfer for Self-improving Embodied Agents"
    Wei et al. arXiv 2026. [paper]
  • "MineEvolve: Self-Evolution with Accumulated Knowledge for Long-Horizon Embodied Minecraft Agents"
    Xie et al. arXiv 2026. [paper]

Accumulation:Game-strategic

  • "Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios"
    Ma et al. arXiv 2026. [paper]
  • "MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games"
    Xie et al. arXiv 2026. [paper]
  • "Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy"
    Guan et al. NeurIPS 2024. [paper]

Accumulation:Domain-specific

  • "GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoning"
    Han et al. arXiv 2026. [paper]
  • "OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence"
    Liu et al. arXiv 2026. [paper]
  • "Emulating Clinician Cognition via Self-Evolving Deep Clinical Research"
    Ren et al. arXiv 2026. [paper]
  • "Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve"
    Shen et al. arXiv 2026. [paper]
  • "PhysNote: Self-Knowledge Notes for Evolvable Physical Reasoning in Vision-Language Model"
    Zhang et al. arXiv 2026. [paper]
  • "HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research"
    Zhu et al. arXiv 2025. [paper]

Accumulation:Multi-agent

  • "CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery"
    Qu et al. arXiv 2026. [paper]
  • "AutoAgent: Evolving Cognition and Elastic Memory Orchestration for Adaptive Agents"
    Wang et al. arXiv 2026. [paper]
  • "Forage V2: Knowledge Evolution and Transfer in Autonomous Agent Organizations"
    Xie arXiv 2026. [paper]
  • "G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems"
    Zhang et al. arXiv 2025. [paper]

Accumulation:Research/discovery

  • "OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery"
    Liu et al. arXiv 2026. [paper]
  • "AI-Supervisor: Autonomous AI Research Supervision via a Persistent Research World Model"
    Long arXiv 2026. [paper]
  • "ASI-Evolve: AI Accelerates AI"
    Xu et al. arXiv 2026. [paper]

Accumulation:Conversational/persona

  • "EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution"
    He et al. arXiv 2026. [paper]
  • "Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization"
    Kwon et al. ICLR 2026. [paper]
  • "Choosing How to Remember: Adaptive Memory Structures for LLM Agents"
    Lu et al. arXiv 2026. [paper]
  • "GAM: Hierarchical Graph-based Agentic Memory for LLM Agents"
    Wu et al. arXiv 2026. [paper]
  • "Lightweight LLM Agent Memory with Small Language Models"
    Zhang et al. ACL 2026. [paper]
  • "To Know is to Construct: Schema-Constrained Generation for Agent Memory"
    Zheng et al. arXiv 2026. [paper]
  • "HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents"
    Zhu et al. arXiv 2026. [paper]
  • "What Deserves Memory: Adaptive Memory Distillation for LLM Agents"
    Ma et al. arXiv 2025. [paper]
  • "A-MEM: Agentic Memory for LLM Agents"
    Xu et al. NeurIPS 2025. [paper]
  • "Generative Agents: Interactive Simulacra of Human Behavior"
    Park et al. UIST 2023. [paper]

Curation/operators

  • "MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution"
    Lin et al. arXiv 2026. [paper]
  • "PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent"
    Wang et al. arXiv 2026. [paper]
  • "Live-Evo: Online Evolution of Agentic Memory from Continuous Feedback"
    Zhang et al. arXiv 2026. [paper]
  • "EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines"
    Zhang et al. arXiv 2026. [paper]
  • "Memento 2: Learning by Stateful Reflective Memory"
    Wang arXiv 2025. [paper]
  • "AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization"
    Zhang et al. arXiv 2025. [paper]

Forgetting/lifecycle

  • "ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems"
    Bering arXiv 2026. [paper]
  • "FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory"
    Gu et al. arXiv 2026. [paper]
  • "When to Forget: A Memory Governance Primitive"
    Simsek arXiv 2026. [paper]
  • "AEL: Agent Evolving Learning for Open-Ended Environments"
    Xu et al. arXiv 2026. [paper]

Meta-evolution

  • "Prism: An Evolutionary Memory Substrate for Multi-Agent Open-Ended Discovery"
    Mishra arXiv 2026. [paper]
  • "M★: Every Task Deserves Its Own Memory Harness"
    Pan et al. arXiv 2026. [paper]
  • "MemEvolve: Meta-Evolution of Agent Memory Systems"
    Zhang et al. arXiv 2025. [paper]

Retrieval innovation

  • "Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems"
    Feng et al. TMLR 2026. [paper]
  • "ROZA Graphs: Self-Improving Near-Deterministic RAG through Evidence-Centric Feedback"
    Penaroza arXiv 2026. [paper]
  • "Latent Preference Modeling for Cross-Session Personalized Tool Calling"
    Yoon et al. arXiv 2026. [paper]
  • "Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models"
    Yang et al. NeurIPS 2024. [paper]

Sense/compression

  • "A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression"
    Ren et al. arXiv 2026. [paper]

Δ, H≠0 (Structural, Human-involved)

Conversational/persona

  • "Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo"
    Gadzhiev et al. arXiv 2026. [paper]
  • "PersonaVLM: Long-Term Personalized Multimodal LLMs"
    Nie et al. arXiv 2026. [paper]
  • "Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory"
    Chhikara et al. arXiv 2025. [paper]
  • "Zep: A Temporal Knowledge Graph Architecture for Agent Memory"
    Rasmussen et al. arXiv 2025. [paper]
  • "RGMem: Renormalization Group-inspired Memory Evolution for Language Agents"
    Tian et al. arXiv 2025. [paper]
  • "Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles"
    Westhäusser et al. arXiv 2025. [paper]
  • "MemoryBank: Enhancing Large Language Models with Long-Term Memory"
    Zhong et al. AAAI 2024. [paper]
  • "MemGPT: Towards LLMs as Operating Systems"
    Packer et al. arXiv 2023. [paper]

Human-in-the-loop

  • "SkinGPT-X: A Self-Evolving Collaborative Multi-Agent System for Transparent and Trustworthy Dermatological Diagnosis"
    Chen et al. arXiv 2026. [paper]
  • "Your Code Agent Can Grow Alongside You with Structured Memory"
    Deng et al. arXiv 2026. [paper]
  • "EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation"
    Zhang et al. arXiv 2026. [paper]
  • "Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance"
    He et al. EMNLP 2025. [paper]
  • "Magentic-UI: Towards Human-in-the-loop Agentic Systems"
    Mozannar et al. arXiv 2025. [paper]

∇, H=0 (Parametric, Autonomous)

World models (Sense)

  • "Self-Improving World Modelling with Latent Actions"
    Qiu et al. arXiv 2026. [paper]
  • "Mastering Diverse Control Tasks through World Models"
    Hafner et al. Nature 2025. [paper]
  • "Recurrent World Models Facilitate Policy Evolution"
    Ha et al. NeurIPS 2018. [paper]

Memory fine-tuning

  • "Learning to (Learn at Test Time): RNNs with Expressive Hidden States"
    Sun et al. ICML 2025. [paper]
  • "Continual Learning via Sparse Memory Finetuning"
    Lin et al. arXiv 2025. [paper]

Δ+∇, H=0 (Hybrid, Autonomous)

Memory+RL

  • "Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents"
    Cai et al. arXiv 2026. [paper]
  • "SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation"
    Kim et al. arXiv 2026. [paper]
  • "VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction"
    Liao et al. arXiv 2026. [paper]
  • "Memory Intelligence Agent"
    Qiao et al. arXiv 2026. [paper]
  • "SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training"
    Wang et al. arXiv 2026. [paper]
  • "SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning"
    Xia et al. arXiv 2026. [paper]
  • "Self-Consolidation for Self-Evolving Agents"
    Yu et al. arXiv 2026. [paper]
  • "MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents"
    Zhang et al. arXiv 2026. [paper]
  • "RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback"
    Zhang et al. arXiv 2026. [paper]
  • "EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle"
    Wu et al. arXiv 2025. [paper]
  • "AgentEvolver: Towards Efficient Self-Evolving Agent System"
    Zhai et al. arXiv 2025. [paper]
  • "Memento: Fine-tuning LLM Agents without Fine-tuning LLMs"
    Zhou et al. arXiv 2025. [paper]

Domain hybrid

  • "S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research"
    Team arXiv 2026. [paper]
  • "PsychAgent: An Experience-Driven Lifelong Learning Agent for Self-Evolving Psychological Counselor"
    Yang et al. arXiv 2026. [paper]
  • "Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration"
    Zhang et al. arXiv 2026. [paper]
  • "EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks"
    Feng et al. arXiv 2025. [paper]

Contributing

Contributions are welcome. Please open a pull request or issue to suggest papers.

About

No description, website, or topics provided.

Resources

License

Stars

4 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors