{"total":75,"rows":[{"id":"2602.08234","title":"SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning","created":"2026-02-09","cited_by_count":278,"area":"lr"},{"id":"2601.02553","title":"SimpleMem: Efficient Lifelong Memory for LLM Agents","created":"2026-01-05","cited_by_count":149,"area":"agents"},{"id":"2601.07055","title":"Dr. Zero: Self-Evolving Search Agents without Training Data","created":"2026-01-11","cited_by_count":44,"area":"agents"},{"id":"2607.07663","title":"Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops","created":"2026-07-08","cited_by_count":35,"area":null},{"id":"2602.21320","title":"Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data","created":"2026-02-24","cited_by_count":34,"area":"agents"},{"id":"2511.19900","title":"Agent0-VL: Exploring Self-Evolving Agent for Tool-Integrated Vision-Language Reasoning","created":"2025-11-25","cited_by_count":31,"area":"lr"},{"id":"2605.06716","title":"From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms","created":"2026-05-07","cited_by_count":21,"area":"agents"},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2602.00359","title":"Position: Agentic Evolution is the Path to Evolving LLMs","created":"2026-01-30","cited_by_count":16,"area":"agents"},{"id":"2601.22154","title":"Exploring Reasoning Reward Model for Agents","created":"2026-01-29","cited_by_count":15,"area":"agents"},{"id":"2604.19572","title":"A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression","created":"2026-04-21","cited_by_count":15,"area":"inference"},{"id":"2606.30639","title":"Self-Evolving World Models for LLM Agent Planning","created":"2026-06-29","cited_by_count":13,"area":"wm"},{"id":"2608.19880","title":"EnvHarness: Awakening Static Worlds for Agent Learning","created":"2026-08-20","cited_by_count":13,"area":"agents"},{"id":"2603.17775","title":"CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution","created":"2026-03-18","cited_by_count":12,"area":"lr"},{"id":"2605.10913","title":"Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces","created":"2026-05-11","cited_by_count":12,"area":"agents"},{"id":"2604.04202","title":"ClawArena: Benchmarking AI Agents in Evolving Information Environments","created":"2026-04-05","cited_by_count":11,"area":"agents"},{"id":"2604.20209","title":"Scaling Self-Play with Self-Guidance","created":"2026-04-22","cited_by_count":10,"area":"synth"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2608.04003","title":"PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents","created":"2026-08-04","cited_by_count":9,"area":null},{"id":"2609.15364","title":"RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments","created":"2026-09-14","cited_by_count":8,"area":"synth"},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2602.03548","title":"SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue","created":"2026-02-03","cited_by_count":7,"area":"agents"},{"id":"2602.06448","title":"Principle-Evolvable Scientific Discovery via Uncertainty Minimization","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2607.29468","title":"Self-Play Meets Skill Evolution: Self-Evolving Search Agents that Pose, Solve, and Remember","created":"2026-07-31","cited_by_count":7,"area":null},{"id":"2603.15255","title":"SAGE: Multi-Agent Self-Evolution for LLM Reasoning","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2607.10113","title":"Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries","created":"2026-07-11","cited_by_count":6,"area":"agents"},{"id":"2605.08703","title":"RewardHarness: Self-Evolving Agentic Post-Training","created":"2026-05-09","cited_by_count":5,"area":"agents"},{"id":"2604.00835","title":"Agentic Tool Use in Large Language Models","created":"2026-04-01","cited_by_count":4,"area":"agents"},{"id":"2606.04703","title":"Rethinking Continual Experience Internalization for Self-Evolving LLM Agents","created":"2026-06-03","cited_by_count":4,"area":"lr"},{"id":"2608.24747","title":"SkillForge: Evolving Verifiable Skills for Reinforcement Learning Agents","created":"2026-08-25","cited_by_count":4,"area":"lr"},{"id":"2512.12658","title":"CogDoc: Towards Unified thinking in Documents","created":"2025-12-14","cited_by_count":3,"area":null},{"id":"2605.13880","title":"PREPING: Zero-Task Agent Memory Construction via Self-Practice","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2607.17558","title":"Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?","created":"2026-07-20","cited_by_count":3,"area":"agents"},{"id":"2602.04411","title":"Self-evolving Embodied AI","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2604.14609","title":"El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation","created":"2026-04-16","cited_by_count":2,"area":"agents"},{"id":"2605.06326","title":"Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.10064","title":"MAGE: Multi-Agent Self-Evolution with Co-Evolutionary Knowledge Graphs","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.14212","title":"MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learning","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2606.07127","title":"Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes","created":"2026-06-05","cited_by_count":2,"area":"wm"},{"id":"2608.14015","title":"MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning","created":"2026-08-14","cited_by_count":2,"area":"lr"},{"id":"2609.20056","title":"MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution","created":"2026-09-17","cited_by_count":2,"area":null},{"id":"2602.22426","title":"SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read","created":"2026-02-25","cited_by_count":1,"area":"mllm"},{"id":"2603.16843","title":"Internalizing Agency from Reflective Experience","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.11636","title":"Seir\\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.17721","title":"EXG: Self-Evolving Agents with Experience Graphs","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2605.20914","title":"RISE: Reliable Improvement in Self-Evolving Vision-Language Models","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.28773","title":"Rethinking Memory as Continuously Evolving Connectivity","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2607.09025","title":"Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.01742","title":"MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2608.10299","title":"Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2609.00768","title":"Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Models","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2610.08327","title":"MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation","created":"2026-10-06","cited_by_count":1,"area":"lr"},{"id":"2610.11345","title":"SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning","created":"2026-10-08","cited_by_count":1,"area":"agents"},{"id":"2602.06975","title":"BiomechAgent: AI-Assisted Biomechanical Analysis Through Code-Generating Agents","created":"2026-01-16","cited_by_count":0,"area":"agents"},{"id":"2604.07378","title":"Evaluation as Evolution: Transforming Adversarial Diffusion into Closed-Loop Curricula for Autonomous Vehicles","created":"2026-04-08","cited_by_count":0,"area":"driving"},{"id":"2605.11666","title":"Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2607.14108","title":"Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2607.23124","title":"AgentOmnia: Scaling Agentic Models for Full-Scenario Applications","created":"2026-07-25","cited_by_count":0,"area":"agents"},{"id":"2607.27360","title":"SkillMentor: LLM Agent Self-Evolution via Learning Blind-Spot Diagnosis","created":"2026-07-29","cited_by_count":0,"area":"agents"},{"id":"2608.06216","title":"Continual Learning in Transition","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.10530","title":"On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models","created":"2026-08-11","cited_by_count":0,"area":"agents"},{"id":"2609.20089","title":"UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.30450","title":"LensDesigner: A Self-Improving Agent for Optical Lens Design","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32423","title":"PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34279","title":"Direct Self-Evolving Optimization: Evolving LLMs without Challenger Training","created":"2026-09-28","cited_by_count":0,"area":"synth"},{"id":"2609.34682","title":"V-Gym: Enhancing Agentic Visual Reasoning via Skill-Data Co-Evolution","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.08773","title":"AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model","created":"2026-10-06","cited_by_count":0,"area":"wm"},{"id":"2610.09856","title":"Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.10183","title":"VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.11803","title":"PRAXIS: Learning Dynamics of Self-Improving Models with Symbolic Archives","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12593","title":"Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning","created":"2026-10-08","cited_by_count":0,"area":"agents"},{"id":"2610.13912","title":"RSI-Anything: Unlocking Recursive Self-Improvement with World Models","created":"2026-10-09","cited_by_count":0,"area":"wm"},{"id":"2610.14118","title":"ClawLoop: Self-Improving Agents via Harness-Native Training Loop","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14163","title":"AutoEnvScaling: Automating the Data Flywheel with Terminal Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.15084","title":"Self-Evolving Visual Agent via Margin Reward","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}