{"total":86,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2510.05592","title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use","created":"2025-10-07","cited_by_count":72,"area":"lr"},{"id":"2504.16129","title":"MARFT: Multi-Agent Reinforcement Fine-Tuning","created":"2025-04-21","cited_by_count":52,"area":"agents"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37,"area":"agents"},{"id":"2510.08529","title":"CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards","created":"2025-10-09","cited_by_count":29,"area":"agents"},{"id":"2510.11062","title":"Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs","created":"2025-10-13","cited_by_count":28,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2504.16918","title":"OptimAI: Optimization from Natural Language Using LLM-Powered AI Agents","created":"2025-04-23","cited_by_count":22,"area":"agents"},{"id":"2509.03817","title":"Learning to Deliberate: Meta-policy Collaboration for Agentic LLMs with Multi-agent Reinforcement Learning","created":"2025-09-04","cited_by_count":18,"area":"lr"},{"id":"2511.13288","title":"Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO","created":"2025-11-17","cited_by_count":18,"area":"lr"},{"id":"2602.08847","title":"Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":16,"area":"lr"},{"id":"2603.02604","title":"Heterogeneous Agent Collaborative Reinforcement Learning","created":"2026-03-03","cited_by_count":15,"area":"agents"},{"id":"2511.06134","title":"Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs","created":"2025-11-08","cited_by_count":14,"area":"agents"},{"id":"2511.02755","title":"Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning","created":"2025-11-04","cited_by_count":13,"area":"agents"},{"id":"2507.08960","title":"How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMs","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2603.21563","title":"Counterfactual Credit Policy Optimization for Multi-Agent Collaboration","created":"2026-03-23","cited_by_count":10,"area":"lr"},{"id":"2509.23537","title":"Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarks","created":"2025-09-28","cited_by_count":9,"area":"agents"},{"id":"2603.07972","title":"Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning","created":"2026-03-09","cited_by_count":9,"area":"agents"},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","cited_by_count":8,"area":"agents"},{"id":"2602.13840","title":"PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training","created":"2026-02-14","cited_by_count":7,"area":"agents"},{"id":"2511.19524","title":"VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learning","created":"2025-11-24","cited_by_count":6,"area":"mllm"},{"id":"2601.21742","title":"Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems","created":"2026-01-29","cited_by_count":6,"area":"agents"},{"id":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2509.26306","title":"Interactive Learning for LLM Reasoning","created":"2025-09-30","cited_by_count":5,"area":"lr"},{"id":"2510.01586","title":"AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning","created":"2025-10-02","cited_by_count":5,"area":"agents"},{"id":"2605.02801","title":"Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces","created":"2026-05-04","cited_by_count":5,"area":"agents"},{"id":"2606.02859","title":"Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions","created":"2026-06-01","cited_by_count":5,"area":null},{"id":"2506.08234","title":"Compound AI Systems Optimization: A Survey of Methods, Challenges, and Future Directions","created":"2025-06-09","cited_by_count":4,"area":null},{"id":"2508.02076","title":"Everyone Contributes! Incentivizing Strategic Cooperation in Multi-LLM Systems via Sequential Public Goods Games","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2508.03864","title":"Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety","created":"2025-08-05","cited_by_count":4,"area":"agents"},{"id":"2605.11136","title":"EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2509.08721","title":"Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2509.24323","title":"MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems","created":"2025-09-29","cited_by_count":3,"area":"agents"},{"id":"2601.09667","title":"Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning","created":"2026-01-14","cited_by_count":3,"area":"lr"},{"id":"2602.07848","title":"MARTI-MARS$^2$: Scaling Multi-Agent Self-Search via Reinforcement Learning for Code Generation","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2607.26212","title":"Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2511.19405","title":"Learning Robust Social Strategies with Large Language Models","created":"2025-11-24","cited_by_count":2,"area":"agents"},{"id":"2601.21473","title":"ScaleSim: Serving Large-Scale Multi-Agent Simulation with Invocation Distance-Based Memory Management","created":"2026-01-29","cited_by_count":2,"area":"agents"},{"id":"2601.23228","title":"Scaling Multiagent Systems with Process Rewards","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2602.16154","title":"Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution","created":"2026-02-18","cited_by_count":2,"area":"lr"},{"id":"2602.21515","title":"Training Generalizable Collaborative Agents via Strategic Risk Aversion","created":"2026-02-25","cited_by_count":2,"area":"agents"},{"id":"2603.15798","title":"CUBE: A Standard for Unifying Agent Benchmarks","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.21574","title":"Adaptive Robust Estimator for Multi-Agent Reinforcement Learning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2604.13488","title":"Towards Scalable Lightweight GUI Agents via Multi-role Orchestration","created":"2026-04-15","cited_by_count":2,"area":"mllm"},{"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":"2606.10684","title":"Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning Signals","created":"2026-06-09","cited_by_count":2,"area":"agents"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2508.10839","title":"Reinforced Language Models for Sequential Decision Making","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2511.02157","title":"Near Optimal Convergence to Coarse Correlated Equilibrium in General-Sum Markov Games","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.20629","title":"Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning","created":"2025-11-28","cited_by_count":1,"area":"agents"},{"id":"2603.12631","title":"Joint Optimization of Multi-agent Memory System","created":"2026-03-13","cited_by_count":1,"area":"agents"},{"id":"2603.16876","title":"Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2604.14564","title":"MARS$^2$: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.04811","title":"Tree-based Credit Assignment for Multi-Agent Memory System","created":"2026-05-06","cited_by_count":1,"area":"agents"},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.03032","title":"The Deliberative Illusion: Diagnosing Factual Attrition and Stance Homogenization in Multi-Agent LLM Deliberation","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.14368","title":"Be My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer Feedback","created":"2026-06-12","cited_by_count":1,"area":"distill"},{"id":"2607.10836","title":"Route, Communicate, and Reason: Gated Routing and Adaptive Depth for Efficient Multi-Agent Reasoning","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2607.13558","title":"Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling","created":"2026-07-15","cited_by_count":1,"area":null},{"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":"2605.03125","title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.04906","title":"Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.08626","title":"Large Language Models over Networks: Collaborative Intelligence under Resource Constraints","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.12943","title":"Reinforced Collaboration in Multi-Agent Flow Networks","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2606.05002","title":"GARL: Game-Theoretic Reinforcement Learning for Multi-Agent Strategic Prioritisation","created":"2026-06-03","cited_by_count":0,"area":"agents"},{"id":"2607.06935","title":"Mathematical methods of reinforcement learning","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2607.18006","title":"MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.07148","title":"A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.22132","title":"SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning","created":"2026-08-22","cited_by_count":0,"area":"agents"},{"id":"2609.04217","title":"At Equal Inference Cost, Multi-Agent Structure Does Not Beat a Single Frozen Agent","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2609.08452","title":"SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs","created":"2026-09-08","cited_by_count":0,"area":"agents"},{"id":"2609.18779","title":"CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.32827","title":"Improving LLM Collaboration via Multi-Agent Preference Learning","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.35928","title":"Prompted Identity Degrades Cooperation in Multi-Agent LLM Systems","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2610.01026","title":"It Takes Workflows to Evolve Better Workflows","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04074","title":"IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.12927","title":"Collaborative Learning and Reasoning over Model Slices","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.17456","title":"Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning","created":"2026-10-12","cited_by_count":0,"area":"lr"},{"id":"2610.17893","title":"Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19133","title":"TRACER: Trace-Regularized Training Against Indirect Prompt Injection","created":"2026-10-13","cited_by_count":0,"area":"safety"},{"id":"2610.19422","title":"AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}