{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2307.07924","title":"ChatDev: Communicative Agents for Software Development","created":"2023-07-16","cited_by_count":919},{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"2503.13657","title":"Why Do Multi-Agent LLM Systems Fail?","created":"2025-03-17","cited_by_count":604},{"id":"1706.05296","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning","created":"2017-06-16","cited_by_count":503},{"id":"2003.08839","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","created":"2020-03-19","cited_by_count":485},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333},{"id":"2011.09533","title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","created":"2020-11-18","cited_by_count":294},{"id":"2008.01062","title":"QPLEX: Duplex Dueling Multi-Agent Q-Learning","created":"2020-08-03","cited_by_count":270},{"id":"2501.03262","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","created":"2025-01-04","cited_by_count":241},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193},{"id":"2505.00212","title":"Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems","created":"2025-04-30","cited_by_count":185},{"id":"2503.01935","title":"MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents","created":"2025-03-03","cited_by_count":178},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"2309.15943","title":"Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?","created":"2023-09-27","cited_by_count":106},{"id":"2501.05707","title":"Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains","created":"2025-01-10","cited_by_count":95},{"id":"2504.00587","title":"AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems","created":"2025-04-01","cited_by_count":90},{"id":"2502.20379","title":"Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers","created":"2025-02-27","cited_by_count":62},{"id":"2508.17445","title":"TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling","created":"2025-08-24","cited_by_count":61},{"id":"2102.04402","title":"Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning","created":"2021-02-08","cited_by_count":56},{"id":"2409.03052","title":"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning","created":"2024-09-04","cited_by_count":50},{"id":"2303.14100","title":"Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting","created":"2023-03-24","cited_by_count":46},{"id":"2506.05183","title":"TreeRPO: Tree Relative Policy Optimization","created":"2025-06-05","cited_by_count":46},{"id":"2502.04780","title":"SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning","created":"2025-02-07","cited_by_count":44},{"id":"2501.15228","title":"Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning","created":"2025-01-25","cited_by_count":39},{"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},{"id":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31},{"id":"2308.10502","title":"GradientCoin: A Peer-to-Peer Decentralized Large Language Models","created":"2023-08-21","cited_by_count":23},{"id":"2502.04510","title":"Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems","created":"2025-02-06","cited_by_count":23},{"id":"2502.06060","title":"Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning","created":"2025-02-09","cited_by_count":16},{"id":"2509.16736","title":"Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach","created":"2025-09-20","cited_by_count":12},{"id":"2601.04703","title":"Beyond Monolithic Architectures: A Multi-Agent Search and Knowledge Optimization Framework for Agentic Search","created":"2026-01-08","cited_by_count":11},{"id":"2408.14597","title":"On Centralized Critics in Multi-Agent Reinforcement Learning","created":"2024-08-26","cited_by_count":10},{"id":"2502.17821","title":"CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems","created":"2025-02-25","cited_by_count":6},{"id":"2111.01100","title":"Investigation of Independent Reinforcement Learning Algorithms in Multi-Agent Environments","created":"2021-11-01","cited_by_count":5},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5},{"id":"2501.14784","title":"DeServe: Towards Affordable Offline LLM Inference via Decentralization","created":"2025-01-04","cited_by_count":4},{"id":"2505.10484","title":"Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning","created":"2025-05-15","cited_by_count":1}],"next_cursor":null}