{"list":"other","total":51,"rows":[{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2308.00352","title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","created":"2023-08-01","cited_by_count":1808},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"2305.19118","title":"Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate","created":"2023-05-30","cited_by_count":1011},{"id":"2402.01680","title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","created":"2024-01-21","cited_by_count":769},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2406.04692","title":"Mixture-of-Agents Enhances Large Language Model Capabilities","created":"2024-06-07","cited_by_count":438},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2306.03314","title":"Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents","created":"2023-06-05","cited_by_count":333},{"id":"2307.10635","title":"SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models","created":"2023-07-20","cited_by_count":256},{"id":"2406.07155","title":"Scaling Large Language Model-based Multi-Agent Collaboration","created":"2024-06-11","cited_by_count":241},{"id":"2411.04468","title":"Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks","created":"2024-11-07","cited_by_count":232},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228},{"id":"2502.08691","title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","created":"2025-02-12","cited_by_count":186},{"id":"2502.04180","title":"Multi-agent Architecture Search via Agentic Supernet","created":"2025-02-06","cited_by_count":179},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2411.11581","title":"OASIS: Open Agent Social Interaction Simulations with One Million Agents","created":"2024-11-18","cited_by_count":132},{"id":"2408.00989","title":"On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents","created":"2024-08-02","cited_by_count":99},{"id":"2407.07791","title":"Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities","created":"2024-07-10","cited_by_count":86},{"id":"2401.11880","title":"PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety","created":"2024-01-22","cited_by_count":80},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79},{"id":"1911.03347","title":"Macro F1 and Macro F1","created":"2019-11-08","cited_by_count":70},{"id":"2502.11127","title":"G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems","created":"2025-02-16","cited_by_count":59},{"id":"2506.01716","title":"Self-Challenging Language Model Agents","created":"2025-06-02","cited_by_count":59},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54},{"id":"2508.03682","title":"Self-Questioning Language Models","created":"2025-08-05","cited_by_count":50},{"id":"2410.15686","title":"NetSafe: Exploring the Topological Safety of Multi-agent Networks","created":"2024-10-21","cited_by_count":29},{"id":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27},{"id":"2508.09101","title":"AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators","created":"2025-08-12","cited_by_count":26},{"id":"2505.07215","title":"Measuring General Intelligence with Generated Games","created":"2025-05-12","cited_by_count":24},{"id":"2508.08791","title":"Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments","created":"2025-08-12","cited_by_count":19},{"id":"2505.16988","title":"MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systems","created":"2025-05-22","cited_by_count":14},{"id":"2407.08995","title":"Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs","created":"2024-07-12","cited_by_count":12},{"id":"2506.00509","title":"Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems","created":"2025-05-31","cited_by_count":8},{"id":"2506.04572","title":"Demonstrations of Integrity Attacks in Multi-Agent Systems","created":"2025-06-05","cited_by_count":8},{"id":"2508.17711","title":"Enhancing LLM-Based Social Bot via an Adversarial Learning Framework","created":"2025-08-25","cited_by_count":7},{"id":"1903.08132","title":"ExplainIt! -- A declarative root-cause analysis engine for time series data (extended version)","created":"2019-03-19","cited_by_count":6}],"next_cursor":null}