{"list":"other","total":73,"rows":[{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"2305.14325","title":"Improving Factuality and Reasoning in Language Models through Multiagent Debate","created":"2023-05-23","cited_by_count":1784},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2412.05579","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","created":"2024-12-07","cited_by_count":465},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431},{"id":"2402.19473","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","created":"2024-02-29","cited_by_count":354},{"id":"2309.13007","title":"ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs","created":"2023-09-22","cited_by_count":309},{"id":"2310.02170","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","created":"2023-10-03","cited_by_count":290},{"id":"2307.05300","title":"Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration","created":"2023-07-11","cited_by_count":251},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205},{"id":"1908.06177","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","created":"2019-08-16","cited_by_count":162},{"id":"2402.18272","title":"Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?","created":"2024-02-28","cited_by_count":159},{"id":"2307.02762","title":"PRD: Peer Rank and Discussion Improve Large Language Model based Evaluations","created":"2023-07-06","cited_by_count":114},{"id":"2406.11776","title":"Improving Multi-Agent Debate with Sparse Communication Topology","created":"2024-06-17","cited_by_count":107},{"id":"2305.11595","title":"Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate","created":"2023-05-19","cited_by_count":97},{"id":"2502.18439","title":"MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learning","created":"2025-02-25","cited_by_count":86},{"id":"2312.01823","title":"Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication","created":"2023-12-04","cited_by_count":82},{"id":"2210.16257","title":"Solving Math Word Problems via Cooperative Reasoning induced Language Models","created":"2022-10-28","cited_by_count":77},{"id":"2310.00280","title":"Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration","created":"2023-09-30","cited_by_count":70},{"id":"2405.06373","title":"LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play","created":"2024-05-10","cited_by_count":66},{"id":"2503.22458","title":"Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey","created":"2025-03-28","cited_by_count":57},{"id":"2310.06272","title":"Let Models Speak Ciphers: Multiagent Debate through Embeddings","created":"2023-10-10","cited_by_count":51},{"id":"2311.08152","title":"Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration","created":"2023-11-14","cited_by_count":51},{"id":"2309.09530","title":"Adapting Large Language Models to Domains via Reading Comprehension","created":"2023-09-18","cited_by_count":50},{"id":"2402.01620","title":"MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models","created":"2024-02-02","cited_by_count":43},{"id":"2408.15232","title":"Into the Unknown Unknowns: Engaged Human Learning through Participation in Language Model Agent Conversations","created":"2024-08-27","cited_by_count":43},{"id":"2405.20267","title":"Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions","created":"2024-05-30","cited_by_count":42},{"id":"2411.03284","title":"SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents","created":"2024-11-05","cited_by_count":30},{"id":"2505.18581","title":"Removal of Hallucination on Hallucination: Debate-Augmented RAG","created":"2025-05-24","cited_by_count":29},{"id":"2404.09127","title":"Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation","created":"2024-04-14","cited_by_count":26},{"id":"2310.01331","title":"ChoiceMates: Supporting Unfamiliar Online Decision-Making with Multi-Agent Conversational Interactions","created":"2023-10-02","cited_by_count":22},{"id":"2401.14589","title":"Enhancing Diagnostic Accuracy through Multi-Agent Conversations: Using Large Language Models to Mitigate Cognitive Bias","created":"2024-01-26","cited_by_count":20},{"id":"2403.19305","title":"MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation","created":"2024-03-28","cited_by_count":20},{"id":"2406.03075","title":"Towards Detecting LLMs Hallucination via Markov Chain-based Multi-agent Debate Framework","created":"2024-06-05","cited_by_count":19},{"id":"2406.11044","title":"Evaluating the Performance of Large Language Models via Debates","created":"2024-06-16","cited_by_count":19},{"id":"2406.11514","title":"Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs","created":"2024-06-17","cited_by_count":17},{"id":"2409.17213","title":"Plurals: A System for Guiding LLMs Via Simulated Social Ensembles","created":"2024-09-25","cited_by_count":17},{"id":"2504.17087","title":"Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments","created":"2025-04-23","cited_by_count":16},{"id":"2506.00066","title":"Literature Review Of Multi-Agent Debate For Problem-Solving","created":"2025-05-29","cited_by_count":15},{"id":"2403.14255","title":"ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification","created":"2024-03-21","cited_by_count":14},{"id":"2505.18596","title":"Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models","created":"2025-05-24","cited_by_count":12},{"id":"2004.14329","title":"Google Scholar, Microsoft Academic, Scopus, Dimensions, Web of Science, and OpenCitations' COCI: a multidisciplinary comparison of coverage via citations","created":"2020-04-29","cited_by_count":11},{"id":"2408.08688","title":"The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset Generation","created":"2024-08-16","cited_by_count":11},{"id":"2503.15272","title":"MAMM-Refine: A Recipe for Improving Faithfulness in Generation with Multi-Agent Collaboration","created":"2025-03-19","cited_by_count":9},{"id":"2503.22038","title":"Debate-Driven Multi-Agent LLMs for Phishing Email Detection","created":"2025-03-27","cited_by_count":9},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9},{"id":"2407.02736","title":"MentalAgora: A Gateway to Advanced Personalized Care in Mental Health through Multi-Agent Debating and Attribute Control","created":"2024-07-03","cited_by_count":8},{"id":"2501.07288","title":"LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks","created":"2025-01-13","cited_by_count":7},{"id":"2312.04792","title":"Playing Large Games with Oracles and AI Debate","created":"2023-12-08","cited_by_count":6},{"id":"2501.14737","title":"EvalSVA: Multi-Agent Evaluators for Next-Gen Software Vulnerability Assessment","created":"2024-12-11","cited_by_count":6},{"id":"2502.14767","title":"Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis","created":"2025-02-20","cited_by_count":6},{"id":"2505.15734","title":"DEBATE, TRAIN, EVOLVE: Self Evolution of Language Model Reasoning","created":"2025-05-21","cited_by_count":6},{"id":"2311.07076","title":"On the Discussion of Large Language Models: Symmetry of Agents and Interplay with Prompts","created":"2023-11-13","cited_by_count":5},{"id":"2501.15791","title":"Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs","created":"2025-01-27","cited_by_count":5},{"id":"2502.15725","title":"Town Hall Debate Prompting: Enhancing Logical Reasoning in LLMs through Multi-Persona Interaction","created":"2025-01-28","cited_by_count":5},{"id":"2509.16494","title":"Can an Individual Manipulate the Collective Decisions of Multi-Agents?","created":"2025-09-20","cited_by_count":5},{"id":"2010.03525","title":"Empirical Standards for Software Engineering Research","created":"2020-10-07","cited_by_count":4},{"id":"2412.04859","title":"Breaking Event Rumor Detection via Stance-Separated Multi-Agent Debate","created":"2024-12-06","cited_by_count":3},{"id":"2406.12374","title":"Problem-Solving in Language Model Networks","created":"2024-06-18","cited_by_count":2},{"id":"2505.17492","title":"PD$^3$: A Project Duplication Detection Framework via Adapted Multi-Agent Debate","created":"2025-05-23","cited_by_count":2},{"id":"2506.13245","title":"A Game-Theoretic Negotiation Framework for Cross-Cultural Consensus in LLMs","created":"2025-06-16","cited_by_count":2}],"next_cursor":null}