{"total":209,"rows":[{"id":"2308.08155","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","created":"2023-08-16","cited_by_count":1988,"area":"agents"},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367,"area":"agents"},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262,"area":"alignment"},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2305.10142","title":"Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback","created":"2023-05-17","cited_by_count":207,"area":"synth"},{"id":"2308.14752","title":"AI Deception: A Survey of Examples, Risks, and Potential Solutions","created":"2023-08-28","cited_by_count":188,"area":null},{"id":"2103.14659","title":"Alignment of Language Agents","created":"2021-03-26","cited_by_count":168,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113,"area":null},{"id":"2206.13353","title":"Is Power-Seeking AI an Existential Risk?","created":"2022-06-16","cited_by_count":105,"area":null},{"id":"2404.08555","title":"RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs","created":"2024-04-12","cited_by_count":90,"area":"alignment"},{"id":"2308.11995","title":"Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations","created":"2023-08-23","cited_by_count":89,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2310.05338","title":"Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models","created":"2023-10-09","cited_by_count":80,"area":"mllm"},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75,"area":null},{"id":"2410.20424","title":"AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions","created":"2024-10-27","cited_by_count":70,"area":null},{"id":"2504.05228","title":"NoveltyBench: Evaluating Language Models for Humanlike Diversity","created":"2025-04-07","cited_by_count":66,"area":null},{"id":"2305.19165","title":"Strategic Reasoning with Language Models","created":"2023-05-30","cited_by_count":64,"area":"lr"},{"id":"2103.15721","title":"CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems","created":"2021-03-29","cited_by_count":62,"area":null},{"id":"2305.13660","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2411.05990","title":"Game-theoretic LLM: Agent Workflow for Negotiation Games","created":"2024-11-08","cited_by_count":56,"area":"agents"},{"id":"2404.13627","title":"NegotiationToM: A Benchmark for Stress-testing Machine Theory of Mind on Negotiation Surrounding","created":"2024-04-21","cited_by_count":51,"area":null},{"id":"2112.07544","title":"Modeling Strong and Human-Like Gameplay with KL-Regularized Search","created":"2021-12-14","cited_by_count":50,"area":"offlinerl"},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2402.15813","title":"Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method","created":"2024-02-24","cited_by_count":48,"area":null},{"id":"2310.08901","title":"Welfare Diplomacy: Benchmarking Language Model Cooperation","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2312.01350","title":"Honesty Is the Best Policy: Defining and Mitigating AI Deception","created":"2023-12-03","cited_by_count":40,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2511.00222","title":"Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning","created":"2025-10-31","cited_by_count":39,"area":"alignment"},{"id":"2402.16499","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments","created":"2024-02-26","cited_by_count":36,"area":"agents"},{"id":"2204.08426","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","created":"2022-04-18","cited_by_count":34,"area":"offlinerl"},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2209.03118","title":"The Ethical Need for Watermarks in Machine-Generated Language","created":"2022-09-07","cited_by_count":32,"area":"safety"},{"id":"2212.09072","title":"Let's Negotiate! A Survey of Negotiation Dialogue Systems","created":"2022-12-18","cited_by_count":31,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2305.20076","title":"Decision-Oriented Dialogue for Human-AI Collaboration","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2402.13550","title":"Are LLMs Effective Negotiators? Systematic Evaluation of the Multifaceted Capabilities of LLMs in Negotiation Dialogues","created":"2024-02-21","cited_by_count":29,"area":null},{"id":"2108.05271","title":"DeliData: A dataset for deliberation in multi-party problem solving","created":"2021-08-11","cited_by_count":26,"area":null},{"id":"2404.01663","title":"CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models","created":"2024-04-02","cited_by_count":26,"area":"agents"},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2106.00920","title":"DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues","created":"2021-06-02","cited_by_count":25,"area":null},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"id":"2405.05248","title":"LLMs with Personalities in Multi-issue Negotiation Games","created":"2024-05-08","cited_by_count":22,"area":null},{"id":"2510.07777","title":"Drift No More? Context Equilibria in Multi-Turn LLM Interactions","created":"2025-10-09","cited_by_count":22,"area":null},{"id":"2403.06769","title":"Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User Simulation","created":"2024-03-11","cited_by_count":21,"area":null},{"id":"2406.04784","title":"SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals","created":"2024-06-07","cited_by_count":21,"area":"agents"},{"id":"2205.00872","title":"COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas","created":"2022-05-02","cited_by_count":20,"area":null},{"id":"2404.19409","title":"Countering Reward Over-optimization in LLM with Demonstration-Guided Reinforcement Learning","created":"2024-04-30","cited_by_count":20,"area":"alignment"},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2510.25779","title":"Magentic Marketplace: An Open-Source Environment for Studying Agentic Markets","created":"2025-10-27","cited_by_count":19,"area":"agents"},{"id":"2312.11792","title":"COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal","created":"2023-12-19","cited_by_count":18,"area":null},{"id":"2404.04289","title":"Designing for Human-Agent Alignment: Understanding what humans want from their agents","created":"2024-04-04","cited_by_count":18,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2204.07433","title":"Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy","created":"2022-04-07","cited_by_count":17,"area":null},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","cited_by_count":16,"area":null},{"id":"2204.03516","title":"Distributed Reinforcement Learning for Robot Teams: A Review","created":"2022-04-07","cited_by_count":16,"area":null},{"id":"2501.14082","title":"Communicating Activations Between Language Model Agents","created":"2025-01-23","cited_by_count":16,"area":"lr"},{"id":"2310.14404","title":"Be Selfish, But Wisely: Investigating the Impact of Agent Personality in Mixed-Motive Human-Agent Interactions","created":"2023-10-22","cited_by_count":15,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2406.18872","title":"Efficacy of Language Model Self-Play in Non-Zero-Sum Games","created":"2024-06-27","cited_by_count":15,"area":"synth"},{"id":"2506.00073","title":"The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets","created":"2025-05-29","cited_by_count":15,"area":"agents"},{"id":"2210.05664","title":"Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks","created":"2022-10-11","cited_by_count":14,"area":null},{"id":"2407.03585","title":"Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2507.02097","title":"The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems","created":"2025-07-02","cited_by_count":14,"area":"agents"},{"id":"2205.00344","title":"Opponent Modeling in Negotiation Dialogues by Related Data Adaptation","created":"2022-04-30","cited_by_count":13,"area":null},{"id":"2207.02253","title":"Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia","created":"2022-07-05","cited_by_count":13,"area":null},{"id":"2308.02541","title":"Towards More Human-like AI Communication: A Review of Emergent Communication Research","created":"2023-08-01","cited_by_count":13,"area":null},{"id":"2406.11978","title":"Dialogue Action Tokens: Steering Language Models in Goal-Directed Dialogue with a Multi-Turn Planner","created":"2024-06-17","cited_by_count":13,"area":"agents"},{"id":"2410.01555","title":"ACE: A LLM-based Negotiation Coaching System","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2505.07775","title":"Must Read: A Comprehensive Survey of Computational Persuasion","created":"2025-05-12","cited_by_count":13,"area":null},{"id":"2508.16846","title":"BASIL: Bayesian Assessment of Sycophancy in LLMs","created":"2025-08-23","cited_by_count":13,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2303.13360","title":"Towards the Scalable Evaluation of Cooperativeness in Language Models","created":"2023-03-16","cited_by_count":12,"area":null},{"id":"2311.05720","title":"Long-Horizon Dialogue Understanding for Role Identification in the Game of Avalon with Large Language Models","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2411.16905","title":"Boundless Socratic Learning with Language Games","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2505.22961","title":"ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2512.03318","title":"Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia","created":"2025-12-03","cited_by_count":12,"area":"agents"},{"id":"2602.06008","title":"AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions","created":"2026-02-05","cited_by_count":12,"area":"agents"},{"id":"2203.07657","title":"Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2308.14328","title":"Reinforcement Learning for Generative AI: A Survey","created":"2023-08-28","cited_by_count":11,"area":null},{"id":"2407.09221","title":"Evaluating AI Evaluation: Perils and Prospects","created":"2024-07-12","cited_by_count":11,"area":null},{"id":"2107.13165","title":"Towards Emotion-Aware Agents For Negotiation Dialogues","created":"2021-07-28","cited_by_count":10,"area":null},{"id":"2510.14318","title":"Evaluating & Reducing Deceptive Dialogue From Language Models with Multi-turn RL","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2105.14207","title":"Maintaining Common Ground in Dynamic Environments","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2110.03262","title":"Situated Dialogue Learning through Procedural Environment Generation","created":"2021-10-07","cited_by_count":9,"area":null},{"id":"2504.12723","title":"KODIS: A Multicultural Dispute Resolution Dialogue Corpus","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2506.00539","title":"ARIA: Training Language Agents with Intention-Driven Reward Aggregation","created":"2025-05-31","cited_by_count":9,"area":"agents"},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2205.03692","title":"Towards a Progression-Aware Autonomous Dialogue Agent","created":"2022-05-07","cited_by_count":7,"area":"agents"},{"id":"2305.17280","title":"Improved Instruction Ordering in Recipe-Grounded Conversation","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2406.14662","title":"Advantage Alignment Algorithms","created":"2024-06-20","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":"2604.09855","title":"Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards","created":"2026-04-10","cited_by_count":7,"area":null}],"next_cursor":"100"}