{"total":64,"rows":[{"id":"2406.20094","title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","created":"2024-06-28","cited_by_count":417,"area":"synth"},{"id":"2503.01307","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","created":"2025-03-03","cited_by_count":377,"area":"lr"},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301,"area":"lr"},{"id":"2310.18940","title":"Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game","created":"2023-10-29","cited_by_count":152,"area":"agents"},{"id":"2404.03683","title":"Stream of Search (SoS): Learning to Search in Language","created":"2024-04-01","cited_by_count":145,"area":"lr"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104,"area":null},{"id":"2404.01230","title":"LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models","created":"2024-04-01","cited_by_count":99,"area":"lr"},{"id":"2309.17234","title":"Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation","created":"2023-09-29","cited_by_count":96,"area":null},{"id":"2406.06613","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","created":"2024-06-07","cited_by_count":95,"area":"lr"},{"id":"2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","created":"2024-06-06","cited_by_count":80,"area":null},{"id":"2505.23646","title":"Are Reasoning Models More Prone to Hallucination?","created":"2025-05-29","cited_by_count":64,"area":"lr"},{"id":"2309.12309","title":"Rehearsal: Simulating Conflict to Teach Conflict Resolution","created":"2023-09-21","cited_by_count":55,"area":null},{"id":"2310.08901","title":"Welfare Diplomacy: Benchmarking Language Model Cooperation","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2412.10270","title":"Cultural Evolution of Cooperation among LLM Agents","created":"2024-12-13","cited_by_count":32,"area":"agents"},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2402.01704","title":"Steering Language Models with Game-Theoretic Solvers","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2410.10479","title":"TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs","created":"2024-10-14","cited_by_count":24,"area":"lr"},{"id":"2412.03920","title":"A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios","created":"2024-12-05","cited_by_count":23,"area":"agents"},{"id":"2503.06047","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","created":"2025-03-08","cited_by_count":23,"area":"agents"},{"id":"2405.16376","title":"STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making","created":"2024-05-25","cited_by_count":22,"area":"lr"},{"id":"2402.01521","title":"K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning","created":"2024-02-02","cited_by_count":21,"area":"lr"},{"id":"2402.08189","title":"Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs","created":"2024-02-13","cited_by_count":21,"area":"agents"},{"id":"2501.01540","title":"BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery","created":"2025-01-02","cited_by_count":18,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"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":"2502.04686","title":"Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization","created":"2025-02-07","cited_by_count":15,"area":"agents"},{"id":"2505.19212","title":"When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2403.06294","title":"ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes","created":"2024-03-10","cited_by_count":13,"area":"lr"},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2410.13204","title":"Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations","created":"2024-10-17","cited_by_count":11,"area":null},{"id":"2501.13122","title":"Zero-Shot Verification-guided Chain of Thoughts","created":"2025-01-21","cited_by_count":10,"area":"lr"},{"id":"2310.17769","title":"Social Contract AI: Aligning AI Assistants with Implicit Group Norms","created":"2023-10-26","cited_by_count":9,"area":null},{"id":"2412.11373","title":"Codenames as a Benchmark for Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2502.12486","title":"EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2505.05029","title":"Reputation as a Solution to Cooperation Collapse in LLM-based MASs","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2602.16662","title":"Evaluating Collective Behaviour of Hundreds of LLM Agents","created":"2026-02-18","cited_by_count":8,"area":"agents"},{"id":"2312.01818","title":"Hybrid Approaches for Moral Value Alignment in AI Agents: a Manifesto","created":"2023-12-04","cited_by_count":7,"area":"agents"},{"id":"2407.06112","title":"Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning","created":"2024-07-08","cited_by_count":5,"area":"lr"},{"id":"2507.20796","title":"Aligning Large Language Model Agents with Rational and Moral Preferences: A Supervised Fine-Tuning Approach","created":"2025-07-28","cited_by_count":5,"area":"agents"},{"id":"2510.08098","title":"The Price of Thought: A Multilingual Analysis of Reasoning, Performance, and Cost of Negotiation in Large Language Models","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2512.00371","title":"Evaluating LLMs in Open-Source Games","created":"2025-11-29","cited_by_count":5,"area":null},{"id":"2510.25626","title":"Are Language Models Efficient Reasoners? A Perspective from Logic Programming","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2502.16339","title":"Dynamic Coalition Structure Detection in Natural Language-based Interactions","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2508.06042","title":"Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning","created":"2025-08-08","cited_by_count":3,"area":"lr"},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2605.14537","title":"Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Bargaining","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2505.19761","title":"Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning","created":"2025-05-26","cited_by_count":2,"area":"lr"},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2510.08255","title":"Opponent Shaping in LLM Agents","created":"2025-10-09","cited_by_count":2,"area":"agents"},{"id":"2604.14386","title":"Coalition Formation in LLM Agent Networks: Stability Analysis and Convergence Guarantees","created":"2026-04-15","cited_by_count":2,"area":"agents"},{"id":"2605.10059","title":"Strategic Exploitation in LLM Agent Markets: A Simulation Framework for E-Commerce Trust","created":"2026-05-11","cited_by_count":2,"area":"agents"},{"id":"2605.16575","title":"Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators","created":"2026-05-15","cited_by_count":2,"area":null},{"id":"2410.05496","title":"Intuitions of Compromise: Utilitarianism vs. Contractualism","created":"2024-10-07","cited_by_count":1,"area":null},{"id":"2602.05183","title":"Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning","created":"2026-02-05","cited_by_count":1,"area":"agents"},{"id":"2609.04303","title":"Abstraction Agent","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2605.10410","title":"Equilibrium Residuals Expose Three Regimes of Matrix-Game Strategic Reasoning in Language Models","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.22238","title":"Evaluating Large Language Models as Live Strategic Agents: Provider Performance, Hybrid Decomposition, and Operational Gaps in Timed Risk Play","created":"2026-05-21","cited_by_count":0,"area":"agents"},{"id":"2606.18950","title":"RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2607.09743","title":"Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling Spatial Markets","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.27536","title":"Strategy, Not Payoffs: A Behavioural Embedding of Normal-Form Games","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}