{"total":99,"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":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"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":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"id":"2407.14507","title":"Internal Consistency and Self-Feedback in Large Language Models: A Survey","created":"2024-07-19","cited_by_count":50,"area":"lr"},{"id":"2410.01639","title":"Moral Alignment for LLM Agents","created":"2024-10-02","cited_by_count":39,"area":"agents"},{"id":"2407.06813","title":"Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy","created":"2024-07-09","cited_by_count":36,"area":"agents"},{"id":"2508.04482","title":"OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use","created":"2025-08-06","cited_by_count":35,"area":"agents"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"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":"2411.00053","title":"ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration","created":"2024-10-30","cited_by_count":24,"area":"agents"},{"id":"2503.12349","title":"SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?","created":"2025-03-16","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":"2503.18071","title":"Mind with Eyes: from Language Reasoning to Multimodal Reasoning","created":"2025-03-23","cited_by_count":22,"area":"lr"},{"id":"2507.15815","title":"LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra","created":"2025-07-21","cited_by_count":22,"area":"agents"},{"id":"2509.11575","title":"A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models","created":"2025-09-15","cited_by_count":21,"area":"lr"},{"id":"2605.26733","title":"Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models","created":"2026-05-26","cited_by_count":21,"area":"lr"},{"id":"2404.15532","title":"BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis","created":"2024-04-23","cited_by_count":20,"area":null},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2502.20432","title":"LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory","created":"2025-02-27","cited_by_count":17,"area":"lr"},{"id":"2410.00079","title":"Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface","created":"2024-09-30","cited_by_count":16,"area":"agents"},{"id":"2410.21287","title":"A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education","created":"2024-10-11","cited_by_count":16,"area":"lr"},{"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":"2512.01992","title":"LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess","created":"2025-12-01","cited_by_count":15,"area":"lr"},{"id":"2512.08769","title":"A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows","created":"2025-12-09","cited_by_count":15,"area":"agents"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2510.23664","title":"Agentsway -- Software Development Methodology for AI Agents-based Teams","created":"2025-10-26","cited_by_count":14,"area":"agents"},{"id":"2512.21699","title":"Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning","created":"2025-12-25","cited_by_count":14,"area":"lr"},{"id":"2505.21627","title":"Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2510.25588","title":"Standardization of Psychiatric Diagnoses -- Role of Fine-tuned LLM Consortium and OpenAI-gpt-oss Reasoning LLM Enabled Decision Support System","created":"2025-10-29","cited_by_count":12,"area":"lr"},{"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":"2504.18671","title":"Proof-of-TBI -- Fine-Tuned Vision Language Model Consortium and OpenAI-o3 Reasoning LLM-Based Medical Diagnosis Support System for Mild Traumatic Brain Injury (TBI) Prediction","created":"2025-04-25","cited_by_count":11,"area":"lr"},{"id":"2505.23713","title":"SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments","created":"2025-05-29","cited_by_count":11,"area":"lr"},{"id":"2508.08292","title":"Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs","created":"2025-08-05","cited_by_count":11,"area":"lr"},{"id":"2510.09901","title":"Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics","created":"2025-10-10","cited_by_count":11,"area":"agents"},{"id":"2504.00285","title":"When Do Large Language Models Exhibit Unsolicited Deception?","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2507.00726","title":"Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess","created":"2025-07-01","cited_by_count":9,"area":"lr"},{"id":"2510.14629","title":"MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMs","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2511.06727","title":"S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning","created":"2025-11-10","cited_by_count":9,"area":"lr"},{"id":"2412.11373","title":"Codenames as a Benchmark for Large Language Models","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2503.01642","title":"Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning","created":"2025-03-03","cited_by_count":8,"area":"lr"},{"id":"2602.16662","title":"Evaluating Collective Behaviour of Hundreds of LLM Agents","created":"2026-02-18","cited_by_count":8,"area":"agents"},{"id":"2408.05241","title":"Large Model Strategic Thinking, Small Model Efficiency: Transferring Theory of Mind in Large Language Models","created":"2024-08-05","cited_by_count":7,"area":"lr"},{"id":"2410.11900","title":"FLARE: Faithful Logic-Aided Reasoning and Exploration","created":"2024-10-14","cited_by_count":7,"area":"lr"},{"id":"2503.02582","title":"Playing games with Large language models: Randomness and strategy","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2505.17315","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2512.04785","title":"ASTRIDE: A Security Threat Modeling Platform for Agentic-AI Applications","created":"2025-12-04","cited_by_count":7,"area":"agents"},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2410.07391","title":"The Cognitive Capabilities of Generative AI: A Comparative Analysis with Human Benchmarks","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2502.13170","title":"Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment","created":"2025-02-17","cited_by_count":6,"area":"lr"},{"id":"2407.06112","title":"Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning","created":"2024-07-08","cited_by_count":5,"area":"lr"},{"id":"2506.12012","title":"Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making","created":"2025-06-13","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":"2602.10122","title":"A Practical Guide to Agentic AI Transition in Organizations","created":"2026-01-27","cited_by_count":5,"area":"agents"},{"id":"2604.08905","title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","created":"2026-04-10","cited_by_count":5,"area":"lr"},{"id":"2409.09536","title":"VernaCopter: Disambiguated Natural-Language-Driven Robot via Formal Specifications","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2409.10372","title":"Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation","created":"2024-09-16","cited_by_count":4,"area":"agents"},{"id":"2412.11761","title":"Harnessing Language for Coordination: A Framework and Benchmark for LLM-Driven Multi-Agent Control","created":"2024-12-16","cited_by_count":4,"area":"agents"},{"id":"2503.04840","title":"Framing the Game: How Context Shapes LLM Decision-Making","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2506.00307","title":"Lossless Token Sequence Compression via Meta-Tokens","created":"2025-05-30","cited_by_count":4,"area":"inference"},{"id":"2512.06867","title":"Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?","created":"2025-12-07","cited_by_count":4,"area":"lr"},{"id":"2410.12464","title":"Exploring LLM Cryptocurrency Trading Through Fact-Subjectivity Aware Reasoning","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2410.21280","title":"TraderTalk: An LLM Behavioural ABM applied to Simulating Human Bilateral Trading Interactions","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2508.12473","title":"Standardization of Neuromuscular Reflex Analysis -- Role of Fine-Tuned Vision-Language Model Consortium and OpenAI gpt-oss Reasoning LLM Enabled Decision Support System","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2411.01271","title":"Interacting Large Language Model Agents. Interpretable Models and Social Learning","created":"2024-11-02","cited_by_count":2,"area":"agents"},{"id":"2503.04750","title":"AI Agents Should be Regulated Based on the Extent of Their Autonomous Operations","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.00577","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","created":"2025-05-31","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":"2604.05987","title":"Flowr -- Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2410.01307","title":"FanCric : Multi-Agentic Framework for Crafting Fantasy 11 Cricket Teams","created":"2024-10-02","cited_by_count":1,"area":"agents"},{"id":"2504.14044","title":"Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2506.10264","title":"WGSR-Bench: Wargame-based Game-theoretic Strategic Reasoning Benchmark for Large Language Models","created":"2025-06-12","cited_by_count":1,"area":"lr"},{"id":"2507.09495","title":"GenAI-based Multi-Agent Reinforcement Learning towards Distributed Agent Intelligence: A Generative-RL Agent Perspective","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2508.11944","title":"CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs","created":"2025-08-16","cited_by_count":1,"area":"lr"},{"id":"2508.17971","title":"Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Finding","created":"2025-08-25","cited_by_count":1,"area":"lr"},{"id":"2511.21935","title":"Breaking Algorithmic Collusion in Human-AI Ecosystems","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.02456","title":"See, Think, Learn: A Self-Taught Multimodal Reasoner","created":"2025-12-02","cited_by_count":1,"area":"lr"},{"id":"2602.06081","title":"Communication Enhances LLMs' Stability in Strategic Thinking","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.13227","title":"An Agentic AI Control Plane for 6G Network Slice Orchestration, Monitoring, and Trading","created":"2026-01-27","cited_by_count":1,"area":"agents"},{"id":"2603.06923","title":"Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping","created":"2026-03-06","cited_by_count":1,"area":"lr"},{"id":"2605.22826","title":"Evaluating Large Language Models in a Complex Hidden Role Game","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2608.26291","title":"Assessing mentalization in humans and large language models","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2410.01929","title":"LLM-Augmented Symbolic Reinforcement Learning with Landmark-Based Task Decomposition","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2412.11763","title":"QUENCH: Measuring the gap between Indic and Non-Indic Contextual General Reasoning in LLMs","created":"2024-12-16","cited_by_count":0,"area":"lr"},{"id":"2509.21134","title":"ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspective","created":"2025-09-25","cited_by_count":0,"area":"agents"},{"id":"2510.08466","title":"In-Context Clustering with Large Language Models","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2602.14106","title":"Anticipating Adversary Behavior in DevSecOps Scenarios through Large Language Models","created":"2026-02-15","cited_by_count":0,"area":null},{"id":"2604.04341","title":"Implementing surrogate goals for safer bargaining in LLM-based agents","created":"2026-04-06","cited_by_count":0,"area":"agents"},{"id":"2604.08563","title":"Temperature-Dependent Performance of Prompting Strategies in Extended Reasoning Large Language Models","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.16337","title":"HR-Agents: Using Multiple LLM-based Agents to Improve Q&A about Brazilian Labor Legislation","created":"2026-03-13","cited_by_count":0,"area":"rag"},{"id":"2605.16269","title":"Train the Trainers -- An Agentic AI Framework for Peer-Based Mental Health Support in Battlefield Environments","created":"2026-03-31","cited_by_count":0,"area":"agents"},{"id":"2605.27296","title":"Probing Cultural Awareness in LLMs: A Case Study of Cross-Culture Aesthetic Stylistics","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.06840","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.19308","title":"Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2608.20129","title":"Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving","created":"2026-08-20","cited_by_count":0,"area":"lr"},{"id":"2609.00604","title":"NeuroGraph: An AI Graph-Driven Neuro-Symbolic Framework for Explainable Threat Reasoning in Advanced Manufacturing","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2609.28557","title":"BaseCamp --- An Agentic AI Framework for Automating DNA Sequencing Data Pipelines","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2610.09371","title":"The Confidence Game: Strategic Miscalibration in Human-AI Delegation","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}