{"total":39,"rows":[{"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":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2305.17390","title":"SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks","created":"2023-05-27","cited_by_count":168,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2402.12348","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","created":"2024-02-19","cited_by_count":120,"area":"lr"},{"id":"2501.11425","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","created":"2025-01-20","cited_by_count":82,"area":"lr"},{"id":"2310.05746","title":"Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena","created":"2023-10-09","cited_by_count":78,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2604.24005","title":"TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents","created":"2026-04-27","cited_by_count":47,"area":"lr"},{"id":"2302.04752","title":"Benchmarks for Automated Commonsense Reasoning: A Survey","created":"2023-02-09","cited_by_count":40,"area":"lr"},{"id":"2502.14276","title":"STeCa: Step-level Trajectory Calibration for LLM Agent Learning","created":"2025-02-20","cited_by_count":37,"area":"lr"},{"id":"2503.03205","title":"MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving","created":"2025-03-05","cited_by_count":24,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2508.01432","title":"TripTailor: A Real-World Benchmark for Personalized Travel Planning","created":"2025-08-02","cited_by_count":22,"area":"lr"},{"id":"2502.02584","title":"QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search","created":"2025-02-04","cited_by_count":20,"area":"lr"},{"id":"2502.12130","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","created":"2025-02-17","cited_by_count":19,"area":"lr"},{"id":"2505.11807","title":"Retrospex: Language Agent Meets Offline Reinforcement Learning Critic","created":"2025-05-17","cited_by_count":12,"area":"lr"},{"id":"2505.13328","title":"Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges","created":"2025-05-19","cited_by_count":12,"area":"lr"},{"id":"2601.03715","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","created":"2026-01-07","cited_by_count":12,"area":"lr"},{"id":"2309.01352","title":"Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning","created":"2023-09-04","cited_by_count":9,"area":"lr"},{"id":"2310.18783","title":"Are NLP Models Good at Tracing Thoughts: An Overview of Narrative Understanding","created":"2023-10-28","cited_by_count":9,"area":"lr"},{"id":"2503.02238","title":"Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions","created":"2025-03-04","cited_by_count":5,"area":"lr"},{"id":"2505.21935","title":"From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models","created":"2025-05-28","cited_by_count":5,"area":"lr"},{"id":"2602.12662","title":"Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents","created":"2026-02-13","cited_by_count":5,"area":"lr"},{"id":"2508.03018","title":"Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning","created":"2025-08-05","cited_by_count":4,"area":"lr"},{"id":"2608.07118","title":"How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning","created":"2026-08-07","cited_by_count":3,"area":"lr"},{"id":"2408.04900","title":"Communicate to Play: Pragmatic Reasoning for Efficient Cross-Cultural Communication in Codenames","created":"2024-08-09","cited_by_count":2,"area":"lr"},{"id":"2411.01790","title":"Thinking Forward and Backward: Effective Backward Planning with Large Language Models","created":"2024-11-04","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2510.14828","title":"RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2606.05263","title":"Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2605.09860","title":"When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2607.27415","title":"Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.12626","title":"LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.27035","title":"Reinforcement Learning with Decomposed Subtasks","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.33166","title":"Downstream-Aware Context Selection for Online In-Context Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.34548","title":"SGG-ReflAct: Sub-Goal Guided ReflAct with Structured Planning for Reliable Long-Horizon Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.13238","title":"State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.20012","title":"ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}