{"total":56,"rows":[{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211,"area":"lr"},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886,"area":"lr"},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560,"area":"lr"},{"id":"2309.16797","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","created":"2023-09-28","cited_by_count":551,"area":"lr"},{"id":"2302.07842","title":"Augmented Language Models: a Survey","created":"2023-02-15","cited_by_count":403,"area":"lr"},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190,"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":"2403.02713","title":"Android in the Zoo: Chain-of-Action-Thought for GUI Agents","created":"2024-03-05","cited_by_count":159,"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":"2408.09559","title":"HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model","created":"2024-08-18","cited_by_count":106,"area":"lr"},{"id":"2402.15116","title":"Large Multimodal Agents: A Survey","created":"2024-02-23","cited_by_count":105,"area":"lr"},{"id":"2406.06613","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents","created":"2024-06-07","cited_by_count":95,"area":"lr"},{"id":"2408.00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","created":"2024-08-01","cited_by_count":83,"area":"lr"},{"id":"2311.04254","title":"Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation","created":"2023-11-07","cited_by_count":74,"area":"lr"},{"id":"2504.07986","title":"SEAL: Steerable Reasoning Calibration of Large Language Models for Free","created":"2025-04-07","cited_by_count":68,"area":"lr"},{"id":"2406.14596","title":"VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought","created":"2024-06-20","cited_by_count":55,"area":"lr"},{"id":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54,"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":"2310.08582","title":"Tree-Planner: Efficient Close-loop Task Planning with Large Language Models","created":"2023-10-12","cited_by_count":48,"area":"lr"},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42,"area":"lr"},{"id":"2410.18963","title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","created":"2024-10-24","cited_by_count":38,"area":"lr"},{"id":"2410.08328","title":"Agents Thinking Fast and Slow: A Talker-Reasoner Architecture","created":"2024-10-10","cited_by_count":36,"area":"lr"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"area":"lr"},{"id":"2505.13426","title":"G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning","created":"2025-05-19","cited_by_count":29,"area":"lr"},{"id":"2402.06529","title":"Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity","created":"2024-02-09","cited_by_count":27,"area":"lr"},{"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":"2312.07062","title":"ThinkBot: Embodied Instruction Following with Thought Chain Reasoning","created":"2023-12-12","cited_by_count":19,"area":"lr"},{"id":"2402.10778","title":"AutoGPT+P: Affordance-based Task Planning with Large Language Models","created":"2024-02-16","cited_by_count":19,"area":"lr"},{"id":"2406.06464","title":"Transforming Wearable Data into Personal Health Insights using Large Language Model Agents","created":"2024-06-10","cited_by_count":19,"area":"lr"},{"id":"2503.06514","title":"GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks","created":"2025-03-09","cited_by_count":15,"area":"lr"},{"id":"2311.13148","title":"Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents","created":"2023-11-22","cited_by_count":14,"area":"lr"},{"id":"2411.03519","title":"AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution","created":"2024-11-05","cited_by_count":14,"area":"lr"},{"id":"2503.08525","title":"GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training","created":"2025-03-11","cited_by_count":14,"area":"lr"},{"id":"2309.10103","title":"Reasoning about the Unseen for Efficient Outdoor Object Navigation","created":"2023-09-18","cited_by_count":13,"area":"lr"},{"id":"2404.11483","title":"AgentKit: Structured LLM Reasoning with Dynamic Graphs","created":"2024-04-17","cited_by_count":13,"area":"lr"},{"id":"2506.01341","title":"TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models","created":"2025-06-02","cited_by_count":13,"area":"lr"},{"id":"2305.15486","title":"SPRING: Studying the Paper and Reasoning to Play Games","created":"2023-05-24","cited_by_count":11,"area":"lr"},{"id":"2404.05966","title":"THOUGHTSCULPT: Reasoning with Intermediate Revision and Search","created":"2024-04-09","cited_by_count":11,"area":"lr"},{"id":"2503.11089","title":"EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks","created":"2025-03-14","cited_by_count":10,"area":"lr"},{"id":"2508.21365","title":"Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models","created":"2025-08-29","cited_by_count":7,"area":"lr"},{"id":"2503.10042","title":"EscapeCraft: A 3D Room Escape Environment for Benchmarking Complex Multimodal Reasoning Ability","created":"2025-03-13","cited_by_count":6,"area":"lr"},{"id":"2408.01942","title":"Visual Grounding for Object-Level Generalization in Reinforcement Learning","created":"2024-08-04","cited_by_count":4,"area":"lr"},{"id":"2501.02026","title":"Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models","created":"2025-01-03","cited_by_count":4,"area":"lr"},{"id":"2505.10543","title":"Reasoning Capabilities of Large Language Models on Dynamic Tasks","created":"2025-05-15","cited_by_count":4,"area":"lr"},{"id":"2410.12568","title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2509.08500","title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2602.22546","title":"Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention","created":"2026-02-26","cited_by_count":3,"area":"lr"},{"id":"2406.16567","title":"Data Augmentation of Multi-turn Psychological Dialogue via Knowledge-driven Progressive Thought Prompting","created":"2024-06-24","cited_by_count":2,"area":"lr"},{"id":"2503.07323","title":"Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning","created":"2025-03-10","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":"2605.19824","title":"From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2502.19500","title":"Conversational Planning for Personal Plans","created":"2025-02-26","cited_by_count":0,"area":"lr"},{"id":"2605.05407","title":"PRISM: Perception Reasoning Interleaved for Sequential Decision Making","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2606.12852","title":"WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2607.04854","title":"CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2607.18100","title":"Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering","created":"2026-07-20","cited_by_count":0,"area":"lr"}],"next_cursor":null}