{"total":33,"rows":[{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706,"area":"lr"},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574,"area":"lr"},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"id":"2509.02544","title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","created":"2025-09-02","cited_by_count":215,"area":"lr"},{"id":"2311.05772","title":"ADaPT: As-Needed Decomposition and Planning with Language Models","created":"2023-11-08","cited_by_count":177,"area":"lr"},{"id":"2505.16421","title":"WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning","created":"2025-05-22","cited_by_count":165,"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":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"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":"2311.15209","title":"See and Think: Embodied Agent in Virtual Environment","created":"2023-11-26","cited_by_count":54,"area":"lr"},{"id":"2505.19683","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","created":"2025-05-26","cited_by_count":40,"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":"2501.10069","title":"A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks","created":"2025-01-17","cited_by_count":21,"area":"lr"},{"id":"2304.00776","title":"Chain-of-Thought Predictive Control","created":"2023-04-03","cited_by_count":18,"area":"lr"},{"id":"2401.04181","title":"Language-Conditioned Robotic Manipulation with Fast and Slow Thinking","created":"2024-01-08","cited_by_count":17,"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":"2306.08651","title":"Toward Grounded Commonsense Reasoning","created":"2023-06-14","cited_by_count":9,"area":"lr"},{"id":"2402.09404","title":"AQA-Bench: An Interactive Benchmark for Evaluating LLMs' Sequential Reasoning Ability","created":"2024-02-14","cited_by_count":8,"area":"lr"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2501.18009","title":"Large Language Models Think Too Fast To Explore Effectively","created":"2025-01-29","cited_by_count":7,"area":"lr"},{"id":"2505.08189","title":"DSADF: Thinking Fast and Slow for Decision Making","created":"2025-05-13","cited_by_count":7,"area":"lr"},{"id":"2405.06691","title":"Fleet of Agents: Coordinated Problem Solving with Large Language Models","created":"2024-05-07","cited_by_count":5,"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":"2505.16928","title":"Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2309.07974","title":"A Data Source for Reasoning Embodied Agents","created":"2023-09-14","cited_by_count":1,"area":"lr"},{"id":"2506.10085","title":"VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision-Language Models","created":"2025-06-11","cited_by_count":1,"area":"lr"},{"id":"2608.01709","title":"SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models","created":"2026-08-03","cited_by_count":1,"area":"lr"},{"id":"2407.09287","title":"Instruction Following with Goal-Conditioned Reinforcement Learning in Virtual Environments","created":"2024-07-12","cited_by_count":0,"area":"lr"},{"id":"2509.00465","title":"Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning","created":"2025-08-30","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":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}