{"total":31,"rows":[{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2501.07542","title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","created":"2025-01-13","cited_by_count":206,"area":"lr"},{"id":"2505.11409","title":"Visual Planning: Let's Think Only with Images","created":"2025-05-16","cited_by_count":85,"area":"lr"},{"id":"2510.27492","title":"ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning","created":"2025-10-30","cited_by_count":56,"area":"lr"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2407.01863","title":"VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs","created":"2024-07-02","cited_by_count":47,"area":"lr"},{"id":"2502.12272","title":"Learning to Reason at the Frontier of Learnability","created":"2025-02-17","cited_by_count":23,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2408.13184","title":"Can LLM be a Good Path Planner based on Prompt Engineering? Mitigating the Hallucination for Path Planning","created":"2024-08-23","cited_by_count":11,"area":"lr"},{"id":"2206.09203","title":"Interactive Visual Reasoning under Uncertainty","created":"2022-06-18","cited_by_count":8,"area":"lr"},{"id":"2402.15420","title":"PREDILECT: Preferences Delineated with Zero-Shot Language-based Reasoning in Reinforcement Learning","created":"2024-02-23","cited_by_count":8,"area":"lr"},{"id":"2506.05523","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2506.10778","title":"SlotPi: Physics-informed Object-centric Reasoning Models","created":"2025-06-12","cited_by_count":5,"area":"lr"},{"id":"2510.19429","title":"NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning","created":"2025-10-22","cited_by_count":5,"area":"lr"},{"id":"2603.02119","title":"Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning","created":"2026-03-02","cited_by_count":5,"area":"lr"},{"id":"2603.20194","title":"MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2505.21055","title":"Agent-Environment Alignment via Automated Interface Generation","created":"2025-05-27","cited_by_count":4,"area":"lr"},{"id":"2211.01994","title":"lilGym: Natural Language Visual Reasoning with Reinforcement Learning","created":"2022-11-03","cited_by_count":3,"area":"lr"},{"id":"2502.12929","title":"Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options","created":"2025-02-18","cited_by_count":3,"area":"lr"},{"id":"2312.17248","title":"Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity","created":"2023-12-28","cited_by_count":2,"area":"lr"},{"id":"2511.21928","title":"Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs","created":"2025-11-26","cited_by_count":2,"area":"lr"},{"id":"2601.20856","title":"SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2606.03102","title":"Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2607.15610","title":"Process Reward Informed Tree Rollout for Effective Multi-Turn RL","created":"2026-07-17","cited_by_count":2,"area":"lr"},{"id":"2609.18708","title":"Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening","created":"2026-09-16","cited_by_count":2,"area":"lr"},{"id":"2505.10992","title":"ReaCritic: Reasoning Transformer-based DRL Critic-model Scaling For Wireless Networks","created":"2025-05-16","cited_by_count":1,"area":"lr"},{"id":"2508.19035","title":"Investigating Advanced Reasoning of Large Language Models via Black-Box Environment Interaction","created":"2025-08-26","cited_by_count":1,"area":"lr"},{"id":"2507.16473","title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","created":"2025-07-22","cited_by_count":0,"area":"lr"},{"id":"2508.10123","title":"Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2606.11770","title":"SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement Learning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2609.24380","title":"Information-Time Proximal Policy Optimization","created":"2026-09-21","cited_by_count":0,"area":"lr"}],"next_cursor":null}