{"total":21,"rows":[{"id":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57,"area":"lr"},{"id":"2505.02665","title":"A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law","created":"2025-05-05","cited_by_count":19,"area":"lr"},{"id":"2601.05110","title":"GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts","created":"2026-01-08","cited_by_count":17,"area":"lr"},{"id":"2511.13026","title":"REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding","created":"2025-11-17","cited_by_count":16,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2505.17746","title":"Fast Quiet-STaR: Thinking Without Thought Tokens","created":"2025-05-23","cited_by_count":5,"area":"lr"},{"id":"2506.15710","title":"RAST: Reasoning Activation in LLMs via Small-model Transfer","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2510.01444","title":"Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2604.08905","title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","created":"2026-04-10","cited_by_count":5,"area":"lr"},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2606.02020","title":"Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning","created":"2026-06-01","cited_by_count":4,"area":"lr"},{"id":"2604.06192","title":"The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2510.02648","title":"SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Models","created":"2025-10-03","cited_by_count":2,"area":"lr"},{"id":"2601.10775","title":"LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2601.13115","title":"Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning","created":"2026-01-19","cited_by_count":1,"area":"lr"},{"id":"2604.09704","title":"Multi-Granularity Reasoning for Image Quality Assessment via Attribute-Aware Reinforcement Learning to Rank","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2604.20500","title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.08978","title":"Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization","created":"2026-05-09","cited_by_count":1,"area":"lr"},{"id":"2602.14054","title":"LogitsCoder: Towards Efficient Chain-of-Thought Path Search via Logits Preference Decoding for Code Generation","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2604.19780","title":"Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMs","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"id":"2610.19561","title":"REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}