{"total":20,"rows":[{"id":"2504.11468","title":"SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models","created":"2025-04-10","cited_by_count":212,"area":"lr"},{"id":"2508.19652","title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","created":"2025-08-27","cited_by_count":97,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2511.12344","title":"Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning","created":"2025-11-15","cited_by_count":21,"area":"lr"},{"id":"2509.25026","title":"GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2506.15651","title":"AutoRule: Reasoning Chain-of-thought Extracted Rule-based Rewards Improve Preference Learning","created":"2025-06-18","cited_by_count":14,"area":"lr"},{"id":"2504.05294","title":"Truthful or Fabricated? Using Causal Attribution to Mitigate Reward Hacking in Explanations","created":"2025-04-07","cited_by_count":9,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"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":"2504.20157","title":"Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models","created":"2025-04-28","cited_by_count":5,"area":"lr"},{"id":"2607.21273","title":"The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and The Channel, Not the Content, Decides What Works","created":"2026-07-23","cited_by_count":5,"area":"lr"},{"id":"2608.09682","title":"Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning","created":"2026-08-10","cited_by_count":3,"area":"lr"},{"id":"2603.02239","title":"Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2604.15705","title":"Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning","created":"2026-04-17","cited_by_count":2,"area":"lr"},{"id":"2605.19723","title":"Mathematical Reasoning in Large Language Models: Benchmarks, Architectures, Evaluation, and Open Challenges","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2607.16492","title":"WeedExpert-R1: Incentivizing Botanical Reasoning in MLLMs with Reinforcement Learning for Precision Weed Grounding","created":"2026-07-17","cited_by_count":1,"area":"lr"},{"id":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"},{"id":"2603.01641","title":"Learning Structured Reasoning via Tractable Trajectory Control","created":"2026-03-02","cited_by_count":0,"area":"lr"},{"id":"2604.17328","title":"Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2606.25757","title":"OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning","created":"2026-06-24","cited_by_count":0,"area":"lr"}],"next_cursor":null}