5 papers
PATS: Policy-Aware Training Scaffolding for Agentic Reinforcement Learning
Yipeng Shi, Zhipeng Ma, Yue Wang +4
In long-horizon LLM agent reinforcement learning, weak policies often repeat similar failures, producing uninformative rollout trajectories and limiting effective policy optimizati…
FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models
Kehan Jiang, Haonan Dong, Zhaolu Kang +2
Recent Large Reasoning Models (LRMs) like DeepSeek-R1 have demonstrated remarkable success in complex reasoning tasks, exhibiting human-like patterns in exploring multiple alternat…
LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
Qifeng Cai, Hao Liang, Zhaoyang Han +6
Long videos contain a vast amount of information, making video-text retrieval an essential and challenging task in multimodal learning. However, existing benchmarks suffer from lim…
Let's Verify Math Questions Step by Step
Chengyu Shen, Zhen Hao Wong, Runming He +8
Large Language Models (LLMs) have recently achieved remarkable progress in mathematical reasoning. To enable such capabilities, many existing works distill strong reasoning models…
MathDebugger: Detecting and Diagnosing Errors in Synthetic Mathematical Data
Hao Liang, Meiyi Qiang, Yuying Li +7
Synthetic mathematical data has become an important resource for scaling the reasoning capabilities of large language models, yet errors in generated questions and solutions can su…