26 papers
Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
Rui Liu, Dian Yu, Tong Zheng +8
Reinforcement learning with verifiable rewards (RLVR) has advanced reasoning capabilities in multimodal large language models. However, existing methods typically treat visual inpu…
One Token to Fool LLM-as-a-Judge
Yulai Zhao, Haolin Liu, Dian Yu +4
Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-ba…
FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention
Yan Wang, Qifan Zhang, Jiachen Yu +12
Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead…
Verified Critical Step Optimization for LLM Agents
Mukai Li, Qingcheng Zeng, Tianqing Fang +5
As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamental challenges: outcome-only rewar…
Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification
Yuxuan Wan, Tianqing Fang, Zaitang Li +5
Recent advances in Deep Research Agents (DRAs) are transforming automated knowledge discovery and problem-solving. While the majority of existing efforts focus on enhancing policy…
Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data
Zhenwen Liang, Yujun Zhou, Sidi Lu +3
Reinforcement Learning (RL) enhances LLM reasoning, yet a paradox emerges as models scale: strong base models saturate standard benchmarks (e.g., MATH), yielding correct but homoge…