activity
20242026
collaborators

26 papers

cs.AI2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CL2026

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…

cs.AI2026

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…

cs.LG2026

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…