6 papers
: A Generalist Value Model for Any Policy at State Zero
Yi-Kai Zhang, Zhiyuan Yao, Hongyan Hao +6
Policy gradient methods rely on a baseline to measure the relative advantage of an action, ensuring the model reinforces behaviors that outperform its current average capability. I…
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs
Zhiyuan Yao, Yi-Kai Zhang, Yuxin Chen +7
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a key approach for enhancing LLM reasoning. However, standard frameworks like Group Relative Policy Optimizatio…
LongCat-Flash-Thinking-2601 Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +162
We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thi…
Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Wanghan Xu, Yuhao Zhou, Yifan Zhou +104
Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific do…
BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice
Yuanpeng Li, Qi Long, Zhiyuan Yao +7
As enterprise codebases continue to grow in scale and complexity, the volume of lint errors far exceeds engineers' manual remediation capacity, leading to continuous accumulation o…
Collaborative Inference for Large Models with Task Offloading and Early Exiting
Zuan Xie, Yang Xu, Hongli Xu +2
In 5G smart cities, edge computing is employed to provide nearby computing services for end devices, and the large-scale models (e.g., GPT and LLaMA) can be deployed at the network…