6 papers
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Yu Wang, Yi-Kai Zhang, Wentao Shi +8
Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR)…
: 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…
: Generalist Value Model as a Prior for Sparse RL Rollouts
Yi-Kai Zhang, Yueqing Sun, Hongyan Hao +4
In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinfor…
ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training
Dunwei Tu, Hongyan Hao, Hansi Yang +10
Training generalist agents capable of adapting to diverse scenarios requires interactive environments for self-exploration. However, interactive environments remain critically scar…
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…