From the 1 of 6 linked papers with an AI index.
7 papers
Agent-G: Gaussian Guidance for Agentic Reinforcement Learning
Zixuan Wang, Yanrui Miao, Zhengxi Lu +6
Hint-based reinforcement learning addresses reward sparsity in long-horizon agentic tasks by retaining a prefix of an expert trajectory before each rollout, letting the policy expl…
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Haolei Xu, Xiaowen Xu, Haiwen Hong +5
The paper proposes Relay On-Policy Distillation (Relay-OPD), a method that lets a teacher model temporarily take over a student’s generation when a wrong reasoning prefix is detect…
Pause or Fabricate? Training Language Models for Grounded Reasoning
Yiwen Qiu, Linjuan Wu, Yizhou Liu +9
Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confi…
Latent Variable Causal Discovery under Selection Bias
Haoyue Dai, Yiwen Qiu, Ignavier Ng +3
Addressing selection bias in latent variable causal discovery is important yet underexplored, largely due to a lack of suitable statistical tools: While various tools beyond basic…
LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization
Xingyu Wu, Yuchen Yan, Shangke Lyu +7
Large reasoning models have achieved remarkable performance through extended chain-of-thought sequences, yet this computational freedom leads to excessive token generation even for…
Identifying Selections for Unsupervised Subtask Discovery
Yiwen Qiu, Yujia Zheng, Kun Zhang
When solving long-horizon tasks, it is intriguing to decompose the high-level task into subtasks. Decomposing experiences into reusable subtasks can improve data efficiency, accele…