46 citations · 156 across the 24 of their papers we have counts for
6 papers · 1 filter
ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents
Xingjian Wu, Xuhang Zhu, Xingchen Liu +6
As LLM-based agents are deployed in complex, multi-step workflows, a critical evaluation gap has emerged: most existing benchmarks judge only final outcomes, unable to distinguish…
Contrastive Reinforced Policy Optimization via Privileged Self-Distillation
Xingjian Wu, Junlin Liu, Xingchen Liu +6
Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Self-Distillation (OPSD). Whil…
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
Tao Chen, Gangwei Jiang, Pengyu Cheng +10
Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current rew…
Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works
Wenhua Nie, Jianan Wu, Junlin Liu +6
Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards, but its group-mean-centered advantage can fail under binary re…
The Coupling Tax: How Shared Token Budgets Undermine Visible Chain-of-Thought Under Fixed Output Limits
Wenhua Nie, Junlin Liu, Jianan Wu +5
Chain-of-thought reasoning is often treated as a monotone way to improve language-model accuracy by letting a model think longer. We identify a countervailing effect, the coupling…
A Neuro-inspired Interpretation of Unlearning in Large Language Models through Sample-level Unlearning Difficulty
Xiaohua Feng, Yuyuan Li, Chengye Wang +3
Driven by privacy protection laws and regulations, unlearning in Large Language Models (LLMs) is gaining increasing attention. However, current research often neglects the interpre…