collaborators

8 papers

cs.CL2026

AlignEvoSkill: Towards Knowledge-Aware and Task-Aligned Agent Skill Evolution

Dingzirui Wang, Xuanliang Zhang, Keyan Xu +3

Reusable skills play a key role in improving LLM-based agents, but existing skill-evolution methods often fail to ensure that evolved skills both cover the knowledge required by th…

cs.AI2026

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents

Shuai Zhen, Yanhua Yu, Ruopei Guo +2

Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly lo…

cs.CL2026

CoSToM:Causal-oriented Steering for Intrinsic Theory-of-Mind Alignment in Large Language Models

Mengfan Li, Xuanhua Shi, Yang Deng

Theory of Mind (ToM), the ability to attribute mental states to others, is a hallmark of social intelligence. While large language models (LLMs) demonstrate promising performance o…

cs.CV2026

Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning

Yang Deng, David Mould, Paul L. Rosin +1

Existing text-to-image diffusion models, while excelling at subject synthesis, exhibit a persistent foreground bias that treats the background as a passive and under-optimized bypr…

cs.CL2026

When Does Context Help? Error Dynamics of Contextual Information in Large Language Models

Dingzirui Wang, Xuanliang Zhang, Keyan Xu +3

Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parame…

cs.CL2025

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond

Dingzirui Wang, Xuanliang Zhang, Keyan Xu +3

Existing research indicates that the output of Chain-of-Thought (CoT) is significantly affected by input perturbations. Although many methods aim to mitigate such impact by optimiz…