8 papers
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…
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…
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…
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…
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…
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…