8 papers
Jev-ToM: Evaluating Theory of Mind in Typed Decision Models
Kawai Chung, Chunkit Chan, Yuxuan Liu +9
Dialogue and collaborative assistants repeatedly judge what a partner knows, believes, or intends. Typed decision models offer a potential alternative to generative large language…
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
Yuxuan Liu, Zhaochen Su, Hangyu Guo +11
Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand task requir…
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
Yuxuan Liu, Haoran Li, Yuhao Zhang +10
Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct b…
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
Yuxuan Liu, Zhaochen Su, Yuhao Zhang +9
Self-evolving skill systems promise to improve agents by turning execution feedback into persistent skill updates without changing the underlying model. Yet it remains unclear when…
Steering LLM Viewpoints through Fabricated Evidence Injection
Xi Yang, Chang Liu, Zhenglin Huang +4
As chatbots increasingly influence daily decision-making, their potential to produce misleading responses poses substantial risks to users. This paper investigates a critical cogni…
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
Yuxuan Liu, Zhaochen Su, Lingyun Xie +11
Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints, and recover from failures. Existing self-evolving methods refine skills using…
InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Grounding
Cheng Jiayang, Qianqian Zhuang, Haoran Li +4
Grounding large language models (LLMs) in external knowledge sources is a promising method for faithful prediction. While existing grounding approaches work well for simple queries…
Persona Knowledge-Aligned Prompt Tuning Method for Online Debate
Chunkit Chan, Cheng Jiayang, Xin Liu +7
Debate is the process of exchanging viewpoints or convincing others on a particular issue. Recent research has provided empirical evidence that the persuasiveness of an argument is…