4 papers
EnGRICH: Enhancing Generative Reward Modeling with Critiques from Humans
Xuancheng Li, Beining Wang, Haitao Li +7
Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside preference judgments, providing…
SkillAlchemy: Open-World Agent Skill Creation
Hengjun Wang, Shuyue Wei, Boyi Liu +2
Agent skills are reusable procedural artifacts that extend language agents with specialized workflows, tool conventions, and domain behaviors at inference time. However, creating r…
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
Chang Liu, Yuqi Zhang, Yiman Zhong +3
Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Existing agent skills are primari…
Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models
Xuancheng Li, Xuanchen Li, Haitao Li +6
User feedback offers natural supervision for persistent LLM improvement, but a single message may support multiple behavioral changes with different scopes of generalization. We in…