Grounding LLM Agents in Knowledge, Context, and Action

PhD Thesis Proposal Defence


Title: "Grounding LLM Agents in Knowledge, Context, and Action"

by

Mr. Jiayang CHENG


Abstract:

Large language models (LLMs) are increasingly deployed as autonomous agents,
yet they remain insufficiently grounded in the information they rely on. This
thesis studies LLM agent grounding along three dimensions. For knowledge, we
develop methods for detecting and resolving conflicts among retrieved evidence,
finding that even strong LLMs frequently favor one piece of conflicting
evidence without justification. We further introduce an evaluation framework
for verifying claims that require multiple interdependent pieces of evidence,
revealing that models struggle with partially supported claims and tend to
compensate for missing information using internal knowledge. For context, we
build an interactive benchmark that evaluates how well agents maintain memory
over extended conversations through on-policy interaction, uncovering
significant memory limitations across both standalone LLMs and LLM-powered
agents. For action, we train agents to orchestrate multi-step API calls
through reinforcement learning with a graduated reward design that decomposes
correctness into atomic validity and orchestration consistency, improving
performance on complex tool-use tasks. Collectively, these contributions
provide evaluation tools and training methods that help LLM agents operate
more reliably in real-world settings.


Date:                   Wednesday, 19 March 2026

Time:                   9:00am - 11:00am

Venue:                  Room 2132C
                        Lift 22

Committee Members:      Dr. Yangqiu Song (Supervisor)
                        Prof. Raymond Wong (Chairperson)
                        Dr. May Fung