4 papers · 1 filter
Who Speaks, Who Authorizes, Who Acts? Understanding Trust Boundaries in Multi-Agent LLMs
Junru Zhu, Xin Chen, Hang Lyu +6
Multi-agent LLM systems exchange messages before acting through tools, but message delivery, signing authority, and tool-side enforcement are separate trust boundaries. We represen…
Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
Yezhou Cheng, Runjia Du, Zeming Liu +3
How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspecting the wo…
Scope Before You Persist: Preventing Cross-Family Interference in Agent Memory
Yezhou Cheng, Runjia Du, Zeming Liu +5
Persistent memory lets language-model agents improve prompts and skills without updating model weights. We show that matching retrieval scope to certification scope enables these e…
Sharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation
Yezhou Cheng, Runjia Du, Zeming Liu +5
Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $…