2 citations · 2 across the 5 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems
Xiaoyang Cao, Siddarth Srinivasan, Michiel A. Bakker
End-to-end reinforcement learning can improve the accuracy of compound LLM systems, but it does not constrain how modules divide labor internally. We identify Role Drift, a failure…
cs.AI2026
Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation
Joshua C. Yang, Maurice Flechtner, Damian Dailisan +1
LLM-based agents are increasingly used to simulate deliberative interactions such as negotiation, conflict resolution, and multi-turn opinion exchange. Yet generated transcripts of…