哈佛和MIT发现复合LLM系统中的角色漂移

Great technical paper from Harvard and MIT. It's on role drift in compound LLM systems. (bookmark it) End-to-end RL improves the accuracy of a multi-module LLM pipeline without constraining how the modules divide labor internally. Researchers name that failure mode and measure it. Role drift happens when a module preserves or improves end-task performance while abandoning its assigned role through shortcuts that system-level evaluation cannot see. Two instances across two pipelines: - A decomposer meant to split a question into sub-questions for a separate solver instead plants the answer inside them. - A reader meant to answer from retrieved passages instead falls back on parametric memory. An interesting finding is that if your hold the decomposer to its role and 86% of the RL improvement disappears. Role Anchor is the proposed control. It preserves how the role prompt shifts a module's next-token predictions relative to a neutral prompt, using that as a proxy for the role's intended effect during training. Gradient analysis indicates it reduces alignment with the drift direction rather than simply suppressing learning. Paper: https://t.co/kKvtowNXhP Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX