From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration

The paper compares human group discussions with large language model (LLM) deliberation traces on various reasoning tasks, finding that both humans and LLMs exhibit an assembly bonus asymmetry where discussion benefits the average member more than the best initial member. While LLM groups mirror some outcome-level patterns of human deliberation, they differ in process-level behaviors: they tend to follow majorities, surface less unique information, and converge earlier. Interventions inspired by human group‑decision research yield modest outcome improvements but do not eliminate coordination bottlenecks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents