Problem
Research questions and friction points this paper is trying to address.
LLM Agents
Human-like Deliberation
Collaborative Problem Solving
Process Signatures
Assembly Bonus
From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaboration
🤖 AI Summary
研究通过比较人类与LLM在多种推理任务中的讨论过程，分析了LLM协作中出现的‘组装奖励’现象及其与人类机制的不同，揭示了两者在信息多样性及决策收敛性上的差异。
📝 Abstract
LLM agents are increasingly used for collaborative problem solving and human-group simulation. This makes outcome-only evaluation insufficient: if LLM groups are used as models of human groups, we need to know whether they succeed or fail through human-like deliberative mechanisms. We compare human group chats with matched LLM deliberation traces on Wason-style deductive reasoning, then test whether the same process signatures generalize to analogical, abductive, and analytical tasks. Humans and LLMs show the same assembly bonus asymmetry: discussion improves the average member more often than the best initial member. Initial-answer diversity accounts for the effect of model heterogeneity, increasing movement in both corrective and destructive directions. The main differences are process-level. Compared with humans, LLM groups follow majorities more often, surface less unique information, and converge earlier; correct minority signals succeed mainly when re-expressed early. Interventions motivated by human group-decision research yield modest improvements in collective outcomes, but do not remove the coordination bottleneck. Together, these results suggest that LLM groups can reproduce some outcome-level patterns of human deliberation while diverging in the mechanisms that generate assembly bonus and process loss, with implications for group simulation and human-AI collaboration.
Innovation
Methods, ideas, or system contributions that make the work stand out.
LLM deliberation
assembly bonus asymmetry
process signatures
group simulation
human-AI collaboration
🔎 Similar Papers
No similar papers found.
