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

arXiv: https://arxiv.org/abs/2609.13261 · HTML: https://mlsanity.com/paper/2609.13261/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 35 of its 90 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 35)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs](https://mlsanity.com/paper/2309.13007/) (2023)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents](https://mlsanity.com/paper/2412.03563/) (2024)
- [Voting or Consensus? Decision-Making in Multi-Agent Debate](https://mlsanity.com/paper/2502.19130/) (2025)
- [GenSim: A General Social Simulation Platform with Large Language Model based Agents](https://mlsanity.com/paper/2410.04360/) (2024)
- [Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information](https://mlsanity.com/paper/2402.18144/) (2024)
- [From LSAT: The Progress and Challenges of Complex Reasoning](https://mlsanity.com/paper/2108.00648/) (2021)
- [X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs](https://mlsanity.com/paper/2505.16997/) (2025)
- [Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoning](https://mlsanity.com/paper/2504.05047/) (2025)
- [DeliData: A dataset for deliberation in multi-party problem solving](https://mlsanity.com/paper/2108.05271/) (2021)
- [Confidence Calibration and Rationalization for LLMs via Multi-Agent Deliberation](https://mlsanity.com/paper/2404.09127/) (2024)
- [Six Fallacies in Substituting Large Language Models for Human Participants](https://mlsanity.com/paper/2402.04470/) (2024)
- [Stay Focused: Problem Drift in Multi-Agent Debate](https://mlsanity.com/paper/2502.19559/) (2025)
- [Enhancing Multi-Agent Debate System Performance via Confidence Expression](https://mlsanity.com/paper/2509.14034/) (2025)
- [Counterfactual Debating with Preset Stances for Hallucination Elimination of LLMs](https://mlsanity.com/paper/2406.11514/) (2024)
- [GPT-4 Emulates Average-Human Emotional Cognition from a Third-Person Perspective](https://mlsanity.com/paper/2408.13718/) (2024)
- [SAND: Boosting LLM Agents with Self-Taught Action Deliberation](https://mlsanity.com/paper/2507.07441/) (2025)
- [AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions](https://mlsanity.com/paper/2602.06008/) (2026)
- [Agents on the Bench: Large Language Model Based Multi Agent Framework for Trustworthy Digital Justice](https://mlsanity.com/paper/2412.18697/) (2024)
- [CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate](https://mlsanity.com/paper/2507.03928/) (2025)
- [Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation](https://mlsanity.com/paper/2509.06337/) (2025)
- [Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models](https://mlsanity.com/paper/2601.04861/) (2026)
- [Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning](https://mlsanity.com/paper/2603.01221/) (2026)

## Abstract (arXiv)

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.