LLM teammates retain performance after swaps but coordinate less efficiently

Role-matched replacements preserved task scores but increased communication costs, especially after teams had developed distinct conventions.

PaperIndustrycs.AIarXiv:2609.05279v1
Jianxin Gao · Tianyi Yu · Linna Deng · Runze Li · Zining Wang

China Agricultural University · Tianjin University of Finance and Economics · Jilin University · Tianjin University of Science and Technology

Research Digest··2 min read
Gao et al. formed independent teams of agents from the same base model, allowed them to accumulate private notes over ten episodes, and then exchanged agents occupying matching roles. On held-out tasks, swaps had little effect on task performance but raised the communication required per unit of progress by 16% to 63%.

What they did

The authors created eight independent teams per experimental setting from a common base model. Each agent maintained a private notebook across ten team-formation episodes, allowing teammates to develop persistent conventions before evaluation.

They then traded role-matched agents between teams and tested the resulting teams on held-out tasks. A placebo intervention reproduced the disruption of a roster change without actually replacing the agent, helping isolate the effect of bringing in a teammate shaped by another team.

Key findings

  • Agent swaps caused little deterioration in task score, but increased communication per unit of progress by 16% to 63% relative to the placebo.
  • In Hanabi, a swapped agent was costlier to coordinate with than an inexperienced agent, which the authors interpret as interference from conventions learned with its previous partner.
  • In Collab-Overcooked, replacing the agenda-setting agent caused most of the additional communication to come from the teammate who remained.
  • Across changes to base model, decoding temperature, and formation length, larger differences between independently formed teams tracked larger swap penalties. Greedy decoding reduced both, while doubling team history increased both.

Why it matters

The results distinguish outcome-level interchangeability from coordination-level interchangeability. Multi-agent systems may preserve headline task performance after replacing a component while silently consuming more messages, tokens, time, or other coordination resources; replacement policies may therefore need to account for team-specific conventions and history.

Caveats

The reported evidence comes from controlled teams formed from a shared base model and evaluated on the paper's selected tasks, including Hanabi and Collab-Overcooked. It remains unclear how strongly the effect generalizes to heterogeneous models, larger or dynamically changing teams, real production workloads, or settings where communication costs directly constrain task success.

§

Analysis

The paper suggests that persistent agent memory can create both useful coordination and switching costs. Its correlation between team divergence and swap penalties points toward possible diagnostics for replacement risk, but does not by itself establish that divergence causes the added communication.

newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.