Agents that Matter: How Subtle Choices Shape Agent Attribution in Multi-Agent Systems

arXiv:2605.27621v2 Announce Type: replace-cross Abstract: As multi-agent systems (MAS) become increasingly complex, identifying the contributions of agents is critical for system optimization. However, existing approaches lack a unified formulation for credit assignment. In this work, we formalize agent attribution as a cooperative game, parameterized by the coalition distribution, intervention protocol, and target metric. Using this framework, we demonstrate that intervention protocols induce distinct games: Agent ablation isolates structural bottlenecks, whereas introspective LLM judges fail to faithfully approximate this behavior. We further find that Leave-One-Out (LOO) identifies bottleneck agents as effectively as combinatorial methods at much lower computational cost. Treating prompt optimization as an intervention protocol, we show that prompt-conditioned attribution can identify optimization targets and improve MAS performance. Finally, we apply our framework to audit a medical MAS, revealing that agent contributions to diagnostic accuracy and ethical behavior are often decoupled. By intervening on counterproductive roles, we observe an increase in ethics alignment while maintaining diagnostic accuracy. Overall, this work provides a principled approach for cost-effective MAS attribution and intervention.

Abstract:As multi-agent systems (MAS) become increasingly complex, identifying the contributions of agents is critical for system optimization. However, existing approaches lack a unified formulation for credit assignment. In this work, we formalize agent attribution as a cooperative game, parameterized by the coalition distribution, intervention protocol, and target metric. Using this framework, we demonstrate that intervention protocols induce distinct games: Agent ablation isolates structural bottlenecks, whereas introspective LLM judges fail to faithfully approximate this behavior. We further find that Leave-One-Out (LOO) identifies bottleneck agents as effectively as combinatorial methods at much lower computational cost. Treating prompt optimization as an intervention protocol, we show that prompt-conditioned attribution can identify optimization targets and improve MAS performance. Finally, we apply our framework to audit a medical MAS, revealing that agent contributions to diagnostic accuracy and ethical behavior are often decoupled. By intervening on counterproductive roles, we observe an increase in ethics alignment while maintaining diagnostic accuracy. Overall, this work provides a principled approach for cost-effective MAS attribution and intervention.

Multiagent Systems (cs.MA); Computation and Language (cs.CL)

arXiv:2605.27621 [cs.MA]

(or arXiv:2605.27621v2 [cs.MA] for this version)

https://doi.org/10.48550/arXiv.2605.27621 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

analiza aiqbench

Agents that Matter: How Subtle Choices Shape Agent Attribution in Multi-Agent Systems

Subiecte conexe