Papers
arxiv:2610.29292

Credit Where Credit Is Due: Contrastive Attribution Topology Search for Multi-Agent Systems

Published on Oct 21
Authors:
,

Abstract

A contrastive attribution method searches compact teams of specialized LLM agents by assigning per-agent credit from execution traces, improving accuracy and reducing token use while pruning harmful agents.

An LLM multi-agent system (MAS) is only as good as the agents it chooses to trust: its accuracy and cost hinge on its topology, meaning which agents are included and how they communicate. A single task score, however, does not reveal which agents help or hinder performance. We propose Contrastive Attribution Topology Search (CATS), which searches for compact teams within a fixed supergraph of specialized agents. An LLM attributer compares execution traces across candidate topologies and assigns credit to individual agents. CATS uses these credits to update supergraph edges while progressively pruning weak edges and agents, yielding a small team for deployment. With small open-weight models and matched candidate evaluations, CATS improves mean accuracy on BigCodeBench by 5.3 percentage points over score-only heuristic search while using 54% fewer deployment tokens. On MBPP, CATS matches the strongest baselines with fewer tokens than the other searches. In a HotpotQA prompt-poisoning stress test, CATS excludes all adversarially prompted agents in all three runs, whereas random search retains some at comparable accuracy. Per-agent credit thus supports both team optimization and the pruning of potentially harmful agents.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2610.29292
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.29292 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.29292 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.29292 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.