PRISM: PRIvileged Sibling-Guided Multi-Agent Topology Design

arXiv: 2610.20628 (cs.CL)

Submitted: 29 September 2026

Authors: Phuong Tuan Dat, Qi Li, Xinchao Wang

Primary Subject: Computation and Language (cs.CL)

DOI: https://doi.org/10.48550/arXiv.2610.20628

Overview

Multi-agent systems (MAS) built on large language models (LLMs) have become a powerful way to address complex problems. Their effectiveness depends critically on the collaboration topology—which agents participate and how they communicate.

Recent work learns to generate this topology from the task query, fitting the generator to corpora of execution-verified graphs. However, the post-training method for such generators remains a limitation: a corpus lists the graphs that solved a query but never ranks them, leaving continued supervised fine-tuning (SFT) with no per-query preference to exploit.

Without such a preference, the generator drifts toward the topologies the corpus contains most often rather than those that suit each query, so a gain on one task can come at a cost on another.

The PRISM Approach

We propose PRISM, which recovers per-query signal from the same corpus by learning with privileged information.

A teacher reads, through a zero-initialized low-rank branch, a sibling graph that also solved the query and is unavailable at deployment. The student then matches its per-decision targets on trajectories the student samples itself.

Results

Across six diverse benchmarks, PRISM improves over every topology-design baseline evaluated. Matched-teacher controls support the contribution of privileged query information.

Availability

Code is available in this link.

Cite as: arXiv:2610.20628 [cs.CL]

Submission History: [v1] Tue, 29 Sep 2026 17:22:16 UTC (284 KB)

via ArXiv CL+LG