Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models

Abstract:Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning quality. We present an adaptive multi-agent controller (ADMA) that learns continuous policies for proposal, challenge, arbitration, and coordination while keeping the task model frozen. Shared trace features describe quality, agreement, and progress, while role-specific features support decentralized control during inference. One controller trained on legal and financial reasoning is transferred without policy updates to four textual and multimodal benchmarks and two successive task-model versions. With Qwen3.5 held fixed, ADMA-Full improves accuracy by 6.2-14.2 percentage points over Direct and by 2.8-3.0 points over ADMA-Fixed. Paired bootstrap ranges for the Full-Fixed comparison are positive on three tasks. Outcome decompositions show that recoveries exceed introduced errors, while process assessment records fewer false-consensus events and more supported correct outcomes. Transfer to Qwen3.6 remains task dependent, which bounds the generality of the learned policy. Median token and latency ratios are 14.3-18.7 and 7.8-16.5 relative to Direct. These results show that adaptive deliberation can improve fixed-model recognition when its task-dependent gains justify the additional computation.

33 pages, including references and technical appendices. Supplementary data included in the ancillary files

Artificial Intelligence (cs.AI)

arXiv:2610.17840 [cs.AI]

(or arXiv:2610.17840v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.17840 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

data/cost_distributions.csv

data/cross_endpoint_transitions.csv

data/cross_version_accuracy.csv

data/incremental_costs.csv

data/outcome_round_allocation.csv

data/paired_bootstrap_intervals.csv

data/paired_differences.csv

data/protocol_paths.csv

data/question_results.csv

data/reliability_states.csv

data/repeat_consistency.csv

data/run_metrics.csv

data/strong_task_failure_incidence.csv

data/within_endpoint_subgroups.csv

(12 additional files not shown) You must enabled JavaScript to view entire file list.

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.