Learning Self-Orchestration in Decentralized Agent Swarms

The capabilities of an agent swarm depend on both its individual members and how they coordinate.

By Xu, Qi, Kiruga +2Oct 15, 2026

Score████░░░░░░4.2

Caveats

Preprint; not yet peer reviewed.

VerdictWorth a reader's time today.

Read the original PDF Code

Abstract

The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents within fixed orchestration structures, separating the learning of individual capabilities from the organization of collective behavior. We introduce market-based post-training (MPT), a framework for jointly learning action policies and self-orchestration in decentralized agent swarms. Agents express their willingness to participate through bids, which determine who acts and how collective outcomes provide local training credit. Learning both action and bidding behavior allows individual capabilities and patterns of participation to adapt together without a central coordinating agent. We evaluate MPT on embodied crafting, robot navigation, and deep research. Results show gains over monolithic post-training and confirm that agent participation indeed evolves with learning. With the same post-trained action policies, learned self-orchestration outperforms alternative coordination strategies. Ablations show that both action and bidding benefit from learning, and that learned bids provide more effective action-training signals. Beyond the original training objectives, trained swarms adapt faster to related tasks and achieve better performance with larger populations at inference time. Larger populations also suffer smaller performance losses under agent dropout, demonstrating that learned self-orchestration supports reuse, scaling, and robustness in decentralized agent swarms. Code and trained models are available at https://github.com/Embodied-Minds-Lab/MPT.

Guowei Xu, Zhenting Qi, Amani Kiruga, Himabindu Lakkaraju, Yilun Du

The editor's rubric

Heuristic review

Leverage3 / 5: A method or resource many groups across the field will adopt within a year.; 24% of this desk’s rubric
Magnitude3 / 5: Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.; 18% of this desk’s rubric
Evidence3 / 5: Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.; 14% of this desk’s rubric
Novelty2 / 5: A new combination of known ideas.; 16% of this desk’s rubric
Trajectory3 / 5: A clear path to scale.; 18% of this desk’s rubric
Stakes2 / 5: Benefits a professional community (practitioners, clinicians, engineers).; 10% of this desk’s rubric

Dimension	Level	Weight	What that level means
Leverage	███░░ 3	24%	A method or resource many groups across the field will adopt within a year.
Magnitude	███░░ 3	18%	Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
Evidence	███░░ 3	14%	Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
Novelty	██░░░ 2	16%	A new combination of known ideas.
Trajectory	███░░ 3	18%	A clear path to scale.
Stakes	██░░░ 2	10%	Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); gains (outperforms); verification (ablations, code released); scale (scalable, efficient); stakes (general AI).

How the score was computed

rank-2026-10-18

Score████░░░░░░4.2

Score = 10 × (65% × adjusted merit / 10 + 25% × attention + 10% × freshness)

Desks place stronger verdicts first, then use this score to order work within the same verdict.

Merit: 5.5 / 10; Weighted rubric, evidence-gated.
Adjusted merit: 4.6 / 10; Shrunk toward the desk prior by editor confidence (42%).
Attention: 31%; Citations, upvotes, points, mentions.
Freshness: 46%; Half-life decay since publication.

Citations0 (reference 15, via semantic-scholar, Oct 18, 2026, 13:49 UTC)
Influential citations0 (reference 3, via semantic-scholar, Oct 18, 2026, 13:49 UTC)
Hugging Face upvotes10 (reference 25, via hf-daily, Oct 18, 2026, 13:49 UTC)
GitHub stars8 (reference 250, via hf-daily, Oct 18, 2026, 13:49 UTC)

The record

Reviewed by heuristic-v7 on Oct 18, 2026, 13:49 UTC. Paper type: method.
Categories: cs.MA, cs.AI, cs.CL
BRIEF, No.3 in the Artificial Intelligence edition of October 18, 2026.