{"paper":{"title":"Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.MA","authors_text":"Brandon Yee, Pairie Koh","submitted_at":"2026-03-03T22:15:27Z","abstract_excerpt":"As multi-agent Large Language Model (LLM) systems scale, evaluating their emergent coordination dynamics becomes increasingly critical. However, current evaluation paradigms-focused on single agents or small, explicitly structured groups-fail to capture the self-organization and viral information dynamics that arise in large, decentralized populations. We introduce a systematic evaluation framework to benchmark role specialization, information diffusion, and cooperative task resolution in open agent environments. We demonstrate this framework on the MoltBook Observatory Archive, a dataset of 2"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By providing standardized evaluation tasks and empirical baselines, our framework enables the rigorous comparison of future multi-agent protocols and establishes evaluation itself as an object of scientific study.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the MoltBook Observatory Archive of 2.73M interactions among 90,704 agents is representative of genuine emergent coordination dynamics in real-world large-scale LLM populations and that the chosen metrics (silhouette score, power-law exponent, Cohen's d) adequately capture the relevant coordination phenomena.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Presents a benchmarking framework for emergent coordination in large LLM agent populations, with baselines from 2.73 million interactions showing strong core-periphery structure, heavy-tailed cascades, and high decentralized overhead.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"496df6d42c88315f68873b17dbe12eaa65bc516d610356875c7adafc07809867"},"source":{"id":"2603.03555","kind":"arxiv","version":3},"verdict":{"id":"4a4a47f9-da0e-4e70-8860-2936515cb116","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T16:03:47.772108Z","strongest_claim":"By providing standardized evaluation tasks and empirical baselines, our framework enables the rigorous comparison of future multi-agent protocols and establishes evaluation itself as an object of scientific study.","one_line_summary":"Presents a benchmarking framework for emergent coordination in large LLM agent populations, with baselines from 2.73 million interactions showing strong core-periphery structure, heavy-tailed cascades, and high decentralized overhead.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the MoltBook Observatory Archive of 2.73M interactions among 90,704 agents is representative of genuine emergent coordination dynamics in real-world large-scale LLM populations and that the chosen metrics (silhouette score, power-law exponent, Cohen's d) adequately capture the relevant coordination phenomena.","pith_extraction_headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.03555/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}