{"record": {"aliases": ["Benchmarking Open-Ended Multi-Agent Coordination in Language Agents"], "artifacts": [{"id": "arxiv:2606.08340", "kind": "paper", "url": "https://arxiv.org/abs/2606.08340"}, {"id": "gh:alem-world/alem-env", "kind": "repo", "url": "https://github.com/alem-world/alem-env"}], "authors": ["Kale-ab Abebe Tessera", "Andras Szecsenyi", "Cameron Barker", "Alexander Rutherford", "Davide Paglieri", "Aidan Scannell", "Henry Gouk", "Elliot J. Crowley", "Tim Rocktäschel", "Amos Storkey"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.08340", "source_url": "https://arxiv.org/abs/2606.08340"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "alem is a JAX-based, long-horizon environment for evaluating coordination among language-agent teams through survival, exploration, crafting, trading, and combat."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.08340", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.08340", "title": "alem"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Edinburgh", "University of Oxford", "University College London"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.08340", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.08340", "source_url": "https://openalex.org/W7164042786"}, "key": "claire-radar:2606.08340", "modality": null, "name": "alem", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_benchmarking-open-ended-multi-agent-coordi_e8962f70", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "517fe99bd69d6966cba422a74b73ed9e8c80b55b1bfcab66345a13a3b2cb38f4", "relation": "introduces", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T17:05:10.792317Z", "source_url": "https://arxiv.org/abs/2606.08340"}, "publisher": null, "released": "2026-06-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.08340", "source_url": "https://arxiv.org/abs/2606.08340"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-08340", "source": "claire_radar", "source_benchmark_id": "2606.08340", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Benchmarking Open-Ended Multi-Agent Coordination in Language Agents"], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Open-ended multi-agent evaluation, frontier-model comparisons, and a public environment provide several credible paths to near-term technical attention.", "score": 4}, "capabilities": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T17:05:10.792317Z", "inputHash": "09ffa2a45943869497f979d6a93afc9b7ecd71885e9b31d9cae44c321a9059a7", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We introduce $alem$, a JAX-based benchmark for open-ended multi-agent coordination", "canonicalNameSource": "abstract", "decisionReason": "The supplied abstract formally names the benchmark, defines its coordination task, reports normalized-return scoring, and provides a public code repository for reuse.", "evaluationEvidence": {"reuse": "Code is available at https://github.com/alem-world/alem-env.", "scoring": "averaging only ~6% normalised return", "task": "open-ended multi-agent coordination built on Craftax-like dynamics"}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T17:05:10.792317Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "alem is a JAX-based, long-horizon environment for evaluating coordination among language-agent teams through survival, exploration, crafting, trading, and combat.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce $alem$, a JAX-based benchmark for open-ended multi-agent coordination built on Craftax-like dynamics."}, "familyId": "bmf_28e32d3036c5", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_benchmarking-open-ended-multi-agent-coordi_e8962f70", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/alem-world/alem-env", "data": null, "paper": "https://arxiv.org/abs/2606.08340", "pdf": "https://arxiv.org/pdf/2606.08340", "project": null, "report": "https://arxiv.org/abs/2606.08340"}, "metrics": [], "motivation": "As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks.", "name": "alem", "oneLine": "alem is a JAX-based, long-horizon environment for evaluating coordination among language-agent teams through survival, exploration, crafting, trading, and combat.", "paperTitle": "Benchmarking Open-Ended Multi-Agent Coordination in Language Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.08340", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "alem-world", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://github.com/alem-world/alem-env"}], "readiness": "Runnable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-06-06", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Kale-ab Abebe Tessera", "Andras Szecsenyi", "Cameron Barker", "Alexander Rutherford", "Davide Paglieri", "Aidan Scannell", "Henry Gouk", "Elliot J. Crowley", "Tim Rockt\\\"aschel", "Amos Storkey"], "categories": ["cs.AI", "cs.LG", "cs.MA"], "id": "2606.08340", "title": "Benchmarking Open-Ended Multi-Agent Coordination in Language Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.08340"}, "sourceUpdatedAt": "2026-06-06T21:13:43Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "It makes multi-agent coordination measurable separately from individual task competence and exposes differences in communication, role allocation, and shared-plan execution."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
