{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N4LROOLBRBTWVYML4YKFK2U2SD","short_pith_number":"pith:N4LROOLB","schema_version":"1.0","canonical_sha256":"6f1717396188676ae18be614556a9a90d544a370cb191893d18f4f5cea63bb98","source":{"kind":"arxiv","id":"2605.24423","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiajun Zhang, Jian Cheng, Jiaxi Yang, Jinmin He, Junliang Xing, Kai Li, Lei Zhang, Yuheng Jing, Zeyao Ma, Zhe Wu, Ziwen Zhang","submitted_at":"2026-05-23T06:39:21Z","abstract_excerpt":"In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark ICRL4AHT, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collec"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.24423","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T06:39:21Z","cross_cats_sorted":[],"title_canon_sha256":"52175301495208e940d67a1e133cf1654b907c65d00592b9f8710fa1a2e56689","abstract_canon_sha256":"fa2330947244f24b7f248764ac540b2099409e0a19ef270d81d47f103a8d1808"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:39.015764Z","signature_b64":"SGQrk6/yB+SlDRPhQ+psz0xWSaC2KT4H9iZ2wiDT72P7ZjibT4e20w1f2Q/ZWrh/zj/eg6G0a++9gAAlwAD7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f1717396188676ae18be614556a9a90d544a370cb191893d18f4f5cea63bb98","last_reissued_at":"2026-05-26T01:03:39.014963Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:39.014963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jiajun Zhang, Jian Cheng, Jiaxi Yang, Jinmin He, Junliang Xing, Kai Li, Lei Zhang, Yuheng Jing, Zeyao Ma, Zhe Wu, Ziwen Zhang","submitted_at":"2026-05-23T06:39:21Z","abstract_excerpt":"In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordination with unknown partners is required-remains unexplored. To rigorously evaluate this, we introduce a large-scale benchmark ICRL4AHT, built upon a high-throughput JAX implementation of Overcooked-V2. Our benchmark includes a large, diverse teammate suite spanning both RL and heuristic policies, enabling controlled train-test shifts, and provides a reproducible end-to-end pipeline for teammate generation, learning-history collec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24423","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.24423/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.24423","created_at":"2026-05-26T01:03:39.015094+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24423v1","created_at":"2026-05-26T01:03:39.015094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24423","created_at":"2026-05-26T01:03:39.015094+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4LROOLBRBTW","created_at":"2026-05-26T01:03:39.015094+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4LROOLBRBTWVYML","created_at":"2026-05-26T01:03:39.015094+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4LROOLB","created_at":"2026-05-26T01:03:39.015094+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD","json":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD.json","graph_json":"https://pith.science/api/pith-number/N4LROOLBRBTWVYML4YKFK2U2SD/graph.json","events_json":"https://pith.science/api/pith-number/N4LROOLBRBTWVYML4YKFK2U2SD/events.json","paper":"https://pith.science/paper/N4LROOLB"},"agent_actions":{"view_html":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD","download_json":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD.json","view_paper":"https://pith.science/paper/N4LROOLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24423&json=true","fetch_graph":"https://pith.science/api/pith-number/N4LROOLBRBTWVYML4YKFK2U2SD/graph.json","fetch_events":"https://pith.science/api/pith-number/N4LROOLBRBTWVYML4YKFK2U2SD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD/action/storage_attestation","attest_author":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD/action/author_attestation","sign_citation":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD/action/citation_signature","submit_replication":"https://pith.science/pith/N4LROOLBRBTWVYML4YKFK2U2SD/action/replication_record"}},"created_at":"2026-05-26T01:03:39.015094+00:00","updated_at":"2026-05-26T01:03:39.015094+00:00"}