{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BK35VD2F55HJCXB2I3UBIEAYZY","short_pith_number":"pith:BK35VD2F","canonical_record":{"source":{"id":"2410.03997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-05T01:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"90ef096cbc3d4ea8841c0d61cc07eaea3d5170d9605d679b1616b1f638ce5ae9","abstract_canon_sha256":"8832a125b30b067f1932ce4cee81482a0dda556ac985a7914c4edfc494b3d372"},"schema_version":"1.0"},"canonical_sha256":"0ab7da8f45ef4e915c3a46e8141018ce0c866691854edd32977f2c238ac0dff7","source":{"kind":"arxiv","id":"2410.03997","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03997","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03997v2","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03997","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"BK35VD2F55HJ","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"BK35VD2F55HJCXB2","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"BK35VD2F","created_at":"2026-07-05T11:23:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BK35VD2F55HJCXB2I3UBIEAYZY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03997","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-05T01:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"90ef096cbc3d4ea8841c0d61cc07eaea3d5170d9605d679b1616b1f638ce5ae9","abstract_canon_sha256":"8832a125b30b067f1932ce4cee81482a0dda556ac985a7914c4edfc494b3d372"},"schema_version":"1.0"},"canonical_sha256":"0ab7da8f45ef4e915c3a46e8141018ce0c866691854edd32977f2c238ac0dff7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:18.644079Z","signature_b64":"wJic8AiPO7q2g7ojT2ld7/g441KfudUbXxLT7pKldTWS49oQu06M33d4eLC4J2dlbQJ+pRpPyZNF13bFXB/DDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ab7da8f45ef4e915c3a46e8141018ce0c866691854edd32977f2c238ac0dff7","last_reissued_at":"2026-07-05T11:23:18.643359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:18.643359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03997","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tt/vYu5s0NF1JRCi+jas7VBG8dOHjGiXPZLXhKuOYMIrA9164kucLbTiN2//z3Xz9LKfB1cvBPO2F+4oDEsuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:19:50.525866Z"},"content_sha256":"ce1ebd7d025dcd227ad8438fce8ce384265a467a155739c299accf1c3afaeff7","schema_version":"1.0","event_id":"sha256:ce1ebd7d025dcd227ad8438fce8ce384265a467a155739c299accf1c3afaeff7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BK35VD2F55HJCXB2I3UBIEAYZY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Fei Miao, Yi Shen, Yuan Zhuang, Yuxiao Chen, Zhili Zhang","submitted_at":"2024-10-05T01:44:11Z","abstract_excerpt":"Advancements in deep multi-agent reinforcement learning (MARL) have positioned it as a promising approach for decision-making in cooperative games. However, it still remains challenging for MARL agents to learn cooperative strategies for some game environments. Recently, large language models (LLMs) have demonstrated emergent reasoning capabilities, making them promising candidates for enhancing coordination among the agents. However, due to the model size of LLMs, it can be expensive to frequently infer LLMs for actions that agents can take. In this work, we propose You Only LLM Once for MARL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03997","kind":"arxiv","version":2},"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/2410.03997/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:23:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t2Qn7bcgrJLjMeExETe4Xq3HazSAuZJHrSaYsRWpXT0fRRp0p7OqySLXmC12lS8R7/RMM6sw+69XbaMLg1/DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:19:50.526385Z"},"content_sha256":"e79cd2ce6dfdf190864d196cbe481086be0b2e18a0e411851a26cd8035c724b4","schema_version":"1.0","event_id":"sha256:e79cd2ce6dfdf190864d196cbe481086be0b2e18a0e411851a26cd8035c724b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BK35VD2F55HJCXB2I3UBIEAYZY/bundle.json","state_url":"https://pith.science/pith/BK35VD2F55HJCXB2I3UBIEAYZY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BK35VD2F55HJCXB2I3UBIEAYZY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T17:19:50Z","links":{"resolver":"https://pith.science/pith/BK35VD2F55HJCXB2I3UBIEAYZY","bundle":"https://pith.science/pith/BK35VD2F55HJCXB2I3UBIEAYZY/bundle.json","state":"https://pith.science/pith/BK35VD2F55HJCXB2I3UBIEAYZY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BK35VD2F55HJCXB2I3UBIEAYZY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BK35VD2F55HJCXB2I3UBIEAYZY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8832a125b30b067f1932ce4cee81482a0dda556ac985a7914c4edfc494b3d372","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-05T01:44:11Z","title_canon_sha256":"90ef096cbc3d4ea8841c0d61cc07eaea3d5170d9605d679b1616b1f638ce5ae9"},"schema_version":"1.0","source":{"id":"2410.03997","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03997","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03997v2","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03997","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"pith_short_12","alias_value":"BK35VD2F55HJ","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"pith_short_16","alias_value":"BK35VD2F55HJCXB2","created_at":"2026-07-05T11:23:18Z"},{"alias_kind":"pith_short_8","alias_value":"BK35VD2F","created_at":"2026-07-05T11:23:18Z"}],"graph_snapshots":[{"event_id":"sha256:e79cd2ce6dfdf190864d196cbe481086be0b2e18a0e411851a26cd8035c724b4","target":"graph","created_at":"2026-07-05T11:23:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.03997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advancements in deep multi-agent reinforcement learning (MARL) have positioned it as a promising approach for decision-making in cooperative games. However, it still remains challenging for MARL agents to learn cooperative strategies for some game environments. Recently, large language models (LLMs) have demonstrated emergent reasoning capabilities, making them promising candidates for enhancing coordination among the agents. However, due to the model size of LLMs, it can be expensive to frequently infer LLMs for actions that agents can take. In this work, we propose You Only LLM Once for MARL","authors_text":"Fei Miao, Yi Shen, Yuan Zhuang, Yuxiao Chen, Zhili Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-05T01:44:11Z","title":"YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03997","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce1ebd7d025dcd227ad8438fce8ce384265a467a155739c299accf1c3afaeff7","target":"record","created_at":"2026-07-05T11:23:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8832a125b30b067f1932ce4cee81482a0dda556ac985a7914c4edfc494b3d372","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-10-05T01:44:11Z","title_canon_sha256":"90ef096cbc3d4ea8841c0d61cc07eaea3d5170d9605d679b1616b1f638ce5ae9"},"schema_version":"1.0","source":{"id":"2410.03997","kind":"arxiv","version":2}},"canonical_sha256":"0ab7da8f45ef4e915c3a46e8141018ce0c866691854edd32977f2c238ac0dff7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ab7da8f45ef4e915c3a46e8141018ce0c866691854edd32977f2c238ac0dff7","first_computed_at":"2026-07-05T11:23:18.643359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:18.643359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wJic8AiPO7q2g7ojT2ld7/g441KfudUbXxLT7pKldTWS49oQu06M33d4eLC4J2dlbQJ+pRpPyZNF13bFXB/DDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:18.644079Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03997","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce1ebd7d025dcd227ad8438fce8ce384265a467a155739c299accf1c3afaeff7","sha256:e79cd2ce6dfdf190864d196cbe481086be0b2e18a0e411851a26cd8035c724b4"],"state_sha256":"0e2f99458430472a64613d198c6f4e9205c4a4ed43541899a5a306e3800e03be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SZO79u6SSU4jsfVoV27mALoxQ8DQn5rrUlw38DpAiR5CZFUQqdJL/3qXbLuSp2oinKfLXbP6pdKpu3oRZFFhBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:19:50.530297Z","bundle_sha256":"0ea8b554e0500ddee442d292bc0c01820ac81652331896bc6ce8b4c06d1b3487"}}