{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WGDKXYEGN3423ONDX2LPTRVL2P","short_pith_number":"pith:WGDKXYEG","schema_version":"1.0","canonical_sha256":"b186abe0866ef9adb9a3be96f9c6abd3dd7096b8c4e2720c3ff6aa99ddbbc018","source":{"kind":"arxiv","id":"2506.05236","version":2},"attestation_state":"computed","paper":{"title":"Towards Language-Augmented Multi-Agent Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Fa\\\"iz Benamar, Jae-Yun Jun, Maxime Toquebiau, Nicolas Bredeche","submitted_at":"2025-06-05T16:55:52Z","abstract_excerpt":"Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we investigate how grounding agents in a human-defined language can improve the learning and coordination of embodied agents. We propose a framework in which agents are trained not only to act but also to produce and interpret natural language descriptions of their observations. This language-augmented learning serves a dual role: enabling efficient and interpre"},"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":"2506.05236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-06-05T16:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"31f0735d4d13f05a466a445c492d1cbdcf3494880e639ada57fcbdd83d1909ea","abstract_canon_sha256":"4f17da4a64f00ba4658dcc72bd68d96239438a6f2450234d99a9982e049c00ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:55.201204Z","signature_b64":"MoxXAivY9W5vzOic9FfynR5gCK9N5UBxR7e1s0aGPlc04BQVFjqrT5IG8RkfUn7r4kjl1iL6s/hgNnL2OsufBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b186abe0866ef9adb9a3be96f9c6abd3dd7096b8c4e2720c3ff6aa99ddbbc018","last_reissued_at":"2026-07-05T11:49:55.200763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:55.200763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Language-Augmented Multi-Agent Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Fa\\\"iz Benamar, Jae-Yun Jun, Maxime Toquebiau, Nicolas Bredeche","submitted_at":"2025-06-05T16:55:52Z","abstract_excerpt":"Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we investigate how grounding agents in a human-defined language can improve the learning and coordination of embodied agents. We propose a framework in which agents are trained not only to act but also to produce and interpret natural language descriptions of their observations. This language-augmented learning serves a dual role: enabling efficient and interpre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05236","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/2506.05236/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":"2506.05236","created_at":"2026-07-05T11:49:55.200822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05236v2","created_at":"2026-07-05T11:49:55.200822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05236","created_at":"2026-07-05T11:49:55.200822+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGDKXYEGN342","created_at":"2026-07-05T11:49:55.200822+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGDKXYEGN3423OND","created_at":"2026-07-05T11:49:55.200822+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGDKXYEG","created_at":"2026-07-05T11:49:55.200822+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/WGDKXYEGN3423ONDX2LPTRVL2P","json":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P.json","graph_json":"https://pith.science/api/pith-number/WGDKXYEGN3423ONDX2LPTRVL2P/graph.json","events_json":"https://pith.science/api/pith-number/WGDKXYEGN3423ONDX2LPTRVL2P/events.json","paper":"https://pith.science/paper/WGDKXYEG"},"agent_actions":{"view_html":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P","download_json":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P.json","view_paper":"https://pith.science/paper/WGDKXYEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05236&json=true","fetch_graph":"https://pith.science/api/pith-number/WGDKXYEGN3423ONDX2LPTRVL2P/graph.json","fetch_events":"https://pith.science/api/pith-number/WGDKXYEGN3423ONDX2LPTRVL2P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P/action/storage_attestation","attest_author":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P/action/author_attestation","sign_citation":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P/action/citation_signature","submit_replication":"https://pith.science/pith/WGDKXYEGN3423ONDX2LPTRVL2P/action/replication_record"}},"created_at":"2026-07-05T11:49:55.200822+00:00","updated_at":"2026-07-05T11:49:55.200822+00:00"}