{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JOTFE6GBV5IC77G3DUJUOYPC4I","short_pith_number":"pith:JOTFE6GB","schema_version":"1.0","canonical_sha256":"4ba65278c1af502ffcdb1d134761e2e2095069e4d27cd167962616cc13bc9028","source":{"kind":"arxiv","id":"2605.29293","version":1},"attestation_state":"computed","paper":{"title":"LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Hui Xiong, Xiaoguang Wu, Zhi Zheng","submitted_at":"2026-05-28T03:19:08Z","abstract_excerpt":"Effective training-time guidance is central to multi-agent reinforcement learning (MARL), yet remains difficult in sparse-reward settings where weak supervision limits coordination and policy improvement, and existing methods often require substantial domain expertise or manual design effort. Large language models (LLMs) provide a promising alternative for flexible learning-signal design, yet existing LLM-based methods remain largely single-agent-oriented, one-shot, or weakly validated for the evolving training dynamics of cooperative MARL. To address these limitations, we propose LLM-ALSO, an"},"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":"2605.29293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2026-05-28T03:19:08Z","cross_cats_sorted":[],"title_canon_sha256":"77cb92e15122302a344474e57b508254e36c2abb92576d049d939da6b972341f","abstract_canon_sha256":"82de68c85fc365f1fb3774fa56341bfdc31677ad057ccb6f1d68e4e02279f956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:29.838204Z","signature_b64":"pL/UMx1XXIKJ2/0ddmzNb1lkNWqsLdlPsKA+tUvNmOd2tvhJLSDRyJV4fVXW+Dv82Tjfj4pTfR5fhgrvq+15Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ba65278c1af502ffcdb1d134761e2e2095069e4d27cd167962616cc13bc9028","last_reissued_at":"2026-05-29T01:05:29.837441Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:29.837441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Hui Xiong, Xiaoguang Wu, Zhi Zheng","submitted_at":"2026-05-28T03:19:08Z","abstract_excerpt":"Effective training-time guidance is central to multi-agent reinforcement learning (MARL), yet remains difficult in sparse-reward settings where weak supervision limits coordination and policy improvement, and existing methods often require substantial domain expertise or manual design effort. Large language models (LLMs) provide a promising alternative for flexible learning-signal design, yet existing LLM-based methods remain largely single-agent-oriented, one-shot, or weakly validated for the evolving training dynamics of cooperative MARL. To address these limitations, we propose LLM-ALSO, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29293","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/2605.29293/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":"2605.29293","created_at":"2026-05-29T01:05:29.837569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29293v1","created_at":"2026-05-29T01:05:29.837569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29293","created_at":"2026-05-29T01:05:29.837569+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOTFE6GBV5IC","created_at":"2026-05-29T01:05:29.837569+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOTFE6GBV5IC77G3","created_at":"2026-05-29T01:05:29.837569+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOTFE6GB","created_at":"2026-05-29T01:05:29.837569+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/JOTFE6GBV5IC77G3DUJUOYPC4I","json":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I.json","graph_json":"https://pith.science/api/pith-number/JOTFE6GBV5IC77G3DUJUOYPC4I/graph.json","events_json":"https://pith.science/api/pith-number/JOTFE6GBV5IC77G3DUJUOYPC4I/events.json","paper":"https://pith.science/paper/JOTFE6GB"},"agent_actions":{"view_html":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I","download_json":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I.json","view_paper":"https://pith.science/paper/JOTFE6GB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29293&json=true","fetch_graph":"https://pith.science/api/pith-number/JOTFE6GBV5IC77G3DUJUOYPC4I/graph.json","fetch_events":"https://pith.science/api/pith-number/JOTFE6GBV5IC77G3DUJUOYPC4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I/action/storage_attestation","attest_author":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I/action/author_attestation","sign_citation":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I/action/citation_signature","submit_replication":"https://pith.science/pith/JOTFE6GBV5IC77G3DUJUOYPC4I/action/replication_record"}},"created_at":"2026-05-29T01:05:29.837569+00:00","updated_at":"2026-05-29T01:05:29.837569+00:00"}