{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SR4SNW3AAQVRBVENIKIIB5WAYR","short_pith_number":"pith:SR4SNW3A","schema_version":"1.0","canonical_sha256":"947926db60042b10d48d429080f6c0c4639ef9fc6b35e048df11e7fe2a900836","source":{"kind":"arxiv","id":"2605.12655","version":1},"attestation_state":"computed","paper":{"title":"Macro-Action Based Multi-Agent Instruction Following through Value Cancellation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Correcting the Bellman backup target at each instruction boundary decouples value estimates across contexts, allowing a single policy to follow interrupting instructions while preserving base-task performance in multi-agent settings.","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Enrico Marchesini Xiang Zhi Tan, Ethan Rathbun, Wo Wei Lin","submitted_at":"2026-05-12T19:01:16Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instructi"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.12655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T19:01:16Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"43132de58f7a27c4c4df01db7fb108f2740977bcc8221c99ca27420f797786e6","abstract_canon_sha256":"13f9e0b6287753427bb2b64460e41c6fe500857010a03b3d0ec76c17189af15d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:50.661982Z","signature_b64":"ZmVB8uY7OwQykk5LC/55UDBsKmKWhWqO4JwoQfNmLVpvkBygky+O/eqhFQzO3/Qejx1V4IdgBUczPw5DinbbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"947926db60042b10d48d429080f6c0c4639ef9fc6b35e048df11e7fe2a900836","last_reissued_at":"2026-05-18T03:09:50.661167Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:50.661167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Macro-Action Based Multi-Agent Instruction Following through Value Cancellation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Correcting the Bellman backup target at each instruction boundary decouples value estimates across contexts, allowing a single policy to follow interrupting instructions while preserving base-task performance in multi-agent settings.","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Enrico Marchesini Xiang Zhi Tan, Ethan Rathbun, Wo Wei Lin","submitted_at":"2026-05-12T19:01:16Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instructi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That correcting the bootstrapping target at instruction boundaries is sufficient to fully decouple value estimates across contexts without introducing new inconsistencies under stochastic switching or macro-action interruptions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in a unified policy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Correcting the Bellman backup target at each instruction boundary decouples value estimates across contexts, allowing a single policy to follow interrupting instructions while preserving base-task performance in multi-agent settings.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"db942b2271ccb422000eb5a68eb94c0fce7bf00258e2963a03f50d84c618cd04"},"source":{"id":"2605.12655","kind":"arxiv","version":1},"verdict":{"id":"7d79834b-368f-4ab7-815a-1cdca8494a7b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:32:37.115796Z","strongest_claim":"MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.","one_line_summary":"MAVIC corrects Bellman backups at instruction boundaries by adjusting the incoming objective and restoring continuation value, enabling consistent estimation under stochastic instruction switching in a unified policy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That correcting the bootstrapping target at instruction boundaries is sufficient to fully decouple value estimates across contexts without introducing new inconsistencies under stochastic switching or macro-action interruptions.","pith_extraction_headline":"Correcting the Bellman backup target at each instruction boundary decouples value estimates across contexts, allowing a single policy to follow interrupting instructions while preserving base-task performance in multi-agent settings."},"references":{"count":4,"sample":[{"doi":"","year":2021,"title":"bring me the tomato,","work_id":"c529cb9f-0686-4e65-9c98-3a674afd2fcb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"When c=c ′, the reward is unchanged","work_id":"b7590f98-9c18-416a-bcc3-e45947033d44","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Don’t use left cutting board","work_id":"adad8480-b299-45e0-8d41-eafaaff87697","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Go to small boxes","work_id":"ced46404-1005-42e0-8a0d-ba22a2e91f4c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":4,"snapshot_sha256":"dc6afdeced95dd3b205a114113da17d69f20013332fe56e6db4f3b2b1d7a6f4d","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":"2605.12655","created_at":"2026-05-18T03:09:50.661310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12655v1","created_at":"2026-05-18T03:09:50.661310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12655","created_at":"2026-05-18T03:09:50.661310+00:00"},{"alias_kind":"pith_short_12","alias_value":"SR4SNW3AAQVR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"SR4SNW3AAQVRBVEN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"SR4SNW3A","created_at":"2026-05-18T12:33:37.589309+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/SR4SNW3AAQVRBVENIKIIB5WAYR","json":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR.json","graph_json":"https://pith.science/api/pith-number/SR4SNW3AAQVRBVENIKIIB5WAYR/graph.json","events_json":"https://pith.science/api/pith-number/SR4SNW3AAQVRBVENIKIIB5WAYR/events.json","paper":"https://pith.science/paper/SR4SNW3A"},"agent_actions":{"view_html":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR","download_json":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR.json","view_paper":"https://pith.science/paper/SR4SNW3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12655&json=true","fetch_graph":"https://pith.science/api/pith-number/SR4SNW3AAQVRBVENIKIIB5WAYR/graph.json","fetch_events":"https://pith.science/api/pith-number/SR4SNW3AAQVRBVENIKIIB5WAYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR/action/storage_attestation","attest_author":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR/action/author_attestation","sign_citation":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR/action/citation_signature","submit_replication":"https://pith.science/pith/SR4SNW3AAQVRBVENIKIIB5WAYR/action/replication_record"}},"created_at":"2026-05-18T03:09:50.661310+00:00","updated_at":"2026-05-18T03:09:50.661310+00:00"}