{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:J7VUG42JD5JBL64RU2NUU2WAAQ","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":"f78f393dab00f2fc22e7e269ac70fc1956099f6c5b1d59df2310d647659f48d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T16:55:50Z","title_canon_sha256":"526f93f4ca6a708da6b5cd71aff634c7c95e61ed26200328e66c4a56b8dc13c3"},"schema_version":"1.0","source":{"id":"2608.12253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12253","created_at":"2026-08-13T01:30:37Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12253v1","created_at":"2026-08-13T01:30:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12253","created_at":"2026-08-13T01:30:37Z"},{"alias_kind":"pith_short_12","alias_value":"J7VUG42JD5JB","created_at":"2026-08-13T01:30:37Z"},{"alias_kind":"pith_short_16","alias_value":"J7VUG42JD5JBL64R","created_at":"2026-08-13T01:30:37Z"},{"alias_kind":"pith_short_8","alias_value":"J7VUG42J","created_at":"2026-08-13T01:30:37Z"}],"graph_snapshots":[{"event_id":"sha256:f780871231cf0ee5cfe3366c4b15e488de29772855712559973eb4367a99fec3","target":"graph","created_at":"2026-08-13T01:30:37Z","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/2608.12253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior. We show that this approach systematically fails to generalize, and trace the failure to simulator collapse: because the simulator LLM is mode-collapsed, an LLM policy trained against it overfits to narrow strategies that exploit the simulator's dominant mode, and such a policy transfers poorly to unseen simulators and real users. We formalize this collapse theoretically and propose two complementary solutions, one at inference time and one at training time. T","authors_text":"Abe Hou, Christopher D. Manning, Derek Chong, Dilara Soylu, Marwa Abdulhai, Nicholas Tomlin, Sergey Levine, Simon Yu, Weiyan Shi, Ximing Lu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T16:55:50Z","title":"One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12253","kind":"arxiv","version":1},"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:ea97cbd6a1bf9b7854c3ef60e0ca79654a5425390cc324b2dad979d585e7be95","target":"record","created_at":"2026-08-13T01:30:37Z","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":"f78f393dab00f2fc22e7e269ac70fc1956099f6c5b1d59df2310d647659f48d4","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-12T16:55:50Z","title_canon_sha256":"526f93f4ca6a708da6b5cd71aff634c7c95e61ed26200328e66c4a56b8dc13c3"},"schema_version":"1.0","source":{"id":"2608.12253","kind":"arxiv","version":1}},"canonical_sha256":"4feb4373491f5215fb91a69b4a6ac0040d8e322c2f97d1fdcf23d6afa71a82fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4feb4373491f5215fb91a69b4a6ac0040d8e322c2f97d1fdcf23d6afa71a82fd","first_computed_at":"2026-08-13T01:30:37.562237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:30:37.562237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gp3AVxNbQ7IGexODyoX5RbcEfmnkxxIspfQWm5BX3wGAgFWfeptiYv98Beay6TTqarGMPXMs8fGZOwBlZcX2Aw==","signature_status":"signed_v1","signed_at":"2026-08-13T01:30:37.564773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea97cbd6a1bf9b7854c3ef60e0ca79654a5425390cc324b2dad979d585e7be95","sha256:f780871231cf0ee5cfe3366c4b15e488de29772855712559973eb4367a99fec3"],"state_sha256":"49b20e7c5d345661ebd47ce7edb3f5c8aab51954b77dfe97a4a5b7e0dc4d13f3"}