{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M3PBBCOOUVRH3IOEZVIWJSJN2J","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":"4cd7700f5ecf8cfba416fe85de5b8834e070056a886d5c04b88ecbcaf95ab900","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:35:42Z","title_canon_sha256":"4009082a2c598a4e641ebf2e0ea5d330c4aa6a99b1973b6d954a0ed70be87661"},"schema_version":"1.0","source":{"id":"2502.01600","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01600","created_at":"2026-07-05T10:26:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01600v3","created_at":"2026-07-05T10:26:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01600","created_at":"2026-07-05T10:26:43Z"},{"alias_kind":"pith_short_12","alias_value":"M3PBBCOOUVRH","created_at":"2026-07-05T10:26:43Z"},{"alias_kind":"pith_short_16","alias_value":"M3PBBCOOUVRH3IOE","created_at":"2026-07-05T10:26:43Z"},{"alias_kind":"pith_short_8","alias_value":"M3PBBCOO","created_at":"2026-07-05T10:26:43Z"}],"graph_snapshots":[{"event_id":"sha256:99412ad58389a7cc53f3f737b23506918a2f64751bdff350816c08592263cc62","target":"graph","created_at":"2026-07-05T10:26:43Z","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/2502.01600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interactive digital agents (IDAs) leverage APIs of stateful digital environments to perform tasks in response to user requests. While IDAs powered by instruction-tuned large language models (LLMs) can react to feedback from interface invocations in multi-step exchanges, they have not been trained in their respective digital environments. Prior methods accomplish less than half of tasks in sophisticated benchmarks such as AppWorld. We present a reinforcement learning (RL) approach that trains IDAs directly in their target environments. We formalize this training as a partially observable Markov","authors_text":"Aleksei Petrenko, Brody Huval, Jackson Hamburger, Kevin Chen, Marco Cusumano-Towner, Philipp Kr\\\"ahenb\\\"uhl, Vladlen Koltun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:35:42Z","title":"Reinforcement Learning for Long-Horizon Interactive LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01600","kind":"arxiv","version":3},"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":"sha256:9a61f61da2ea4e7424e5828d10e45e9dfa1d3255db02ee14a8552c64293e07d7","target":"record","created_at":"2026-07-05T10:26:43Z","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":"4cd7700f5ecf8cfba416fe85de5b8834e070056a886d5c04b88ecbcaf95ab900","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T18:35:42Z","title_canon_sha256":"4009082a2c598a4e641ebf2e0ea5d330c4aa6a99b1973b6d954a0ed70be87661"},"schema_version":"1.0","source":{"id":"2502.01600","kind":"arxiv","version":3}},"canonical_sha256":"66de1089cea5627da1c4cd5164c92dd25259d9d162f4b400319a9a0e65b66151","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66de1089cea5627da1c4cd5164c92dd25259d9d162f4b400319a9a0e65b66151","first_computed_at":"2026-07-05T10:26:43.513663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:26:43.513663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qKTi7iEzzSrh7Lpu+bR9fAb2Wkkcaou7p27mLmeGf1NAvjRU3oo3SSHST19FhCbi4PiX4Z/0Y63xjUb9Yj8cBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:26:43.514393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01600","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a61f61da2ea4e7424e5828d10e45e9dfa1d3255db02ee14a8552c64293e07d7","sha256:99412ad58389a7cc53f3f737b23506918a2f64751bdff350816c08592263cc62"],"state_sha256":"a3d3c59caadee8a64ba71a50cd8b4e04d5b4684095d4abcfc997e8519b730d93"}