{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F5UPDFXW2JLIU6TT7IFKYQCXMJ","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":"4967dec33adb663ee9715a24d2e916d5cf4a2842c9b38aa2c73c98478f7b9729","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T02:47:29Z","title_canon_sha256":"d2682b17d4cd27c2a25a2abde5e0aaacf1ed94287a8dfca13eb003c1a80f0c1f"},"schema_version":"1.0","source":{"id":"2606.05622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05622","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05622v1","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05622","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_12","alias_value":"F5UPDFXW2JLI","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_16","alias_value":"F5UPDFXW2JLIU6TT","created_at":"2026-06-05T01:14:56Z"},{"alias_kind":"pith_short_8","alias_value":"F5UPDFXW","created_at":"2026-06-05T01:14:56Z"}],"graph_snapshots":[{"event_id":"sha256:7e3d5a1081fc4cf6a11a790906306f5013164b756221e62e0290f806dcc1d236","target":"graph","created_at":"2026-06-05T01:14:56Z","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/2606.05622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclosed through interaction. However, existing benchmarks still underexplore adaptive planning under such progressively revealed dual constraints. To address this gap, we introduce AdaPlanBench, a dynamic interactive benchmark for evaluating whether Large Language Model (LLM) agents can adaptively plan and re-plan under progressively revealed world and user constraints. AdaPlanBench is built on 307 household tasks, with a scalable ","authors_text":"Bingxuan Li, Cheng Qian, Heng Ji, Heng Wang, Jeonghwan Kim, Jiateng Liu, Jiayu Liu, Xiusi Chen, Yi R. Fung, Yumeng Wang, Zhenhailong Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T02:47:29Z","title":"AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05622","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:db146f4ba0fe20668cd3ba2bc4bdfdf27cdc0d7b17527b00000e1cfbe1870481","target":"record","created_at":"2026-06-05T01:14:56Z","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":"4967dec33adb663ee9715a24d2e916d5cf4a2842c9b38aa2c73c98478f7b9729","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T02:47:29Z","title_canon_sha256":"d2682b17d4cd27c2a25a2abde5e0aaacf1ed94287a8dfca13eb003c1a80f0c1f"},"schema_version":"1.0","source":{"id":"2606.05622","kind":"arxiv","version":1}},"canonical_sha256":"2f68f196f6d2568a7a73fa0aac4057625bb56f387351ce2abb949aa1bca10719","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f68f196f6d2568a7a73fa0aac4057625bb56f387351ce2abb949aa1bca10719","first_computed_at":"2026-06-05T01:14:56.778931Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:14:56.778931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FsqzBz1ZXnh/lgUDZZ53m6MvfGmP0NlEp6xrD+Lj94G/CgRq4qBQJgg2XLYv2RhK0d4yPwVpOLH4QZBGD3UDg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:14:56.779575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db146f4ba0fe20668cd3ba2bc4bdfdf27cdc0d7b17527b00000e1cfbe1870481","sha256:7e3d5a1081fc4cf6a11a790906306f5013164b756221e62e0290f806dcc1d236"],"state_sha256":"283cedd8aac2332ee4aaca119be2dfd5924bbc37bdfb16e5853e7a31c4fe2e83"}