{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YOCFBCT4BOOXTCKGKVVS67EP3C","short_pith_number":"pith:YOCFBCT4","canonical_record":{"source":{"id":"2507.07441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:38:15Z","cross_cats_sorted":[],"title_canon_sha256":"0e6ed838407b761b76d960a7fd1f8e5ccea4f7e6f1281ff0226cf1acdb426feb","abstract_canon_sha256":"4cbbc0b66548310cf7c6ebc1b2ca00b184ed1dd6003e096f65df428973977c0c"},"schema_version":"1.0"},"canonical_sha256":"c384508a7c0b9d798946556b2f7c8fd8a7343c91e0e1e5d486e26a8eeffa6339","source":{"kind":"arxiv","id":"2507.07441","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07441","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07441v2","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07441","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"YOCFBCT4BOOX","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"YOCFBCT4BOOXTCKG","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"YOCFBCT4","created_at":"2026-07-05T11:56:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YOCFBCT4BOOXTCKGKVVS67EP3C","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:38:15Z","cross_cats_sorted":[],"title_canon_sha256":"0e6ed838407b761b76d960a7fd1f8e5ccea4f7e6f1281ff0226cf1acdb426feb","abstract_canon_sha256":"4cbbc0b66548310cf7c6ebc1b2ca00b184ed1dd6003e096f65df428973977c0c"},"schema_version":"1.0"},"canonical_sha256":"c384508a7c0b9d798946556b2f7c8fd8a7343c91e0e1e5d486e26a8eeffa6339","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:58.837348Z","signature_b64":"sLaFQgGi+5h9o5iXcYTfcDcNKeqcWP2h2vnr3U5NY5u5B7VlS+JI+jhhpcjpKNIaN7+1t0EF4cLhmyBZREbeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c384508a7c0b9d798946556b2f7c8fd8a7343c91e0e1e5d486e26a8eeffa6339","last_reissued_at":"2026-07-05T11:56:58.836911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:58.836911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07441","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e26tkKuGqK4noBHKGmfd+QKV80JEAXMbeO50okKa+qTdSI2cYRa8mOxEDY+ce0YlT5d5+6KY4O3wHfL2X7GtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:04:10.434865Z"},"content_sha256":"23afcc7c7bc07b8412a16ff045a1986901b2a5690816fd3aa359cef698e03dc1","schema_version":"1.0","event_id":"sha256:23afcc7c7bc07b8412a16ff045a1986901b2a5690816fd3aa359cef698e03dc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YOCFBCT4BOOXTCKGKVVS67EP3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAND: Boosting LLM Agents with Self-Taught Action Deliberation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Julian McAuley, Junda Wu, Lina Yao, Ryan A. Rossi, Sungchul Kim, Tong Yu, Yiran Shen, Yu Xia","submitted_at":"2025-07-10T05:38:15Z","abstract_excerpt":"Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts. Most of these methods focus on imitating specific expert behaviors or promoting chosen reasoning thoughts and actions over rejected ones. However, without reasoning and comparing over alternatives actions, LLM agents finetuned with these methods may over-commit towards seemingly plausible but suboptimal actions due to limited action space exploration. To address this, in this paper we propose Self-taught ActioN Deliberation (SAND)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07441","kind":"arxiv","version":2},"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/2507.07441/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RSoHSxGzcTfka3ur36LQqPzPTCr5jMKrk9HQkKFBDEzizJsxuMnH4tBIv+YBnAM79Zjs0KoK0M/s+ZVDl/gOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:04:10.435382Z"},"content_sha256":"c0fdf354dc1e927713c23050b8be30d610746da3199a0a5e2ba5f938868ebe90","schema_version":"1.0","event_id":"sha256:c0fdf354dc1e927713c23050b8be30d610746da3199a0a5e2ba5f938868ebe90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOCFBCT4BOOXTCKGKVVS67EP3C/bundle.json","state_url":"https://pith.science/pith/YOCFBCT4BOOXTCKGKVVS67EP3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOCFBCT4BOOXTCKGKVVS67EP3C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:04:10Z","links":{"resolver":"https://pith.science/pith/YOCFBCT4BOOXTCKGKVVS67EP3C","bundle":"https://pith.science/pith/YOCFBCT4BOOXTCKGKVVS67EP3C/bundle.json","state":"https://pith.science/pith/YOCFBCT4BOOXTCKGKVVS67EP3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOCFBCT4BOOXTCKGKVVS67EP3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YOCFBCT4BOOXTCKGKVVS67EP3C","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":"4cbbc0b66548310cf7c6ebc1b2ca00b184ed1dd6003e096f65df428973977c0c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:38:15Z","title_canon_sha256":"0e6ed838407b761b76d960a7fd1f8e5ccea4f7e6f1281ff0226cf1acdb426feb"},"schema_version":"1.0","source":{"id":"2507.07441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07441","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07441v2","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07441","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"YOCFBCT4BOOX","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"YOCFBCT4BOOXTCKG","created_at":"2026-07-05T11:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"YOCFBCT4","created_at":"2026-07-05T11:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:c0fdf354dc1e927713c23050b8be30d610746da3199a0a5e2ba5f938868ebe90","target":"graph","created_at":"2026-07-05T11:56:58Z","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/2507.07441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts. Most of these methods focus on imitating specific expert behaviors or promoting chosen reasoning thoughts and actions over rejected ones. However, without reasoning and comparing over alternatives actions, LLM agents finetuned with these methods may over-commit towards seemingly plausible but suboptimal actions due to limited action space exploration. To address this, in this paper we propose Self-taught ActioN Deliberation (SAND)","authors_text":"Julian McAuley, Junda Wu, Lina Yao, Ryan A. Rossi, Sungchul Kim, Tong Yu, Yiran Shen, Yu Xia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:38:15Z","title":"SAND: Boosting LLM Agents with Self-Taught Action Deliberation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07441","kind":"arxiv","version":2},"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":"sha256:23afcc7c7bc07b8412a16ff045a1986901b2a5690816fd3aa359cef698e03dc1","target":"record","created_at":"2026-07-05T11:56:58Z","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":"4cbbc0b66548310cf7c6ebc1b2ca00b184ed1dd6003e096f65df428973977c0c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T05:38:15Z","title_canon_sha256":"0e6ed838407b761b76d960a7fd1f8e5ccea4f7e6f1281ff0226cf1acdb426feb"},"schema_version":"1.0","source":{"id":"2507.07441","kind":"arxiv","version":2}},"canonical_sha256":"c384508a7c0b9d798946556b2f7c8fd8a7343c91e0e1e5d486e26a8eeffa6339","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c384508a7c0b9d798946556b2f7c8fd8a7343c91e0e1e5d486e26a8eeffa6339","first_computed_at":"2026-07-05T11:56:58.836911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:58.836911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sLaFQgGi+5h9o5iXcYTfcDcNKeqcWP2h2vnr3U5NY5u5B7VlS+JI+jhhpcjpKNIaN7+1t0EF4cLhmyBZREbeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:58.837348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23afcc7c7bc07b8412a16ff045a1986901b2a5690816fd3aa359cef698e03dc1","sha256:c0fdf354dc1e927713c23050b8be30d610746da3199a0a5e2ba5f938868ebe90"],"state_sha256":"0e7671f45e02a37a31b0af310f88ae1136b35233215711011b290e2a55a5ccb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bd23mpN2vyyAcSloc5KkgB153OAZr5GVf7ro9NMISpsFsTydhMOJ39WTz5AZA0+j5lu1OhhOGBpDjBmOsw86DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:04:10.439088Z","bundle_sha256":"cc665084e29b9fbd7c736649f6d57e0f245211155317daa0fb6fdb62b02ac511"}}