{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NNGOB6WANGI6P5TQQON5AIXEET","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":"d96f159ee9dba57c77c1bdc11bc633e60175229433523169d19a8e02f9d04306","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T11:05:27Z","title_canon_sha256":"e075ad04ce8d99af3aa4935a0a5ff7b5587d02d6e32e533837c07b9a202535aa"},"schema_version":"1.0","source":{"id":"2502.15771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15771","created_at":"2026-07-05T11:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15771v2","created_at":"2026-07-05T11:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15771","created_at":"2026-07-05T11:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"NNGOB6WANGI6","created_at":"2026-07-05T11:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"NNGOB6WANGI6P5TQ","created_at":"2026-07-05T11:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"NNGOB6WA","created_at":"2026-07-05T11:11:42Z"}],"graph_snapshots":[{"event_id":"sha256:93395d556c812b77209edad61ed76dfec6bd4877183cc885461d52f9c7777d2a","target":"graph","created_at":"2026-07-05T11:11:42Z","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/2502.15771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solving complex tasks in a single attempt is challenging for large language models (LLMs). Iterative interaction with the environment and feedback is often required to achieve success, making effective feedback utilization a critical topic. Existing approaches either struggle with length generalization or rely on naive retries without leveraging prior information. In this paper, we introduce FTTT, a novel paradigm that formulates feedback utilization as an optimization problem at test time. Additionally, we propose a learnable test-time optimizer, OpTune, to effectively exploit feedback. Exper","authors_text":"Liwei Wang, Michael Lyu, Yanyang Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T11:05:27Z","title":"Learning to Reason from Feedback at Test-Time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15771","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:fc6c44627c5b295db16ef44411b40592ff1c0c5acaa1bcd6c5217816762295ba","target":"record","created_at":"2026-07-05T11:11:42Z","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":"d96f159ee9dba57c77c1bdc11bc633e60175229433523169d19a8e02f9d04306","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-16T11:05:27Z","title_canon_sha256":"e075ad04ce8d99af3aa4935a0a5ff7b5587d02d6e32e533837c07b9a202535aa"},"schema_version":"1.0","source":{"id":"2502.15771","kind":"arxiv","version":2}},"canonical_sha256":"6b4ce0fac06991e7f670839bd022e424da07ad8a0726c33c4a87ca6808336d80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b4ce0fac06991e7f670839bd022e424da07ad8a0726c33c4a87ca6808336d80","first_computed_at":"2026-07-05T11:11:42.284002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:42.284002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ubWDRgs2HXkBiMayogwz1n4N0sNCl56tHnvExHevNbXU5KRCM7Jm5ctJ5EOIEJIHLbyZlBm0XY3oC9EfgUuyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:42.284490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc6c44627c5b295db16ef44411b40592ff1c0c5acaa1bcd6c5217816762295ba","sha256:93395d556c812b77209edad61ed76dfec6bd4877183cc885461d52f9c7777d2a"],"state_sha256":"77bb4aad8fc77108e50f58f276cfb6b9ba8087a1bf3fe3593450246d5b9aa2f3"}