{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QTKDZWKQCGIN37XEWEDLAIV3TL","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":"8962c6d5e8aec9fc1631c5275514b4ab36691847b95edacc1bc796d1496843d4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T21:42:35Z","title_canon_sha256":"e1a8ab156ed6ddc0ff5dd1dd5979646aa9d1b2eef83eaf70cda3170b5dd3bbef"},"schema_version":"1.0","source":{"id":"2410.02052","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02052","created_at":"2026-07-05T10:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02052v5","created_at":"2026-07-05T10:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02052","created_at":"2026-07-05T10:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"QTKDZWKQCGIN","created_at":"2026-07-05T10:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"QTKDZWKQCGIN37XE","created_at":"2026-07-05T10:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"QTKDZWKQ","created_at":"2026-07-05T10:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:e5031fce5cc027ecefafd13913292ffd55fc67b1d70498a2b81a694dccee8450","target":"graph","created_at":"2026-07-05T10:21:23Z","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/2410.02052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks. However, even state-of-the-art vision-language models (VLMs), such as GPT-4o, still fall short of human-level performance, particularly in intricate web environments and long-horizon tasks. To address these limitations, we present ExACT, an approach to combine test-time search and self-learning to build o1-like models for agentic applications. We first introduce Reflective Monte Carlo Tree Search (R-MCTS), a novel test time algorithm designed to enhance AI agents' ability to explore","authors_text":"Baolin Peng, Hao Cheng, Jianfeng Gao, Michel Galley, Vineeth Vajipey, Xiao Yu, Zhou Yu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T21:42:35Z","title":"ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02052","kind":"arxiv","version":5},"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":"sha256:514356f1cf2a21a11f96196fde13591499e76091fb03c6d30d69fa59013d6aef","target":"record","created_at":"2026-07-05T10:21:23Z","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":"8962c6d5e8aec9fc1631c5275514b4ab36691847b95edacc1bc796d1496843d4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T21:42:35Z","title_canon_sha256":"e1a8ab156ed6ddc0ff5dd1dd5979646aa9d1b2eef83eaf70cda3170b5dd3bbef"},"schema_version":"1.0","source":{"id":"2410.02052","kind":"arxiv","version":5}},"canonical_sha256":"84d43cd9501190ddfee4b106b022bb9af3f0adf9668b31aaaf9db967159d1426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84d43cd9501190ddfee4b106b022bb9af3f0adf9668b31aaaf9db967159d1426","first_computed_at":"2026-07-05T10:21:23.834914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:23.834914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9AgGBFE09JdgdEl14wPB7g9OXMzEsQ8tvLtbs9aXD2tPNhR3ftJMixhsNfF+Hv5giC/OYqhzYLKfNpmQy5pSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:23.835449Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02052","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:514356f1cf2a21a11f96196fde13591499e76091fb03c6d30d69fa59013d6aef","sha256:e5031fce5cc027ecefafd13913292ffd55fc67b1d70498a2b81a694dccee8450"],"state_sha256":"c738d0707077aff4aab9fde0721045e02c35d3c609a8b0e83bc7a2befbdffbf8"}