{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QTKDZWKQCGIN37XEWEDLAIV3TL","short_pith_number":"pith:QTKDZWKQ","schema_version":"1.0","canonical_sha256":"84d43cd9501190ddfee4b106b022bb9af3f0adf9668b31aaaf9db967159d1426","source":{"kind":"arxiv","id":"2410.02052","version":5},"attestation_state":"computed","paper":{"title":"ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Hao Cheng, Jianfeng Gao, Michel Galley, Vineeth Vajipey, Xiao Yu, Zhou Yu","submitted_at":"2024-10-02T21:42:35Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.02052","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T21:42:35Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e1a8ab156ed6ddc0ff5dd1dd5979646aa9d1b2eef83eaf70cda3170b5dd3bbef","abstract_canon_sha256":"8962c6d5e8aec9fc1631c5275514b4ab36691847b95edacc1bc796d1496843d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:23.835449Z","signature_b64":"9AgGBFE09JdgdEl14wPB7g9OXMzEsQ8tvLtbs9aXD2tPNhR3ftJMixhsNfF+Hv5giC/OYqhzYLKfNpmQy5pSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84d43cd9501190ddfee4b106b022bb9af3f0adf9668b31aaaf9db967159d1426","last_reissued_at":"2026-07-05T10:21:23.834914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:23.834914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Baolin Peng, Hao Cheng, Jianfeng Gao, Michel Galley, Vineeth Vajipey, Xiao Yu, Zhou Yu","submitted_at":"2024-10-02T21:42:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02052","kind":"arxiv","version":5},"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/2410.02052/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.02052","created_at":"2026-07-05T10:21:23.834970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02052v5","created_at":"2026-07-05T10:21:23.834970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02052","created_at":"2026-07-05T10:21:23.834970+00:00"},{"alias_kind":"pith_short_12","alias_value":"QTKDZWKQCGIN","created_at":"2026-07-05T10:21:23.834970+00:00"},{"alias_kind":"pith_short_16","alias_value":"QTKDZWKQCGIN37XE","created_at":"2026-07-05T10:21:23.834970+00:00"},{"alias_kind":"pith_short_8","alias_value":"QTKDZWKQ","created_at":"2026-07-05T10:21:23.834970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2602.15353","citing_title":"NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17180","citing_title":"BranchBench: Aligning Database Branching with Agentic Demands","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL","json":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL.json","graph_json":"https://pith.science/api/pith-number/QTKDZWKQCGIN37XEWEDLAIV3TL/graph.json","events_json":"https://pith.science/api/pith-number/QTKDZWKQCGIN37XEWEDLAIV3TL/events.json","paper":"https://pith.science/paper/QTKDZWKQ"},"agent_actions":{"view_html":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL","download_json":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL.json","view_paper":"https://pith.science/paper/QTKDZWKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02052&json=true","fetch_graph":"https://pith.science/api/pith-number/QTKDZWKQCGIN37XEWEDLAIV3TL/graph.json","fetch_events":"https://pith.science/api/pith-number/QTKDZWKQCGIN37XEWEDLAIV3TL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL/action/storage_attestation","attest_author":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL/action/author_attestation","sign_citation":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL/action/citation_signature","submit_replication":"https://pith.science/pith/QTKDZWKQCGIN37XEWEDLAIV3TL/action/replication_record"}},"created_at":"2026-07-05T10:21:23.834970+00:00","updated_at":"2026-07-05T10:21:23.834970+00:00"}