{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIKIOQT3QCE352OFJ7QN6EBCA5","short_pith_number":"pith:LIKIOQT3","schema_version":"1.0","canonical_sha256":"5a1487427b8089bee9c54fe0df1022074d6a3ff3e0875f43e5667648f182895d","source":{"kind":"arxiv","id":"2408.08862","version":4},"attestation_state":"computed","paper":{"title":"Visual Agents as Fast and Slow Thinkers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng-Long Wang, Dongfang Liu, Guangyan Sun, Mingyu Jin, Qifan Wang, Siqi Ma, Tong Geng, Ying Nian Wu, Yongfeng Zhang, Zhenting Wang","submitted_at":"2024-08-16T17:44:02Z","abstract_excerpt":"Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition. Transitioning from structured benchmarks to real-world scenarios presents challenges for visual agents, often leading to inaccurate and overly confident responses. To address the challenge, we introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents. FaST employs a switch adapter to dynamically select between System 1/2 mod"},"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":"2408.08862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-16T17:44:02Z","cross_cats_sorted":[],"title_canon_sha256":"218d9205cc4fd74c6f4fafdd46f2f408d8a2b7f2df2e2f0037c09c0a3509f268","abstract_canon_sha256":"4bfbe85725f1014a306eb4b4394fe68b6c8210b49c68b100a282888f3b3f3d5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:23.127425Z","signature_b64":"515kTnLJgkRFUSLU8jZwOXX+P40GKk32emU2iAeBQe3QpYW7IO+7g728A+M4vXSebTFlhbsutZKkkupm09lGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a1487427b8089bee9c54fe0df1022074d6a3ff3e0875f43e5667648f182895d","last_reissued_at":"2026-07-05T10:11:23.126914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:23.126914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Agents as Fast and Slow Thinkers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cheng-Long Wang, Dongfang Liu, Guangyan Sun, Mingyu Jin, Qifan Wang, Siqi Ma, Tong Geng, Ying Nian Wu, Yongfeng Zhang, Zhenting Wang","submitted_at":"2024-08-16T17:44:02Z","abstract_excerpt":"Achieving human-level intelligence requires refining cognitive distinctions between System 1 and System 2 thinking. While contemporary AI, driven by large language models, demonstrates human-like traits, it falls short of genuine cognition. Transitioning from structured benchmarks to real-world scenarios presents challenges for visual agents, often leading to inaccurate and overly confident responses. To address the challenge, we introduce FaST, which incorporates the Fast and Slow Thinking mechanism into visual agents. FaST employs a switch adapter to dynamically select between System 1/2 mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08862","kind":"arxiv","version":4},"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/2408.08862/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":"2408.08862","created_at":"2026-07-05T10:11:23.126971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08862v4","created_at":"2026-07-05T10:11:23.126971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08862","created_at":"2026-07-05T10:11:23.126971+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIKIOQT3QCE3","created_at":"2026-07-05T10:11:23.126971+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIKIOQT3QCE352OF","created_at":"2026-07-05T10:11:23.126971+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIKIOQT3","created_at":"2026-07-05T10:11:23.126971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25319","citing_title":"V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20912","citing_title":"DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20912","citing_title":"DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15542","citing_title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05920","citing_title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14044","citing_title":"OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27494","citing_title":"Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14362","citing_title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5","json":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5.json","graph_json":"https://pith.science/api/pith-number/LIKIOQT3QCE352OFJ7QN6EBCA5/graph.json","events_json":"https://pith.science/api/pith-number/LIKIOQT3QCE352OFJ7QN6EBCA5/events.json","paper":"https://pith.science/paper/LIKIOQT3"},"agent_actions":{"view_html":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5","download_json":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5.json","view_paper":"https://pith.science/paper/LIKIOQT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08862&json=true","fetch_graph":"https://pith.science/api/pith-number/LIKIOQT3QCE352OFJ7QN6EBCA5/graph.json","fetch_events":"https://pith.science/api/pith-number/LIKIOQT3QCE352OFJ7QN6EBCA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5/action/storage_attestation","attest_author":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5/action/author_attestation","sign_citation":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5/action/citation_signature","submit_replication":"https://pith.science/pith/LIKIOQT3QCE352OFJ7QN6EBCA5/action/replication_record"}},"created_at":"2026-07-05T10:11:23.126971+00:00","updated_at":"2026-07-05T10:11:23.126971+00:00"}