{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C757O2MRLHQBAEEYAMLEYHRIXC","short_pith_number":"pith:C757O2MR","schema_version":"1.0","canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","source":{"kind":"arxiv","id":"2303.11381","version":1},"attestation_state":"computed","paper":{"title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ce Liu, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Michael Zeng, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-03-20T18:31:47Z","abstract_excerpt":"We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows lan"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2303.11381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-20T18:31:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"d8fc08a05575b94e41ebafb15d423ba6457301a1ecb6e571ce2d3f5d4f47bbb0","abstract_canon_sha256":"ad55e24432253d2a7fd679fd3f5d8e67b783e447d9f8098fe700f8965e46239c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:00:13.088103Z","signature_b64":"kMNFWkKgzOuQdXY3C7yoiTv2eBYTzSHtQUA2vkPYWFby03hLD0hPhnY/ANxKj8/i6TTsCgHoLbjK5nc8gV/uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17fbf7699159e010109803164c1e28b8be7a9d986cdbd49dc4371790e0fd38f7","last_reissued_at":"2026-05-18T03:00:13.087518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:00:13.087518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ce Liu, Ehsan Azarnasab, Faisal Ahmed, Jianfeng Wang, Kevin Lin, Lijuan Wang, Linjie Li, Michael Zeng, Zhengyuan Yang, Zicheng Liu","submitted_at":"2023-03-20T18:31:47Z","abstract_excerpt":"We propose MM-REACT, a system paradigm that integrates ChatGPT with a pool of vision experts to achieve multimodal reasoning and action. In this paper, we define and explore a comprehensive list of advanced vision tasks that are intriguing to solve, but may exceed the capabilities of existing vision and vision-language models. To achieve such advanced visual intelligence, MM-REACT introduces a textual prompt design that can represent text descriptions, textualized spatial coordinates, and aligned file names for dense visual signals such as images and videos. MM-REACT's prompt design allows lan"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The textual prompt design can faithfully represent and allow language models to process dense visual signals such as images and videos without loss of critical information.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9d7f11d0f7de4153634e5044445836d36d2ec36322404c5ff59d92a988d63b19"},"source":{"id":"2303.11381","kind":"arxiv","version":1},"verdict":{"id":"b74c6a6f-c277-4064-92f1-c74bac347ebb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T01:12:43.672888Z","strongest_claim":"Zero-shot experiments demonstrate MM-REACT's effectiveness in addressing the specified capabilities of interests and its wide application in different scenarios that require advanced visual understanding.","one_line_summary":"MM-REACT uses textual prompts to let ChatGPT collaborate with external vision experts for zero-shot multimodal reasoning and action on advanced visual tasks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The textual prompt design can faithfully represent and allow language models to process dense visual signals such as images and videos without loss of critical information.","pith_extraction_headline":"A textual prompt design lets ChatGPT collaborate with vision experts to handle advanced multimodal reasoning and action in zero-shot settings."},"references":{"count":60,"sample":[{"doi":"","year":2022,"title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","work_id":"037320f1-b0a9-4cbe-a639-bfb25409ce71","ref_index":1,"cited_arxiv_id":"2204.01691","is_internal_anchor":true},{"doi":"","year":2022,"title":"Flamingo: a Visual Language Model for Few-Shot Learning","work_id":"a110f764-38dc-41b2-a802-53744ecea1fc","ref_index":2,"cited_arxiv_id":"2204.14198","is_internal_anchor":true},{"doi":"","year":2020,"title":"Lan- guage models are few-shot learners","work_id":"9d80ea01-55d6-44ef-a69e-0ca87cabb940","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"End-to- end object detection with transformers","work_id":"8376a687-7c64-4343-88ee-9ab3141e93a7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Harrison Chase. Langchain. https://langchain. readthedocs.io/, 2023. 4 6 Figure 4. Case studies of MM-R EACT’s capabilities and application scenarios: visual math and text reasoning. 7","work_id":"28eb406b-9a34-43fa-94df-ca72fd959644","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"0c88837ac336b5a608d05b739f13655b39808a38ed12b8adc144911be5f17fbb","internal_anchors":18},"formal_canon":{"evidence_count":2,"snapshot_sha256":"eaed9143d2045250ee98f9ffdd88129e7a4f5d96c1f76f99d18c8a3e7d5d81dd"},"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":"2303.11381","created_at":"2026-05-18T03:00:13.087598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11381v1","created_at":"2026-05-18T03:00:13.087598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11381","created_at":"2026-05-18T03:00:13.087598+00:00"},{"alias_kind":"pith_short_12","alias_value":"C757O2MRLHQB","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"C757O2MRLHQBAEEY","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"C757O2MR","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":42,"internal_anchor_count":42,"sample":[{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16409","citing_title":"Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16740","citing_title":"TRACE: Evidence Grounding-Guided Multi-Video Event Understanding and Claim Generation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":290,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20911","citing_title":"FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2409.07825","citing_title":"Deep Multimodal Learning with Missing Modality: A Survey","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2506.09965","citing_title":"Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2403.00476","citing_title":"TempCompass: Do Video LLMs Really Understand Videos?","ref_index":128,"is_internal_anchor":true},{"citing_arxiv_id":"2310.14566","citing_title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2401.16158","citing_title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2501.07542","citing_title":"Imagine while Reasoning in Space: Multimodal Visualization-of-Thought","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":142,"is_internal_anchor":true},{"citing_arxiv_id":"2304.05376","citing_title":"ChemCrow: Augmenting large-language models with chemistry tools","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01070","citing_title":"How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2305.18323","citing_title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13228","citing_title":"ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2311.10122","citing_title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2305.06355","citing_title":"VideoChat: Chat-Centric Video Understanding","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00270","citing_title":"OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":167,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC","json":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC.json","graph_json":"https://pith.science/api/pith-number/C757O2MRLHQBAEEYAMLEYHRIXC/graph.json","events_json":"https://pith.science/api/pith-number/C757O2MRLHQBAEEYAMLEYHRIXC/events.json","paper":"https://pith.science/paper/C757O2MR"},"agent_actions":{"view_html":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC","download_json":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC.json","view_paper":"https://pith.science/paper/C757O2MR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11381&json=true","fetch_graph":"https://pith.science/api/pith-number/C757O2MRLHQBAEEYAMLEYHRIXC/graph.json","fetch_events":"https://pith.science/api/pith-number/C757O2MRLHQBAEEYAMLEYHRIXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/action/storage_attestation","attest_author":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/action/author_attestation","sign_citation":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/action/citation_signature","submit_replication":"https://pith.science/pith/C757O2MRLHQBAEEYAMLEYHRIXC/action/replication_record"}},"created_at":"2026-05-18T03:00:13.087598+00:00","updated_at":"2026-05-18T03:00:13.087598+00:00"}