{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3GABHT2CFF5TYFMGM3UVNPT6U5","short_pith_number":"pith:3GABHT2C","schema_version":"1.0","canonical_sha256":"d98013cf42297b3c158666e956be7ea74fcaeef5b6afb15b644c3746d5b2ae37","source":{"kind":"arxiv","id":"2302.07842","version":1},"attestation_state":"computed","paper":{"title":"Augmented Language Models: a Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Augmented language models combine reasoning and tool use to address traditional LM limits on interpretability, consistency, and scalability.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Baptiste Rozi\\`ere, Christoforos Nalmpantis, Edouard Grave, Gr\\'egoire Mialon, Jane Dwivedi-Yu, Maria Lomeli, Ram Pasunuru, Roberta Raileanu, Roberto Dess\\`i, Thomas Scialom, Timo Schick, Yann LeCun","submitted_at":"2023-02-15T18:25:52Z","abstract_excerpt":"This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially complex task into simpler subtasks while the latter consists in calling external modules such as a code interpreter. LMs can leverage these augmentations separately or in combination via heuristics, or learn to do so from demonstrations. While adhering to a standard missing tokens prediction objective, such augmented LMs can use various, possibly non-parametric external modules to expand their context processing ability, t"},"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":true},"canonical_record":{"source":{"id":"2302.07842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-15T18:25:52Z","cross_cats_sorted":[],"title_canon_sha256":"cda05848a173eb842936e17f8a3ffb57e152e0f4d55538958e1b940dcedd45b6","abstract_canon_sha256":"2c0ced008c791b37237a86536f48cbe83b6bb45320414d53d156edc1f4acbd70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.340488Z","signature_b64":"+CJv1S+ZiIS6d+Um7ukMtgaoQGYQe36O6yHDYbLn+HqGWyB38fbbK55sdBZOQTUrH71idD8uyjn6uXmKAps2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98013cf42297b3c158666e956be7ea74fcaeef5b6afb15b644c3746d5b2ae37","last_reissued_at":"2026-05-17T23:38:49.339970Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.339970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmented Language Models: a Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Augmented language models combine reasoning and tool use to address traditional LM limits on interpretability, consistency, and scalability.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asli Celikyilmaz, Baptiste Rozi\\`ere, Christoforos Nalmpantis, Edouard Grave, Gr\\'egoire Mialon, Jane Dwivedi-Yu, Maria Lomeli, Ram Pasunuru, Roberta Raileanu, Roberto Dess\\`i, Thomas Scialom, Timo Schick, Yann LeCun","submitted_at":"2023-02-15T18:25:52Z","abstract_excerpt":"This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially complex task into simpler subtasks while the latter consists in calling external modules such as a code interpreter. LMs can leverage these augmentations separately or in combination via heuristics, or learn to do so from demonstrations. While adhering to a standard missing tokens prediction objective, such augmented LMs can use various, possibly non-parametric external modules to expand their context processing ability, t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"this new research direction has the potential to address common limitations of traditional LMs such as interpretability, consistency, and scalability issues.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the reviewed augmentations with reasoning and tools will demonstrably improve interpretability, consistency, and scalability in practice, as implied by the synthesis of existing works.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Augmented language models combine reasoning and tool-calling abilities with standard language modeling to improve performance on complex tasks while retaining core capabilities.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Augmented language models combine reasoning and tool use to address traditional LM limits on interpretability, consistency, and scalability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"51627ebcc7a258dd0d199c6ed0bea05ab5cc8c3f033bbceb8922699df2a7bcaf"},"source":{"id":"2302.07842","kind":"arxiv","version":1},"verdict":{"id":"e74b1d60-cce0-496a-ac4e-4e6762a436e1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T02:35:15.768907Z","strongest_claim":"this new research direction has the potential to address common limitations of traditional LMs such as interpretability, consistency, and scalability issues.","one_line_summary":"Augmented language models combine reasoning and tool-calling abilities with standard language modeling to improve performance on complex tasks while retaining core capabilities.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the reviewed augmentations with reasoning and tools will demonstrably improve interpretability, consistency, and scalability in practice, as implied by the synthesis of existing works.","pith_extraction_headline":"Augmented language models combine reasoning and tool use to address traditional LM limits on interpretability, consistency, and scalability."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"3ca75d5136476388d0cc6c64103e060fe92a2e4f3fea41ecf8318ee7475f3683"},"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":"2302.07842","created_at":"2026-05-17T23:38:49.340051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.07842v1","created_at":"2026-05-17T23:38:49.340051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07842","created_at":"2026-05-17T23:38:49.340051+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GABHT2CFF5T","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GABHT2CFF5TYFMG","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GABHT2C","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":32,"sample":[{"citing_arxiv_id":"2409.00557","citing_title":"Learning to Ask: When LLM Agents Meet Unclear Instruction","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21937","citing_title":"MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16359","citing_title":"LLM4Log: A Systematic Review of Large Language Model-based Log Analysis","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14038","citing_title":"Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17625","citing_title":"Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20061","citing_title":"Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2403.17134","citing_title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17452","citing_title":"ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2404.08144","citing_title":"LLM Agents can Autonomously Exploit One-day Vulnerabilities","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2510.23853","citing_title":"Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2303.17491","citing_title":"Language Models can Solve Computer Tasks","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":121,"is_internal_anchor":true},{"citing_arxiv_id":"2309.02427","citing_title":"Cognitive Architectures for Language Agents","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2504.19793","citing_title":"Prompt Injection Attack to Tool Selection in LLM Agents","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2304.08244","citing_title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2306.06070","citing_title":"Mind2Web: Towards a Generalist Agent for the Web","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2305.18323","citing_title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16359","citing_title":"LLM4Log: A Systematic Review of Large Language Model-based Log Analysis","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14038","citing_title":"Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":179,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21937","citing_title":"MolClaw: An Autonomous Agent with Hierarchical Skills for Drug Molecule Evaluation, Screening, and Optimization","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2305.05176","citing_title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5","json":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5.json","graph_json":"https://pith.science/api/pith-number/3GABHT2CFF5TYFMGM3UVNPT6U5/graph.json","events_json":"https://pith.science/api/pith-number/3GABHT2CFF5TYFMGM3UVNPT6U5/events.json","paper":"https://pith.science/paper/3GABHT2C"},"agent_actions":{"view_html":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5","download_json":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5.json","view_paper":"https://pith.science/paper/3GABHT2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.07842&json=true","fetch_graph":"https://pith.science/api/pith-number/3GABHT2CFF5TYFMGM3UVNPT6U5/graph.json","fetch_events":"https://pith.science/api/pith-number/3GABHT2CFF5TYFMGM3UVNPT6U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5/action/storage_attestation","attest_author":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5/action/author_attestation","sign_citation":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5/action/citation_signature","submit_replication":"https://pith.science/pith/3GABHT2CFF5TYFMGM3UVNPT6U5/action/replication_record"}},"created_at":"2026-05-17T23:38:49.340051+00:00","updated_at":"2026-05-17T23:38:49.340051+00:00"}