{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AIAENHVDVOP3XAIACVKK4FJS4K","short_pith_number":"pith:AIAENHVD","schema_version":"1.0","canonical_sha256":"0200469ea3ab9fbb81001554ae1532e29ddc4f9242c712921ba03609556d0f72","source":{"kind":"arxiv","id":"2205.00445","version":1},"attestation_state":"computed","paper":{"title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MRKL systems combine large language models with external knowledge and discrete reasoning modules to address inherent LM limits.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amnon Shashua, Barak Lenz, Dor Muhlgay, Ehud Karpas, Erez Schwartz, Gal Shachaf, Hofit Bata, Kevin Leyton-Brown, Moshe Tenenholtz, Nir Ratner, Noam Rozen, Omri Abend, Opher Lieber, Shai Shalev-Shwartz, Yoav Levine, Yoav Shoham, Yonatan Belinkov","submitted_at":"2022-05-01T11:01:28Z","abstract_excerpt":"Huge language models (LMs) have ushered in a new era for AI, serving as a gateway to natural-language-based knowledge tasks. Although an essential element of modern AI, LMs are also inherently limited in a number of ways. We discuss these limitations and how they can be avoided by adopting a systems approach. Conceptualizing the challenge as one that involves knowledge and reasoning in addition to linguistic processing, we define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules. We describe this neuro-symbolic architecture, dubbed th"},"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":"2205.00445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-01T11:01:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"18c647d28ce5d0ac2f31250b5c40afffc6fe0a93dc0516aeebe66669afb6e5cd","abstract_canon_sha256":"1999b508cf59abc1f097ea9dba4c11f02cf4b973f0f34fda729975ac53eaaa33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.129636Z","signature_b64":"dxcqt8NOD5gk+q/853BYU2CG1wE5r3fxq4rQACNthkPzaxYSu3hKZ0pZ44Ls2wXl008sZ8cCeuRwdCJqV/WRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0200469ea3ab9fbb81001554ae1532e29ddc4f9242c712921ba03609556d0f72","last_reissued_at":"2026-05-17T23:38:53.129067Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.129067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MRKL systems combine large language models with external knowledge and discrete reasoning modules to address inherent LM limits.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amnon Shashua, Barak Lenz, Dor Muhlgay, Ehud Karpas, Erez Schwartz, Gal Shachaf, Hofit Bata, Kevin Leyton-Brown, Moshe Tenenholtz, Nir Ratner, Noam Rozen, Omri Abend, Opher Lieber, Shai Shalev-Shwartz, Yoav Levine, Yoav Shoham, Yonatan Belinkov","submitted_at":"2022-05-01T11:01:28Z","abstract_excerpt":"Huge language models (LMs) have ushered in a new era for AI, serving as a gateway to natural-language-based knowledge tasks. Although an essential element of modern AI, LMs are also inherently limited in a number of ways. We discuss these limitations and how they can be avoided by adopting a systems approach. Conceptualizing the challenge as one that involves knowledge and reasoning in addition to linguistic processing, we define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules. We describe this neuro-symbolic architecture, dubbed th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the interfaces between neural language components and discrete knowledge/reasoning modules can be made reliable enough to deliver net gains over monolithic LMs without introducing new failure modes at the boundaries.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MRKL systems combine large language models with external knowledge and discrete reasoning modules to address inherent LM limits.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4db53586f57fd1747b022651e035d8e599f1ce57e992e810daf8154e113c7055"},"source":{"id":"2205.00445","kind":"arxiv","version":1},"verdict":{"id":"b8533b3f-b13e-4a88-8077-f85ec93238a2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T07:27:22.153857Z","strongest_claim":"We define a flexible architecture with multiple neural models, complemented by discrete knowledge and reasoning modules.","one_line_summary":"MRKL is a modular neuro-symbolic architecture that integrates LLMs with external knowledge and discrete reasoning to overcome limitations of pure neural language models.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the interfaces between neural language components and discrete knowledge/reasoning modules can be made reliable enough to deliver net gains over monolithic LMs without introducing new failure modes at the boundaries.","pith_extraction_headline":"MRKL systems combine large language models with external knowledge and discrete reasoning modules to address inherent LM limits."},"references":{"count":23,"sample":[{"doi":"","year":2019,"title":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K.BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingin Proceedings of the 2019 Conference of the North American Chapter of ","work_id":"00b22d1f-29ac-44d3-bf74-53f063f7fcc9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","ref_index":2,"cited_arxiv_id":"2005.14165","is_internal_anchor":true},{"doi":"","year":2021,"title":"& Shoham, Y.Jurassic-1: Technical Details and Evaluation 2021","work_id":"070df3c5-50c5-4ecc-96da-8eda8669e750","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","ref_index":4,"cited_arxiv_id":"2204.02311","is_internal_anchor":true},{"doi":"","year":2020,"title":"et al.Exploring the Limits of Transfer Learning with a Unified Text- to-Text Transformer.Journal of Machine Learning Research21, 1–67","work_id":"d84daa05-7815-47fc-a7b2-07f57b7f5ccd","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"d55a7c18d81a4d8d0bb51283b730d8426d9af077ec367868f9b06cab7a260e63","internal_anchors":8},"formal_canon":{"evidence_count":3,"snapshot_sha256":"21da73a1f8baeafce09a0bfa9902f932c0ec68bce1e1bbd26a170692e6bed4e5"},"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":"2205.00445","created_at":"2026-05-17T23:38:53.129165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.00445v1","created_at":"2026-05-17T23:38:53.129165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00445","created_at":"2026-05-17T23:38:53.129165+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIAENHVDVOP3","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIAENHVDVOP3XAIA","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIAENHVD","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":27,"sample":[{"citing_arxiv_id":"2605.20190","citing_title":"Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24697","citing_title":"Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17487","citing_title":"Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18882","citing_title":"To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18133","citing_title":"An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19604","citing_title":"Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2304.05376","citing_title":"ChemCrow: Augmenting large-language models with chemistry tools","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2509.02544","citing_title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10834","citing_title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10555","citing_title":"Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25155","citing_title":"Rethinking Wireless Communications through Formal Mathematical AI Reasoning","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24594","citing_title":"Skill Retrieval Augmentation for Agentic AI","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2310.03714","citing_title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05287","citing_title":"Securing the Agent: Vendor-Neutral, Multitenant Enterprise Retrieval and Tool Use","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21304","citing_title":"PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13180","citing_title":"SciFi: A Safe, Lightweight, User-Friendly, and Fully Autonomous Agentic AI Workflow for Scientific Applications","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12513","citing_title":"Agentic Control in Variational Language Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":187,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10513","citing_title":"Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05547","citing_title":"COSMO-Agent: Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05278","citing_title":"Spec Kit Agents: Context-Grounded Agentic Workflows","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12717","citing_title":"Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16736","citing_title":"When Agents Go Quiet: Output Generation Capacity and Format-Cost Separation for LLM Document Synthesis","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K","json":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K.json","graph_json":"https://pith.science/api/pith-number/AIAENHVDVOP3XAIACVKK4FJS4K/graph.json","events_json":"https://pith.science/api/pith-number/AIAENHVDVOP3XAIACVKK4FJS4K/events.json","paper":"https://pith.science/paper/AIAENHVD"},"agent_actions":{"view_html":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K","download_json":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K.json","view_paper":"https://pith.science/paper/AIAENHVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.00445&json=true","fetch_graph":"https://pith.science/api/pith-number/AIAENHVDVOP3XAIACVKK4FJS4K/graph.json","fetch_events":"https://pith.science/api/pith-number/AIAENHVDVOP3XAIACVKK4FJS4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K/action/storage_attestation","attest_author":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K/action/author_attestation","sign_citation":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K/action/citation_signature","submit_replication":"https://pith.science/pith/AIAENHVDVOP3XAIACVKK4FJS4K/action/replication_record"}},"created_at":"2026-05-17T23:38:53.129165+00:00","updated_at":"2026-05-17T23:38:53.129165+00:00"}