{"paper":{"title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A review organizes roughly 60 benchmarks for large language models and autonomous agents into one taxonomy covering reasoning, code, and real-world tasks.","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Merouane Debbah, Mohamed Amine Ferrag, Norbert Tihanyi","submitted_at":"2025-04-28T11:08:22Z","abstract_excerpt":"Large language models and autonomous AI agents have evolved rapidly, resulting in a diverse array of evaluation benchmarks, frameworks, and collaboration protocols. Driven by the growing need for standardized evaluation and integration, we systematically consolidate these fragmented efforts into a unified framework. However, the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey. Therefore, we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains. In addition, we propose a tax"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains... we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey, which the authors' proposed taxonomy of approximately 60 benchmarks is assumed to resolve without major omissions or selection bias in the covered works.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A review organizes roughly 60 benchmarks for large language models and autonomous agents into one taxonomy covering reasoning, code, and real-world tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"12155fb9a0f94458fa89bacc37f0cce8fac32ae1941962551607bff5de458453"},"source":{"id":"2504.19678","kind":"arxiv","version":2},"verdict":{"id":"e97de2dc-ed32-4712-8b7f-1ded3d7cb153","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:53:18.046467Z","strongest_claim":"we present a side-by-side comparison of benchmarks developed between 2019 and 2025 that evaluate these models and agents across multiple domains... we propose a taxonomy of approximately 60 benchmarks that cover general and academic knowledge reasoning, mathematical problem-solving, code generation and software engineering, factual grounding and retrieval, domain-specific evaluations, multimodal and embodied tasks, task orchestration, and interactive assessments.","one_line_summary":"A survey consolidating benchmarks, agent frameworks, real-world applications, and protocols for LLM-based autonomous agents into a proposed taxonomy with recommendations for future research.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"the landscape remains fragmented and lacks a unified taxonomy or comprehensive survey, which the authors' proposed taxonomy of approximately 60 benchmarks is assumed to resolve without major omissions or selection bias in the covered works.","pith_extraction_headline":"A review organizes roughly 60 benchmarks for large language models and autonomous agents into one taxonomy covering reasoning, code, and real-world tasks."},"references":{"count":236,"sample":[{"doi":"","year":2024,"title":"OpenAI o1 System Card","work_id":"68d3c334-0fc9-49e3-b7b0-a69afae933e2","ref_index":1,"cited_arxiv_id":"2412.16720","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen2.5-Omni Technical Report","work_id":"438f105c-fa9b-44aa-ad52-43acb8045cda","ref_index":2,"cited_arxiv_id":"2503.20215","is_internal_anchor":true},{"doi":"","year":2025,"title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","work_id":"e6b75ad5-2877-4168-97c8-710407094d20","ref_index":3,"cited_arxiv_id":"2501.12948","is_internal_anchor":true},{"doi":"","year":2024,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","ref_index":4,"cited_arxiv_id":"2407.21783","is_internal_anchor":true},{"doi":"","year":2024,"title":"Understanding the planning of LLM agents: A survey","work_id":"6daa5311-7f56-401d-94db-17be43e95cbc","ref_index":5,"cited_arxiv_id":"2402.02716","is_internal_anchor":true}],"resolved_work":236,"snapshot_sha256":"d9a8e56106c8959ad2eeb33339464e4cc83c02bd5819d7e3eb8b20a0074ce7b8","internal_anchors":43},"formal_canon":{"evidence_count":1,"snapshot_sha256":"df92f97a9cc1f0285d2d10bcc1fb6d1a80591f55a84b879debac6c25f0c3f401"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}