# General LLM agent frameworks and benchmarks Area: [LLM agents and tool use](https://mlsanity.com/agents/index.md). HTML: https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/ ## Key facts - General LLM agent frameworks and benchmarks: 2,917 papers on arXiv since 2022 (data through 14 Oct 2026). - 520 of its 2,917 mapped papers (18%) cite “MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework” (2023, arXiv 2308.00352). - 370 of its 2,917 mapped papers (13%) cite “A Survey on Large Language Model based Autonomous Agents” (2023, arXiv 2308.11432). - 175 new papers 17 Sep–14 Oct. ## Most cited here - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023), cited by 520 papers here - [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023), cited by 370 papers here - [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023), cited by 365 papers here - [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024), cited by 264 papers here - [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023), cited by 245 papers here - [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023), cited by 243 papers here - [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023), cited by 206 papers here - [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024), cited by 190 papers here - [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023), cited by 162 papers here - [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023), cited by 130 papers here ## New (17 Sep–14 Oct) - [The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock](https://mlsanity.com/paper/2610.20665/) (2026-10-14) - [The Wealth of Agents: Scaling Agentic AI Across Developers](https://mlsanity.com/paper/2610.20518/) (2026-10-14) - [Towards Agentic Robots: Model, Data, Environment, and Harness](https://mlsanity.com/paper/2610.20442/) (2026-10-14) - [RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios](https://mlsanity.com/paper/2610.19698/) (2026-10-14) - [Interlock: From Local Correctness to Task Completion in Long-Horizon Agents](https://mlsanity.com/paper/2610.19686/) (2026-10-14) - [L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving Agents](https://mlsanity.com/paper/2610.19591/) (2026-10-14) - [XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents](https://mlsanity.com/paper/2610.19581/) (2026-10-14) - [τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions](https://mlsanity.com/paper/2610.19560/) (2026-10-14) - [Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents](https://mlsanity.com/paper/2610.19439/) (2026-10-14) - [EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents](https://mlsanity.com/paper/2610.19433/) (2026-10-14) - [DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents](https://mlsanity.com/paper/2610.19376/) (2026-10-14) - [Beyond Corrected Actions: Training LLM Agents on Textual Critiques](https://mlsanity.com/paper/2610.19367/) (2026-10-14) - [When Is Smaller Greener? Right-Sizing Language Models for Agentic AI](https://mlsanity.com/paper/2610.19345/) (2026-10-14) - [Agentic Self-Awareness: Aligning Knowing, Acting, and Holding](https://mlsanity.com/paper/2610.19226/) (2026-10-13) - [Hybrid Reasoning Agents](https://mlsanity.com/paper/2610.18861/) (2026-10-13) - [LLM Agents for Automated Post-Training via Structured Recipe Optimization](https://mlsanity.com/paper/2610.18572/) (2026-10-13) - [AM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses](https://mlsanity.com/paper/2610.18090/) (2026-10-13) - [From Agents to Edges: Paired Optimization for Multi-Agent Collaboration](https://mlsanity.com/paper/2610.18069/) (2026-10-13) - [ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning](https://mlsanity.com/paper/2610.17869/) (2026-10-13) - [Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models](https://mlsanity.com/paper/2610.17840/) (2026-10-13) - [Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes](https://mlsanity.com/paper/2610.17751/) (2026-10-13) - [MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification](https://mlsanity.com/paper/2610.17613/) (2026-10-13) - [EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation](https://mlsanity.com/paper/2610.17560/) (2026-10-13) - [Scaling Inference-Time Compute with Teams of Coding Agents](https://mlsanity.com/paper/2610.17471/) (2026-10-12) - [Agency as a New Organizing Abstraction for Computer Science](https://mlsanity.com/paper/2610.17410/) (2026-10-12) - [OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains](https://mlsanity.com/paper/2610.17143/) (2026-10-12) - [Scaling Multi-Agent Intelligence with Substrate-Centric Coordination](https://mlsanity.com/paper/2610.16120/) (2026-10-12) - [Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues](https://mlsanity.com/paper/2610.16117/) (2026-10-12) - [When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2610.15459/) (2026-10-11) - [Persistent LLM Orchestration of Heterogeneous Robot Teams via Partial Delegation to Multi-Agent Protocols](https://mlsanity.com/paper/2610.15224/) (2026-10-10)