OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning

arXiv:2502.11271v2 Announce Type: replace-cross Abstract: Solving complex reasoning tasks may involve visual understanding, domain knowledge retrieval, numerical calculation, and multi-step reasoning. Existing methods augment large language models (LLMs) with external tools but are restricted to specialized domains, limited tool types, or require additional training data. In this paper, we introduce OctoTools, a training-free, user-friendly, and easily extensible multi-agent framework designed to tackle complex reasoning across diverse domains. OctoTools introduces standardized tool cards to encapsulate tool functionality, a planner for both high-level and low-level planning, and an executor to carry out tool usage. We validate OctoTools' generality across 16 diverse tasks (including MathVista, MMLU-Pro, MedQA, and GAIA-Text), achieving substantial average accuracy gains of 9.3% over GPT-4o. Furthermore, OctoTools also outperforms AutoGen, GPT-Functions, and LangChain by up to 10.6% when given the same set of tools. Through comprehensive analysi, ablations, and robustness tests with compact backbones and noisy tool environments, OctoTools demonstrates advantages in task planning, effective tool usage, and multi-step problem solving. Code, demos, and visualization are publicly available at https://octotools.github.io/.

Related

• Structure-Grounded Knowledge Retrieval via Code Dependencies for Multi-Step Data Reasoning
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
• Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning
• Reasoning Graphs: Deterministic Agent Accuracy through Evidence-Centric Chain-of-Thought Feedback
• Memp: Exploring Agent Procedural Memory

Source: arXiv cs.CL | 2026-04-15