# Tools as Continuous Flow for Evolving Agentic Reasoning

arXiv: https://arxiv.org/abs/2605.07339 · HTML: https://mlsanity.com/paper/2605.07339/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 26 of 26)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [AgentSquare: Automatic LLM Agent Search in Modular Design Space](https://mlsanity.com/paper/2410.06153/) (2024)
- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning](https://mlsanity.com/paper/2406.05804/) (2024)
- [In-the-Flow Agentic System Optimization for Effective Planning and Tool Use](https://mlsanity.com/paper/2510.05592/) (2025)
- [LLM With Tools: A Survey](https://mlsanity.com/paper/2409.18807/) (2024)
- [OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows](https://mlsanity.com/paper/2508.09124/) (2025)
- [AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2507.21836/) (2025)
- [SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?](https://mlsanity.com/paper/2603.00718/) (2026)
- [Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning](https://mlsanity.com/paper/2511.14460/) (2025)
- [Agents of Change: Self-Evolving LLM Agents for Strategic Planning](https://mlsanity.com/paper/2506.04651/) (2025)
- [FlowAgent: Achieving Compliance and Flexibility for Workflow Agents](https://mlsanity.com/paper/2502.14345/) (2025)
- [Coarse-to-Fine Grounded Memory for LLM Agent Planning](https://mlsanity.com/paper/2508.15305/) (2025)
- [Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution](https://mlsanity.com/paper/2504.16563/) (2025)
- [Self-Organizing Agent Network for LLM-based Workflow Automation](https://mlsanity.com/paper/2508.13732/) (2025)
- [Agent-S: LLM Agentic workflow to automate Standard Operating Procedures](https://mlsanity.com/paper/2503.15520/) (2025)
- [Scaling Graph Chain-of-Thought Reasoning: A Multi-Agent Framework with Efficient LLM Serving](https://mlsanity.com/paper/2511.01633/) (2025)
- [Routine: A Structural Planning Framework for LLM Agent System in Enterprise](https://mlsanity.com/paper/2507.14447/) (2025)
- [CATCH: A Novel Data Synthesis Framework for High Therapy Fidelity and Memory-Driven Planning Chain of Thought in AI Counseling](https://mlsanity.com/paper/2509.25733/) (2025)
- [Chain-of-thought obfuscation learned from output supervision can generalise to unseen tasks](https://mlsanity.com/paper/2601.23086/) (2026)
- [ML-Tool-Bench: Tool-Augmented Planning for ML Tasks](https://mlsanity.com/paper/2512.00672/) (2025)
- [Fine-Tuning and Prompt Engineering of LLMs, for the Creation of Multi-Agent AI for Addressing Sustainable Protein Production Challenges](https://mlsanity.com/paper/2506.20598/) (2025)
- [CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving](https://mlsanity.com/paper/2603.15771/) (2026)

## Built on by (most cited first, 2 of 2)

- [Dual-Frontier: When Can an Agent Trust Its World Model?](https://mlsanity.com/paper/2609.26293/) (2026)
- [DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning](https://mlsanity.com/paper/2610.16822/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a step-wise paradigm that lacks a global perspective, which causes error accumulation over long horizons and restricts generalization to unseen tools. To overcome these limitations, we propose Tools as Continuous Flow for Evolving Agentic Reasoning (FlowAgent), which reconceptualizes tool chaining as continuous trajectory generation within a semantic space. To systematically evaluate this paradigm, we introduce the first plan-level closed-loop benchmark dedicated to plan-level agentic reasoning in dynamic real-world environments. Specifically, the proposed FlowAgent leverages conditional flow matching to generate continuous latent trajectories, providing a global planning perspective to ensure coherent and robust tool execution. Theoretically, we establish formal bounds on utility convergence and prove that our continuous formulation fundamentally guarantees robust generalization and error attenuation. Empirical evaluations show that FlowAgent achieves superior robustness and adaptability in long-horizon reasoning tasks.