From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use

• URL: http://arxiv.org/abs/2608.24368v2
• Date: Thu, 27 Aug 2026 08:07:54 GMT
• Title: From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use
• Abstract summary: We introduce OODA-Tool, a typed closed-loop policy designed to mitigate state-action competition.<n>OODA-Tool routes each decision through controller-checked intermediate states, ensuring the final output remains grounded in the current task state.<n>We evaluate OODA-Tool against direct function-calling and ReAct policies using Qwen3 models ranging from 0.6B to 14B across multi-turn, multi-tool, and incomplete-information settings.
• Score: 12.466318496864742
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable multi-turn tool use requires an agent to preserve an evolving task state and ensure that each action remains consistent with it. However, direct function-calling and ReAct-style policies learn state tracking and action generation within the same autoregressive trajectory. This coupling creates state-action competition: the pressure to produce the next call can overwrite or ignore information accumulated earlier in the interaction. Inspired by Boyd's Observe-Orient-Decide-Act cycle, we introduce OODA-Tool, a typed closed-loop policy designed to mitigate this competition by separating state preservation from action realization. Rather than generating an action directly from the interaction history, OODA-Tool routes each decision through controller-checked intermediate states, ensuring that the final output remains grounded in the current task state. Specifically, Observe reconstructs the task state, Orient determines whether execution is warranted, Decide forms an admissible action structure, and Act realizes the external output. We evaluate OODA-Tool against direct function-calling and ReAct policies using Qwen3 models ranging from 0.6B to 14B across multi-turn, multi-tool, and incomplete-information settings. OODA-Tool consistently improves task success across model sizes, with larger gains on smaller models and on tasks whose actions depend strongly on information accumulated across turns and prior tool results. Controlled variants, stage-level ablations, and transfer evaluations further demonstrate the robustness of these improvements.

Related papers

• S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement? [66.17176838165994]
  Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience.<n>It remains unclear whether an agent can actively test its behavior, judge the resulting experience, and use that experience to improve future decisions.<n>We introduce textbfStextsuperscript3Gym, an interactive benchmark for evaluating LLM self-improvement.
  arXiv  Detail & Related papers  (2026-08-31T17:05:41Z)
• IAPO: Influence-Aware Policy Optimization for Credit Assignment in Multi-Turn Service Agents [10.577620258047665]
  Large Language Model (LLM) agents increasingly solve long-horizon tasks through multi-turn interactions with users and external tools.<n>This work advances the understanding of credit assignment in multi-turn user interactions and provides a principled approach to training service agents from sparse outcome feedback.
  arXiv  Detail & Related papers  (2026-08-25T14:14:36Z)
• Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents [4.138547191663224]
  We propose Intent-Driven Situation States (IDSS), a training-free framework that maintains an explicit situation state alongside the dialogue.<n>IDSS parses tool returns into provenance-aware entities and attributes, tracks user intents, required variables, constraints, and execution status, and propagates new facts to task constraints to update action executability.
  arXiv  Detail & Related papers  (2026-08-16T14:14:07Z)
• AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies [4.786936073180585]
  Action-chunking visuomotor policies learn from demonstrations and improve temporal consistency.<n>We present AutoIntervene, an online framework that selectively transfers control between an action-chunking policy and an operator during deployment.
  arXiv  Detail & Related papers  (2026-08-07T10:14:29Z)
• Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback [38.251599309409]
  We study a different failure mode, cognitive poisoning, in which a malicious tool behaves plausibly during exploration.<n>We present VISTA-Guard, a backbone-agnostic framework for final-action risk scoring.
  arXiv  Detail & Related papers  (2026-05-17T13:51:34Z)
• ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents [59.626170560327274]
  We present textbfClawForge, a generator-backed benchmark framework for executable command-line categories under state conflict.<n>We instantiate this framework as the ClawForge-Bench (17 scenarios, 6 ability categories)
  arXiv  Detail & Related papers  (2026-05-13T21:34:08Z)
• OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents [74.20327254615854]
  Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks.<n>Existing inference-time adaptation methods for LLM agents mainly rely on prompting or retrieval.<n>We propose OLIVIA, an inference-time action adaptation framework for ReAct-style agents.
  arXiv  Detail & Related papers  (2026-05-11T19:28:20Z)
• See, Plan, Rewind: Progress-Aware Vision-Language-Action Models for Robust Robotic Manipulation [59.07792608884117]
  We introduce See, Plan, Rewind (SPR), a progress-aware vision-language-action framework.<n>SPR operates through a continuous core cycle, Seeing the current state and upcoming milestone, Planning a trajectory towards the next 2D waypoint, and Rewinding to a recoverable state upon failure.<n>SPR achieves state-of-the-art robustness with the smallest performance drop, surpassing OpenVLA-OFT and UniVLA.
  arXiv  Detail & Related papers  (2026-03-10T07:22:51Z)
• SIT-Graph: State Integrated Tool Graph for Multi-Turn Agents [35.85800795225018]
  State Integrated Tool Graph (SIT-Graph) is inspired by human decision-making that integrates episodic and procedural memory.<n>At inference time, SIT-Graph enables a human-like balance between episodic recall and procedural execution.<n> Experiments across multiple stateful multi-turn tool-use benchmarks show that SIT-Graph consistently outperforms strong memory- and graph-based baselines.
  arXiv  Detail & Related papers  (2025-12-08T08:27:24Z)
• DeepAgent: A General Reasoning Agent with Scalable Toolsets [111.6384541877723]
  DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution.<n>To address the challenges of long-horizon interactions, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories.<n>We develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens.
  arXiv  Detail & Related papers  (2025-10-24T16:24:01Z)
• How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench [58.114899897566964]
  In a multi-turn conversational environment, large language models (LLMs) often struggle with consistent reasoning and adherence to domain-specific policies.<n>We propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules.<n>IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1%, 12.7%, and 19.1%, respectively.
  arXiv  Detail & Related papers  (2025-08-28T15:57:33Z)
• You Only Look at Screens: Multimodal Chain-of-Action Agents [37.118034745972956]
  Auto-GUI is a multimodal solution that directly interacts with the interface. We propose a chain-of-action technique to help the agent decide what action to execute. We evaluate our approach on a new device-control benchmark AITW with 30$K$ unique instructions.
  arXiv  Detail & Related papers  (2023-09-20T16:12:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.