Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents

• URL: http://arxiv.org/abs/2605.26691v1
• Date: Tue, 26 May 2026 08:29:38 GMT
• Title: Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents
• Abstract summary: We study medical tool use under imperfect-tool settings to correct failure instances missed by individual tools.<n>We propose a GRPO-based reinforcement learning framework with rewards for probabilistic risk minimization and disagreement-aware synergy learning.<n>Our method consistently achieves robust and stable improvements over a broad range of baselines.
• Score: 17.585879443335788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Medical AI agents increasingly use external tools for diagnosis, treatment recommendation, and evidence retrieval, yet most existing approaches assume that task-appropriate tools are reliable within their intended scope. This assumption is fragile in real clinical settings, where even relevant tools may fail on challenging instances and lead to unsafe downstream decisions. To address this issue, we study medical tool use under imperfect-tool settings to correct failure instances missed by individual tools. Instance-dependent failure patterns create a gap between the best fixed single tool and an ideal instance-wise selector, which we refer to as the Single-Oracle risk gap. The core challenge is that conventional task-level tool selection cannot realize this gap, as it is inherently bounded by the performance of the best single tool. Motivated by this observation, we therefore account for instance-level heterogeneity and formulate tool use as an instance-level selection problem. Particularly, we propose a GRPO-based reinforcement learning framework with rewards for probabilistic risk minimization and disagreement-aware synergy learning, which promotes instance-level correction of erroneous tool consensus. Furthermore, an entropy-guided sampling strategy is adopted to upweight high-disagreement instances, which provide stronger signals for learning instance-specific tool synergy. These two components complement each other in mitigating instance-level heterogeneity and improving tool synergy. Experiments on two tasks and seven medical benchmarks show that our method consistently achieves robust and stable improvements over a broad range of baselines, highlighting the importance of synergy-aware tool use for reliable medical agentic systems.

Related papers

• Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents [54.050506620820784]
  Agentic Tool Unlearning (ATU) aims to reduce both parametric recall and tool-mediated recovery while preserving normal tool use for retained knowledge.<n>ATU achieves a better balance between target forgetting and retained utility, making unlearning more robust under tool-augmented agent deployment.
  arXiv  Detail & Related papers  (2026-08-21T18:34:48Z)
• ARMOR: An Agentic Framework for Reaction Feasibility Prediction via Adaptive Utility-aware Multi-tool Reasoning [11.65859277511507]
  ARMOR is an agentic framework that explicitly models tool-specific utilities, adaptively prioritizes tools, and resolves potential tool conflicts.<n>Experiments on a public dataset demonstrate that ARMOR consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-05-08T01:30:20Z)
• Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery [26.23353599153354]
  MACRO is a self-evolving, experience-augmented medical agent that shifts from static tool composition to experience-driven tool discovery.<n>A lightweight image-feature memory grounds tool selection in a visual-clinical context, while a GRPO-like training loop reinforces reliable invocation of discovered composites.
  arXiv  Detail & Related papers  (2026-03-06T03:34:47Z)
• ToolMATH: A Math Tool Benchmark for Realistic Long-Horizon Multi-Tool Reasoning [11.99927786717109]
  ToolMATH turns math problems into a controlled, correctness-checkable benchmark with tool sets.<n>ToolMATH provides actionable diagnostic evidence of failure modes in tool-augmented agents.
  arXiv  Detail & Related papers  (2026-02-24T09:23:12Z)
• AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning [66.24374176797075]
  We introduce textbfAdaReasoner, a family of multimodal models that learn tool use as a general reasoning skill rather than as tool-specific or explicitly supervised behavior.<n>AdaReasoner is enabled by (i) a scalable data curation pipeline exposing models to long-horizon, multi-step tool interactions; (ii) Tool-GRPO, a reinforcement learning algorithm that prioritizes tool selection and sequencing based on end-task success; and (iii) an adaptive learning mechanism that dynamically regulates tool usage.
  arXiv  Detail & Related papers  (2026-01-26T16:04:43Z)
• Quantifying Distributional Robustness of Agentic Tool-Selection [8.457056023589951]
  We introduce ToolCert, the first statistical framework that formally certifies tool selection robustness.<n>We show that ToolCert produces a high-confidence lower bound on accuracy, formally quantifying the agent's worst-case performance.<n>Our evaluation with ToolCert uncovers the severe fragility: under attacks injecting deceptive tools or saturating retrieval, the certified accuracy bound drops near zero.
  arXiv  Detail & Related papers  (2025-10-05T01:50:34Z)
• BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models [55.119657444627855]
  Large language models (LLMs) often rely on external tools drawn from marketplaces where multiple providers offer functionally equivalent options.<n>This raises a critical point concerning fairness: if selection is systematically biased, it can degrade user experience and distort competition.<n>We introduce a benchmark of diverse tool categories, each containing multiple functionally equivalent tools, to evaluate tool-selection bias.
  arXiv  Detail & Related papers  (2025-09-30T22:02:13Z)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space.<n>MeCo is fine-tuning-free and incurs minimal cost.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)
• SMART: Self-Aware Agent for Tool Overuse Mitigation [58.748554080273585]
  Current Large Language Model (LLM) agents demonstrate strong reasoning and tool use capabilities, but often lack self-awareness.<n>This imbalance leads to Tool Overuse, where models unnecessarily rely on external tools for tasks with parametric knowledge.<n>We introduce SMART (Strategic Model-Aware Reasoning with Tools), a paradigm that enhances an agent's self-awareness to optimize task handling and reduce tool overuse.
  arXiv  Detail & Related papers  (2025-02-17T04:50:37Z)
• Reducing Tool Hallucination via Reliability Alignment [31.761771794788462]
  Large Language Models (LLMs) have expanded their capabilities beyond language generation to interact with external tools, enabling automation and real-world applications.<n>Tool hallucinations, where models either select inappropriate tools or misuse them, pose significant challenges, leading to erroneous task execution, increased computational costs, and reduced system reliability.<n>We introduce RelyToolBench, which integrates specialized test cases and novel metrics to assess hallucination-aware task success and efficiency.<n>Finally, we propose Relign, a reliability alignment framework that expands the tool-use action space to include indecisive actions, allowing LLMs to defer tool use, seek clarification, or adjust tool selection
  arXiv  Detail & Related papers  (2024-12-05T13:10:54Z)
• Learning to Use Tools via Cooperative and Interactive Agents [58.77710337157665]
  Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. We propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. Our experiments on three datasets show that the LLMs, when equipped with ConAgents, outperform baselines with substantial improvement.
  arXiv  Detail & Related papers  (2024-03-05T15:08:16Z)

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.