IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents

• URL: http://arxiv.org/abs/2606.11652v1
• Date: Wed, 10 Jun 2026 04:30:37 GMT
• Title: IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal Agents
• Abstract summary: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in small language models (SLM)<n>We propose IAPO, an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher.<n>Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.
• Score: 12.019312046941396
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper investigates reinforcement learning (RL) methods for improving tool-calling capabilities in multimodal small language model (SLM) agents. While existing works have explored various reward designs to improve agentic tool-calling ability, these approaches face inherent limitations for SLM training, especially under multimodal scenarios. First, many existing methods evaluate tool use correctness through exact matching against certain ground-truth or predefined formats. However, this assumption is often unsuitable for multimodal tasks, where multiple tool use paths may be valid and annotated tool trajectories are typically unavailable. Second, such sparse and brittle binary rewards provide little guidance on how to improve the underlying decision process, making them particularly difficult for multimodal SLM to learn from. To address these issues, we propose Input Attribution-Aware Policy Optimization (IAPO), an RL algorithm for improving tool use in multimodal SLM by aligning the model's attribution across input components with that of a stronger teacher. Experiments on Qwen2.5-VL-3B show that the proposed method improves visual question answering accuracy by an average of 3% across six test sets compared with existing visual tool use work, by helping the model attend to the most relevant input evidence.

Related papers

• PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Models [9.904299892454594]
  PORTS is a novel odds ratio preference optimization method for training retrievers aimed at tool selection.<n>Our approach fine-tunes a retriever to find helpful tools by optimizing the correlation between the selection probabilities and the downstream performances.<n>With low computational demands, our alignment process facilitates generalization to new queries and tools.
  arXiv  Detail & Related papers  (2026-07-03T18:47:06Z)
• RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models [57.15854852525046]
  We introduce RaTA-Tool, a novel framework for open-world multimodal tool selection.<n>Our approach enables an MLLM to convert a multimodal query into a structured task description and subsequently retrieve the most appropriate tool.<n>To further improve alignment between task descriptions and tool selection, we incorporate a preference-based optimization stage.
  arXiv  Detail & Related papers  (2026-04-16T12:47:09Z)
• 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)
• PORTool: Tool-Use LLM Training with Rewarded Tree [11.154654446183455]
  We propose a reinforcement learning (RL) method that encourages a tool-use LLM to explore various trajectories yielding the correct answer.<n>A shared step across different trajectories receives the same reward, while different steps under the same fork receive different rewards.<n>Experiments utilize 17 tools to address user queries, covering both time-sensitive and time-invariant topics.
  arXiv  Detail & Related papers  (2025-10-29T23:28:53Z)
• Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
  Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
  arXiv  Detail & Related papers  (2025-10-06T10:44:04Z)
• Step-wise Policy for Rare-tool Knowledge (SPaRK): Offline RL that Drives Diverse Tool Use in LLMs [0.0]
  Step-wise Policy for Rare-tool Knowledge (SPaRK) teaches large language models to explore diverse tool usage patterns.<n>We introduce a dual-objective reward system that simultaneously optimize for answer quality and tool diversity.
  arXiv  Detail & Related papers  (2025-07-15T14:44:29Z)
• Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning [68.00304954972232]
  Multimodal agents, which integrate a controller e.g., a vision language model, with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks.<n>Existing approaches for training these agents depend on extensive human-annotated task-answer pairs and tool trajectories.<n>We propose an iterative tool usage exploration method for multimodal agents without any pre-collected data, namely SPORT.<n>SPORT has four iterative components: task synthesis, step sampling, step verification, and preference tuning.
  arXiv  Detail & Related papers  (2025-04-30T12:01:27Z)
• ToolRL: Reward is All Tool Learning Needs [54.16305891389931]
  Large Language Models (LLMs) often undergo supervised fine-tuning (SFT) to acquire tool use capabilities.<n>Recent advancements in reinforcement learning (RL) have demonstrated promising reasoning and generalization abilities.<n>We present the first comprehensive study on reward design for tool selection and application tasks within the RL paradigm.
  arXiv  Detail & Related papers  (2025-04-16T21:45:32Z)
• TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use [72.32614703504122]
  Large language models (LLMs) achieve remarkable advancements by leveraging tools to interact with environments.<n>Standard supervised fine-tuning approach, which relies on large-scale datasets, often overlooks task-specific characteristics in tool use.<n>We propose TL-Training, a task-feature-based framework that mitigates the effects of suboptimal training data.
  arXiv  Detail & Related papers  (2024-12-20T02:21:36Z)

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.