Looped Language Models Improve Compositional Tool Calling

• URL: http://arxiv.org/abs/2608.18171v1
• Date: Mon, 17 Aug 2026 18:17:54 GMT
• Title: Looped Language Models Improve Compositional Tool Calling
• Abstract summary: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored.<n>We study this question in compositional tool-calling settings, where models must coordinate multiple API calls, maintain intermediate state, and preserve dependencies across tool interactions.<n>Our results suggest that looped language models are a promising architecture for agentic systems that require reliable planning, coordination, and execution of compositional tool use.
• Score: 16.36140240070991
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Looped language models have shown promising results on reasoning benchmarks, yet their potential for agentic tool use remains largely unexplored. We study this question in compositional tool-calling settings, where models must coordinate multiple API calls, maintain intermediate state, and preserve dependencies across tool interactions. We evaluate native and retrofitted looped language models on API-Bank, BFCL, and NESTful, comparing looped and non-looped models trained under matched supervised fine-tuning recipes and varying recurrent depth at inference time. In controlled experiments, recurrent computation generally benefits compositional and dependency-aware tool use, while providing smaller and more model-dependent gains on isolated API invocation. Accuracy on multi-step tool use generally increases with recurrent depth; adaptive inference, however, achieves a more favorable compute-performance trade-off by allocating additional computation only when needed. Our results suggest that looped language models are a promising architecture for agentic systems that require reliable planning, coordination, and execution of compositional tool use workflows.

Related papers

• Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning [10.650418762477475]
  Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world.<n>For autoregressive models, tool use naturally fits the generation process: the model emits a tool call, waits for the result, and then continues generating.<n>It can force tool decisions before the model's reasoning has stabilized, delay useful observations until a discrete call finishes, and introduce redundant refinement and tool execution.<n>We introduce Continuous Interaction Diffusion (CID), a diffusion-runtime architecture that integrates model interaction into denoising.
  arXiv  Detail & Related papers  (2026-08-11T03:35:59Z)
• PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language [21.03524402280427]
  We introduce PEARL, a system for interactive optimization modeling.<n>PEARL learns when to test partial models, how to revise from solver diagnostics, and when to stop.<n>It operates in a multi-turn tool-integrated setting where intermediate execution results, feasibility signals, and solution checks are used to improve both formulations and solver code before finalization.
  arXiv  Detail & Related papers  (2026-05-14T06:47:20Z)
• UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents [22.52508596251479]
  We present UniToolCall, a unified framework for tool learning that standardizes the entire pipeline from construction and dataset generation to evaluation.<n>We convert 7 public benchmarks into a unified Query-Action--Observation-Answer (QAOA) representation with fine-grained evaluation at the function-call, turn, and conversation levels.<n>Under the Anchoror-heavy Hybrid-20 setting, achieves 93.0% single-turn Strict Precision, outperforming commercial models including GPT, Gemini, and Claude.
  arXiv  Detail & Related papers  (2026-04-13T14:43:47Z)
• In-Context Reinforcement Learning for Tool Use in Large Language Models [68.66653829365187]
  Large language models (LLMs) exhibit strong reasoning abilities, but their performance on complex tasks is often constrained by their internal knowledge.<n>We propose In-Context Reinforcement Learning (ICRL), an RL-only framework that eliminates the need for supervised fine-tuning.<n>ICRL achieves state-of-the-art performance, demonstrating its effectiveness as a scalable, data-efficient alternative to traditional SFT-based pipelines.
  arXiv  Detail & Related papers  (2026-03-09T08:06:18Z)
• 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)
• 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)
• Acting Less is Reasoning More! Teaching Model to Act Efficiently [87.28134636548705]
  Tool-integrated reasoning augments large language models with the ability to invoke external tools to solve tasks.<n>Current approaches typically optimize only for final correctness without considering the efficiency or necessity of external tool use.<n>We propose a framework that encourages models to produce accurate answers with minimal tool calls.<n>Our approach reduces tool calls by up to 68.3% and improves tool productivity by up to 215.4%, while maintaining comparable answer accuracy.
  arXiv  Detail & Related papers  (2025-04-21T05:40:05Z)
• ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning [84.69651852838794]
  Tool learning allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks.<n>We propose ToolACE-R, a novel framework that includes both model-aware iterative training and adaptive refinement for tool learning.<n>We conduct extensive experiments across several benchmark datasets, showing that ToolACE-R achieves competitive performance compared to advanced API-based models.
  arXiv  Detail & Related papers  (2025-04-02T06:38:56Z)
• 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)
• FREYR: A Framework for Recognizing and Executing Your Requests [2.4797200957733576]
  This paper introduces FREYR, a streamlined framework that modularizes the tool usage process into separate steps.<n>We show that FREYR achieves superior performance compared to conventional tool usage methods.<n>We evaluate FREYR on a set of real-world test cases specific for video game design and compare it against traditional tool usage as provided by the Ollama API.
  arXiv  Detail & Related papers  (2025-01-21T11:08:18Z)

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.