ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents

• URL: http://arxiv.org/abs/2606.06284v1
• Date: Thu, 04 Jun 2026 15:24:10 GMT
• Title: ToolChoiceConfusion: Causal Minimal Tool Filtering for Reliable LLM Agents
• Abstract summary: We propose a training-free method that selects tools by causal sufficiency.<n>We compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations.<n>In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step. We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweight precondition-effect contracts to expose only the minimal next-step tool frontier needed to advance from the current state toward the user goal. Across multi-step tool-use tasks, we compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations, measuring task success, wrong-tool calls, premature actions, tool exposure, and token cost. In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success while reducing visible tools from 100 to one per step and reducing token usage by about 90% relative to all-tools exposure.

Related papers

• Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation [1.6774701449274187]
  Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond pretrained knowledge.<n>The Model Context Protocol (MCP) standardizes how such tools are surfaced, and a proxy MCP server aggregates many backend servers behind a single endpoint.<n>We present SCOUT, which reframes tool exposure as a context-selection problem, injecting only tools relevant to the current step.
  arXiv  Detail & Related papers  (2026-08-25T02:33:44Z)
• ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents [0.0]
  ToolFailBench is a diagnostic benchmark for measuring tool-use failures.<n>We label each trace with Tool-Skip, Result-Ignore, Output-Fabrication, and Unnecessary-Tool-Use.
  arXiv  Detail & Related papers  (2026-07-06T05:25:21Z)
• SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents [64.59100414726556]
  Large language model (LLM) agents increasingly rely on harnesses that manage context, tools, and multi-turn execution.<n>Retrieval-augmented tool selection offers a natural alternative, but existing one-shot retrieval methods fail to align isolated tool descriptions with the agent's true task intention.<n>We propose SING, an intention-aware active tool discovery framework that builds an intention-tool graph linking user intentions, tool capabilities, and tool collaboration patterns.
  arXiv  Detail & Related papers  (2026-06-15T11:37:37Z)
• Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection [1.2633421050364024]
  Large Language Models (LLMs) with tool-calling capabilities have demonstrated remarkable potential in executing complex tasks through external tool integration.<n>The Model Context Protocol (MCP) has emerged as a standardized framework for connecting LLMs to diverse toolsets, with individual MCP servers potentially exposing dozens to hundreds of tools.<n>We present a semantic tool discovery architecture that addresses these challenges through vector-based retrieval.
  arXiv  Detail & Related papers  (2026-03-19T18:10:35Z)
• Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs [78.58042751671393]
  Tool-DC is a Divide-and-Conquer framework for boosting tool-calling performance of Large Language Models.<n>Tool-DC involves two variants: 1) the training-free Tool-DC (TF), which is plug-and-play and flexible; 2) the training-based Tool-DC (TB), which is more inference-efficient.<n>Extensive experiments show that both Tool-DC methods outperform their counterparts by a clear margin.
  arXiv  Detail & Related papers  (2026-03-12T03:30:01Z)
• Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls [56.407063247662336]
  We introduce Gecko, a comprehensive environment that simulates tool responses using a combination of rules and LLMs.<n>GATS consistently improves the tool calling performance of various LLMs including GPT-4o, GPT-5, and Gemini-3.0-pro.
  arXiv  Detail & Related papers  (2026-02-22T15:02:00Z)
• 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)
• Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models [47.145844910856134]
  Tool learning aims to augment large language models with diverse tools, enabling them to act as agents for solving practical tasks.<n>Due to the limited context length of tool-using LLMs, adopting information retrieval (IR) models to select useful tools from large toolsets is a critical initial step.<n>Most tool-use benchmarks simplify this step by manually pre-annotating a small set of relevant tools for each task, which is far from the real-world scenarios.<n>We propose ToolRet, a heterogeneous tool retrieval benchmark comprising 7.6k diverse retrieval tasks, and a corpus of 43k tools, collected from
  arXiv  Detail & Related papers  (2025-03-03T17:37:16Z)
• PTR: Precision-Driven Tool Recommendation for Large Language Models [43.53494041932615]
  We propose a Precision-driven Tool Recommendation (PTR) approach for Large Language Models (LLMs) PTR captures an initial, concise set of tools by leveraging historical tool bundle usage and dynamically adjusts the tool set by performing tool matching. We present a new dataset, RecTools, and a metric, TRACC, designed to evaluate the effectiveness of tool recommendation for LLMs.
  arXiv  Detail & Related papers  (2024-11-14T17:33:36Z)
• Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents [56.822238860147024]
  Augmenting large language models with external tools has emerged as a promising approach to extend their utility.<n>Previous methods manually parse tool documentation and create in-context demonstrations, transforming tools into structured formats for LLMs to use in their step-by-step reasoning.<n>We propose AutoTools, a framework that enables LLMs to automate the tool-use workflow.
  arXiv  Detail & Related papers  (2024-05-26T11:40:58Z)
• Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding [11.51687663492722]
  Large language models (LLMs) excel at many tasks but often fail to use external tools due to complicated and unfamiliar syntax constraints. We propose TOOLDEC, a decoding algorithm using finite state machines to force LLMs to follow tool syntax. Experiments show that TOOLDEC eliminates all syntax errors, achieving significantly better performance on various base models and benchmarks.
  arXiv  Detail & Related papers  (2023-10-10T23:37:53Z)
• Large Language Models as Tool Makers [85.00361145117293]
  We introduce a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving. Our approach consists of two phases: 1) tool making: an LLM acts as the tool maker that crafts tools for a set of tasks. 2) tool using: another LLM acts as the tool user, which applies the tool built by the tool maker for problem-solving.
  arXiv  Detail & Related papers  (2023-05-26T17:50:11Z)
• ART: Automatic multi-step reasoning and tool-use for large language models [105.57550426609396]
  Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings. Each reasoning step can rely on external tools to support computation beyond the core LLM capabilities. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program.
  arXiv  Detail & Related papers  (2023-03-16T01:04:45Z)

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.