# RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent

arXiv: https://arxiv.org/abs/2609.30717 · HTML: https://mlsanity.com/paper/2609.30717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 21 of 21)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach](https://mlsanity.com/paper/2305.07001/) (2023)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (2025)
- [ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario](https://mlsanity.com/paper/2501.10132/) (2025)
- [Let Me Do It For You: Towards LLM Empowered Recommendation via Tool Learning](https://mlsanity.com/paper/2405.15114/) (2024)
- [ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use](https://mlsanity.com/paper/2501.02506/) (2025)
- [MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models](https://mlsanity.com/paper/2505.16700/) (2025)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents](https://mlsanity.com/paper/2506.07672/) (2025)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [iAgent: LLM Agent as a Shield between User and Recommender Systems](https://mlsanity.com/paper/2502.14662/) (2025)
- [Fairly Adaptive Negative Sampling for Recommendations](https://mlsanity.com/paper/2302.08266/) (2023)
- [A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms](https://mlsanity.com/paper/2504.16420/) (2025)
- [Benchmarking LLM Tool-Use in the Wild](https://mlsanity.com/paper/2604.06185/) (2026)
- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [Interactive Recommendation Agent with Active User Commands](https://mlsanity.com/paper/2509.21317/) (2025)
- [RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation](https://mlsanity.com/paper/2603.09843/) (2026)

## Abstract (arXiv)

Recent advances in agentic recommender systems are shifting recommender systems from passive filtering engines to instruction-following agents that use external tools to resolve user intent. However, existing benchmarks often assume explicit user intent, simplified tool environments, or isolated function calls, leaving realistic tool orchestration for recommendation underexplored. To bridge this gap, we propose RecToolBench, a Model Context Protocol (MCP)-based benchmark for evaluating tool-using recommender agents under fuzzy user instructions. RecToolBench contains more than 1,200 executable tasks across three recommendation domains, 13 MCP servers, and 32 tools, spanning single-tool calls, parallel tool calls, sequential tool chains, and hybrid tool orchestration. We construct RecToolBench with a scalable synthesize--fuzzify--judge pipeline that generates executable fuzzy recommendation tasks, and evaluates agent trajectories using rule-based execution checks and rubric-based LLM evaluation. Experiments on representative LLMs show that syntactically valid tool calls do not guarantee successful recommendations. Models struggle with semantic parameter grounding, multi-step evidence integration, and grounded final recommendations, especially as orchestration complexity increases. Our results identify tool orchestration under fuzzy user intent as a major bottleneck for agentic recommender systems. Our data and code are available at https://github.com/ShawnChenn/RecToolBench.