agent/papers/items/2025-2509-26553-towards-reliable-benchmarking-a-contamination-free-controllable-evaluation-frame.md

Paper: Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling

---

type: paper title: "Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling" authors: Seiji Maekawa, Jackson Hassell, Pouya Pezeshkpour, Tom Mitchell, Estevam Hruschka year: 2025 venue: arXiv url: https://arxiv.org/abs/2509.26553 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2025-09-30 updated_at: 2026-02-06 status: queued relevance: high topics:

• agent-evaluation
• reasoning
• tool-use methods:

benchmarks:

models:

datasets:

• cs.CL
• cs.PL related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 15 collection_queries: function-calling

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: function-calling
• inferred topics: agent-evaluation, reasoning, tool-use
• arXiv categories: cs.CL, cs.PL
• collection score: 15

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2509.26553