arxiv
PublishedMay 22, 2026 at 4:00 AM
LLM Agents Already Know When to Call Tools -- Even Without Reasoning
Publisher summary· verbatim
arXiv:2605.09252v2 Announce Type: replace Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed. We prop
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivEDEN: A Large-Scale Corpus of Clinical Notes for Italian17harxivASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection17harxivLoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling17harxivAPPO: Agentic Procedural Policy Optimization17hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗