·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Chinese cybercrime operation that used AI to scam ‘hundreds of thousands of victims’ sued by Google1h◆SpaceX IPO: Live updates on everything you need to know1h◆Mistral is rumored to be raising €3B at €20B valuation4h◆Siri is good now??4h◆Elon Musk is the world’s first trillionaire5h◆SpaceX, Anthropic, and OpenAI’s hot IPO summer5h◆olmo-eval: An evaluation workbench for the model development loop5h◆It’s hot IPO summer, and the MANGOS are ripe5h◆SpaceX’s massive IPO: all the latest news7h◆Jeff Bezos’ AI startup aims to build an ‘artificial general engineer’7h◆New OpenAI Academy courses for the next era of work11h◆Siri won’t be your AI girlfriend14h◆Cheaper, faster, and culturally aware, Avataar’s video AI is built for India’s scale17h◆EDEN: A Large-Scale Corpus of Clinical Notes for Italian17h◆ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection17h◆LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling17h◆APPO: Agentic Procedural Policy Optimization17h◆ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing17h◆Grounding Computer Use Agents on Human Demonstrations17h◆WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning17h◆Chinese cybercrime operation that used AI to scam ‘hundreds of thousands of victims’ sued by Google1h◆SpaceX IPO: Live updates on everything you need to know1h◆Mistral is rumored to be raising €3B at €20B valuation4h◆Siri is good now??4h◆Elon Musk is the world’s first trillionaire5h◆SpaceX, Anthropic, and OpenAI’s hot IPO summer5h◆olmo-eval: An evaluation workbench for the model development loop5h◆It’s hot IPO summer, and the MANGOS are ripe5h◆SpaceX’s massive IPO: all the latest news7h◆Jeff Bezos’ AI startup aims to build an ‘artificial general engineer’7h◆New OpenAI Academy courses for the next era of work11h◆Siri won’t be your AI girlfriend14h◆Cheaper, faster, and culturally aware, Avataar’s video AI is built for India’s scale17h◆EDEN: A Large-Scale Corpus of Clinical Notes for Italian17h◆ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection17h◆LoHoSearch: Benchmarking Long-Horizon Search Agents Beyond the Human Difficulty Ceiling17h◆APPO: Agentic Procedural Policy Optimization17h◆ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing17h◆Grounding Computer Use Agents on Human Demonstrations17h◆WISE: A Long-Horizon Agent in Minecraft with Why-Which Reasoning17h◆
News/LLM Agents Already Know When to Call Tools -- Even Without Reasoning
arxiv
PublishedMay 22, 2026 at 4:00 AM

LLM Agents Already Know When to Call Tools -- Even Without Reasoning

Source
arxiv.orgfull article ↗
Read on arxiv→
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.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

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 Optimization17h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews