Fixing Tool-Call Accuracy in vLLM(ubicloud.com)
108 points by coffeemug | 60 comments
Ubicloud blog post explaining tool-call schema accuracy problems when serving open-weight models like Kimi K2.6 in vLLM and how constrained decoding fixes them.
#tool-calling on Hacker News
4 stories tagged tool-calling, newest first.
Muse Spark 1.3(developer.meta.com)
670 points by bvaldivielso | 435 comments
Meta developer product page for Muse Spark 1.3, an AI model trained for agentic workflows and optimized for coding performance and reliable tool calling.
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots(cactuscompute.com)
501 points by HenryNdubuaku | 169 comments
Product page for Cactus Needle 2, an open 14MB agentic LLM for tool calling, device use, and structured extraction on phones, wearables, and tiny devices.
Show HN: My LLM CLI tool can run tools now, from Python code or plugins(simonwillison.net)
494 points by simonw | 157 comments
Simon Willison's blog post announcing LLM 0.26, which adds tool support to his LLM CLI and Python library via Python functions and tool plugins.