Insight certainty 4/5 debate potential 2/5

Vaidya: LLM agents get confused when exposed to over 20 tool actions

Karan Vaidya · ⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra · Aug 4, 2025 · at 10:46

Karan Vaidya, co-founder of Composio, explains practical constraints in agent tool selection on the Latent Space podcast.

0:00 / 0:12exact quote · 12.5s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“More than like 20, 25 actions like just confuses the server. Like it's not able to kind of like figure out which tool to use. And same goes with like, if the schema of the tools are really complex, that also confuses the agent.”

quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →

More from Karan Vaidya

Disclosure
Vaidya: Composio evolves agent skills by analyzing usage patterns
“We are kind of self evolving skills now for agents. So people building or using agents want to like basically make Agents interact with their apps. They can use Composio. We manage all the authentication and user account related stuff for them so that they don…”
Karan Vaidya Aug 4, 2025 ▶ 0:36 ⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra
Disclosure
Karan Vaidya: Composio runs an internal agent to build and evaluate skills
“We have an agent essentially, which builds a lot of these skills and kind of like does a lot of like testing as well as eval. So it's like, you can say like agent as an eval where our internal agent uses these tools and kind of like we figured out where it is …”
Karan Vaidya Aug 4, 2025 ▶ 5:38 ⚡️Composio: 10,000+ tools that evolve for Agents — Karan Vaidya and Soham Ganatra
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.