Why Agents Can Code But Struggle in Enterprise
wzenus · x · 2026-07-10
This ICML/FAGEN 2026 invited talk discussed why modern agents excel at coding but still struggle with daily enterprise tasks. The speaker described modern agents as "the smartest novices in the world," suggesting that the core of continuous learning is compressing experiences into reusable skills, enabling agents to learn the unique rules of each organization.
Related event: Scholars Discuss AI Agent Enterprise Challenges and Security(2 posts)→
More from coding & agent
- Shopify design lead on AI-era workflow: designers are becoming full-stack editors — KlausCodes · 2026-10-26
- Ultrametric open-sources Open Startup Repo to let AI agents run startup operations — garrytan · 2026-10-26
- MCP fault injection study: agent task scores drop 60% under realistic tool failures, scale doesn't help — dair_ai · 2026-10-26
- General agents burn ~140M tokens/month on LinkedIn outreach; scripts do it 60x cheaper — ChrisHarpon2 · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- NLI alone rejects 5/6 new agent memories; a 0.45 similarity gate fixes it all — Alternative_Pin9598 · 2026-10-26