ICML Spotlights Three Studies on Agent Failures
wzenus · x · 2026-07-10
This post covers a contributed oral session by @jiankuiuc, @mertcemri, and Yuting Yan, featuring three complementary studies on agent failures: D-CEM discussed using loss-aware negotiation control to avoid unsafe consensus; Who&When Pro serves as a large-scale multimodal failure attribution benchmark; and ATLAS demonstrated how an adaptive failure taxonomy improves judgment, reflection, and agent optimization.
The original post also notes that those unable to attend ICML 2026 in person can catch up on these projects via Discord's live paper QA.
Related event: ICML 2026 FAGEN Workshop Spotlights AI Agent Failure Modes(11 posts)→
More from coding & agent
- OpenWiki adds Gemini AI Studio and Vertex AI support for codebase docs — BraceSproul · 2026-07-22
- OpenWiki adds Gemini AI Studio and Vertex AI support plus Gemini 3.6 Flash — BraceSproul · 2026-07-22
- Poolside launches Laguna S 2.1 with 118B parameters and 8B active per token — Madisonkanna · 2026-07-22
- OpenWiki adds Gemini AI Studio, Vertex AI, and new Flash models — BraceSproul · 2026-07-22
- A Forward Deployed Engineer job really has three stages: audit, evals, deploy — blaizedsouza · 2026-07-22
- 438 sealed tests show coding agents prefer DIY over third-party databases — cramforce · 2026-07-22