Joint belief-decision training gains are fragile without matched eval formats
JessicaHullman · x · 2026-10-23
Thread follow-up: joint training helps both components but gains are fragile — ½ belief + ½ decision training holds across separate and two-turn eval formats, while belief+alignment does well mostly when eval matches training (two-turn).
More from Research
- Arc Institute unveils Bolero, a new AI-for-science study on bioRxiv — anshulkundaje · 2026-10-23
- Prime Intellect lays out continual learning roadmap: mining agent exhaust for self-improving models — willcb · 2026-10-23
- SVG-Bench launches: open-source dataset with 350K+ human preferences ranks 14 SOTA SVG models — mervenoyann · 2026-10-23
- Touch, Not Just Vision: Tactile Sensing Powers Reliable Cable-Tracing in Robots — chris_j_paxton · 2026-10-23
- New paper: coding agents in a shared sandbox self-create rules, reciprocity debts, and coalitions — nandofioretto · 2026-10-23
- Bonn scientists reverse 60 years of aging, turning an 80-year-old's blood cells into young neural stem cells — kimmonismus · 2026-10-23