dair-ai's Top AI Papers of the Week: CMU's Harness Learning and Six More Picks
dair_ai · x · 2026-10-11
dair-ai's weekly paper roundup (Oct 5–11) features seven picks: VERA, HERMES, CorpusMap, VeriHarness, Sharpening Tax, Harness Learning, and Multi-Agent Self-Supervision.
The top pick, Harness Learning from CMU, frames an agent as model + harness, where the harness is the program organizing model calls, tool use, and information flow—and trains a proposer model to iteratively revise the harness. The rest span verification, multi-agent self-supervision, and other directions.
More from Research
- figwig: auto-optimized multithreaded bigWig reader/writer, 20x faster FIMO — jmschreiber91 · 2026-10-11
- auto-optimize speeds up genomics tool fimo ~20x with bit-identical results — jmschreiber91 · 2026-10-11
- Pointing auto-optimize at genomics code: tomtom made 7.8x faster, bit-identical output — jmschreiber91 · 2026-10-11
- 13-line lean proof of Catalan's constant irrationality; OpenAI proof controversies blamed on formalization conventions — ctjlewis · 2026-10-11
- Narrow ASI Inevitable, Broad ASI Not: Ramez and Sayashk Debate Task-Level Limits — sudoraohacker · 2026-10-11
- Auditing Agents' Last Exam: Porting the ALE Linux CLI subset to Verifiers v1 reveals widespread data flaws — dejavucoder · 2026-10-11