Meta proposes AI Research Preference Models to help agents select high-value experiments
omarsar0 · x · 2026-09-02
Meta discusses a key bottleneck for long-horizon research agents: selecting which experiments to run given limited GPU budget. The paper introduces "AI Research Preference Models" trained to predict the most promising candidate solutions before execution. Two variants are proposed: an inference-only model that reasons over plans and history, and an agentic model that runs small-scale pilot experiments first. Integrated into AIRA-dojo and measured on AIRS-Bench, the approach improved the average normalized score from 0.684 to 0.711 and 0.729, outperforming unguided agents.
More from coding & agent
- Pi Durable Agent harness on Cloudflare powers fully autonomous apps with zero human input — MicahBerkley · 2026-10-18
- Dev: the right prompts can make your codebase 2x faster every 10 minutes for an hour straight — cephaloform · 2026-10-18
- LLM one-shots a Minecraft 3x3 piston door by building its own Linux test infra — Vjeux · 2026-10-18
- Dev builds Mumbai-inspired 3D manga background generator from OpenStreetMap data — CurieuxExplorer · 2026-10-18
- Solo founder builds a money-printing data service on Claude's Pi Durable harness — MicahBerkley · 2026-10-18
- Dev builds Arch-based OS with custom desktop and browser using Claude Code — Snoo-10493 · 2026-10-18