DUET 联合优化智能体与评分器，Finance Agent Benchmark 达 96.5%
DUET 通过交替更新 LLM 评分器与智能体求解器，在 Finance Agent Benchmark 上将求解器成绩提升至 96.5%，超过 GEPA（94.4%）和 SkillOpt（94.0%）。
Nice paper on optimizing agents and their graders together.
The key finding is that you want to update your LLM grader alongside the agent instead of keeping it fixed, because the agent's failure modes change as it improves.
DUET alternates between the two.
Each round picks training tasks, runs the solver, has the grader score and critique the trajectories, then a tool-using updater revises either the grader or the solver while the other stays fixed.
On the Finance Agent Benchmark, the solver reaches 96.5%, above GEPA (94.4%) and SkillOpt (94.0%). It also beats both when they optimize against the benchmark's own reference evaluator.
Grader agreement rises from 68.4% to 78.5% on GDPval. Training the grader with the solver frozen moves agreement only from 67.9% to 68.8%.
Paper: academy.dair.ai/papers/duet-…
来源：dair_ai · x.com