一项研究让六款前沿模型针对 7 篇近期 NLP 论文提出实验方案，并实际执行全部 415 个实验，其中 194 个被评为合理、有价值且新颖，仅 73 个同时超出种子论文且非显而易见。模型排名作用有限：首选方案优于随机选择，但未能证明优于最先写出的实验；预测优于基准率，却不比同模型仅读论文和注册信息的新实例明显更好。多智能体团队成本更高，提案质量未见明显提升。
Regarding autoresearch agents, this question has attracted a lot of attention.
Do research agents have taste?
This has attracted massive interest because autoresearch agents could unlock major discoveries.
This study gave six frontier models seven recent NLP papers, then ran every experiment they proposed, including the ones they ranked last.
Of 415 experiments, 194 were judged sound, valuable, and new. Only 73 were also beyond the seed paper and non-obvious.
The rankings added little. First choices beat a random pick, but they were not shown to beat the experiment written first.
Forecasts beat a base rate, but they were not measurably better than a fresh instance of the same model that read only the paper and registrations.
They tested with teams of agents, which cost more, with no clear improvement in proposal quality.
https://arxiv.org/abs/2610.40488
Chat with Paper: https://academy.dair.ai/papers/rtaste-do-research-agents-have-taste-evaluating-early-stage-research-judgment-2610.40488
来源：elvis · x.com