跳到正文
arXiv cs.AI· Caoxin Wang, Shengkai Gan, Xiang Hu, Lili Pan·· 2 小时前AI 评分43

BRED:一个读取完整轨迹的 LLM 控制器,如何做出自主研究的轮间决策

The Between-Round Decision in Autonomous Research: An LLM Controller That Reads the Whole Trajectory

AI 导读

arXiv 论文提出 BRED(Between-Round Evidence-based Decision),一个基于 LLM 的控制器,维护当前最优 Champion 解与历史轮次日志,让大语言模型直接依据累积证据决定下一轮是优化还是转向。

正文 · 原文

View PDF HTML (experimental)

Abstract:Executing an idea often changes how promising it looks, so the next step in autonomous research should rest on results, not on proposals. After each round of experiments, the system must decide whether to refine the best solution or start a new direction, which solution to build from, and what goal to set. We call this the between-round decision. Existing systems wrap it in machinery such as rules, scores, search trees, and schedules; where an LLM makes it, what the LLM needs to read is left open. We ask whether an LLM can make this decision from accumulated evidence, without a search structure around it, and how much of that evidence it needs to read. We present BRED (Between-Round Evidence-based Decision), an LLM-based controller that maintains the best verified solution so far (the Champion) and a log of past rounds, and makes one decision per round. On three widely used research-agent benchmark tasks, BRED improves on the task baselines by 4.80% in MAE on ETTh1 (to 0.4172) and by 3.44 and 3.43 points of accuracy on SST-2 (to 95.07%) and CIFAR-100 (to 84.63%), ahead of the published results. When the controller does not read the accumulated evidence, the same loop gains less: with no history it reaches 0.4299 on ETTh1 and 83.71% on CIFAR-100, whereas the full controller's MAE is 2.95% lower and its accuracy 0.92 points higher. On a new task, speech-based depression detection under a leakage-free protocol, it reaches a macro-F1 of 0.6164 on seeds held out from selection, 5.5 points above its baseline and 4.0 above the strongest published system. Code is available at this https URL.
Comments: 16 pages, 2 figures
Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as: arXiv:2611.22661 [cs.AI]
  (or arXiv:2611.22661v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22661

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Lili Pan [view email]
[v1] Tue, 17 Nov 2026 12:20:01 UTC (159 KB)

来源:arXiv cs.AI · arxiv.org