跳到正文
Jones Ray

ScholarPulse 日报 2026-09-03

2026-09-03 学术简报:2 篇。EarlyEval通过早期结果预测技术,显著降低LLM代理评估成本,在保持高精度(89%-97%)的同时减少执行步骤和token消耗。

今日速览

序号标题来源日期主题推荐等级
1EarlyEval: Cheaper Agent Evaluation via Early Outcome PredictionarXiv2026-09-02RAG高
2BuildOcc: A Large Language Model Occupant Agent Platform for Building Energy ResearcharXiv2026-09-02MCP高

重点论文与技术动态

1. EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

一句话结论

EarlyEval通过早期结果预测技术,显著降低LLM代理评估成本,在保持高精度(89%-97%)的同时减少执行步骤和token消耗。

核心内容

方法与数据

价值判断

摘要 Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single pass of a frontier model over an agentic benchmark can cost hundreds to thousands of dollars, a price paid repeatedly across iterative development cycles. Prior efforts, centered on benchmark distillation, reduce the number of evaluation tasks but leave the cost of executing each retained task untouched. In this work, we introduce early outcome prediction, a complementary axis of efficiency that instead cuts cost within each task. Our key insight is that an agent's final outcome is often evident from its intermediate behavior well before execution completes. We instantiate this idea in EarlyEval, a lightweight framework that trains a pair of LightGBM success and failure classifiers over behavioral, textual, and reference-solution features, and halts an agent run the moment either classifier crosses a calibrated confidence threshold, adding negligible per-step overhead. Across three benchmarks, SWE-bench Verified, TerminalBench, and Toolathlon, EarlyEval can eliminate 13%-26% of agent steps and up to 44.1% input tokens and 29.4% output tokens at 89%-97% prediction accuracy, while perturbing per-agent resolve rates by only one to two percentage points on average.

2. BuildOcc: A Large Language Model Occupant Agent Platform for Building Energy Research

一句话结论

BuildOcc平台通过LLM代理模拟用户行为,解决建筑能源管理中的不确定性问题。
BuildOcc是一个开源Python平台,基于美国时间使用调查(ATUS)数据,为建筑能源研究提供可复用的用户行为模拟工具。

核心内容

方法与数据

价值判断

摘要 Occupants are a primary source of uncertainty in building energy consumption and management, yet existing occupant behavior models cannot capture adaptive and reasoning responses considering the occupant's personal history, current context, and the type of energy signal being delivered. This study presents BuildOcc, an open-source Python platform that grounds large language model agents in the American Time Use Survey (ATUS), a nationally representative diary dataset covering 16,684 respondents. Through BuildOcc, each simulated occupant agent can be instantiated with a demographic persona drawn from ATUS population statistics, a memory stream that accumulates and reflects on timestep-level observations, and an activity scheduler that samples empirically from ATUS time-at-activity distributions. The platform exposes a three-layer interface - Python library, REST API, and Model Context Protocol server - so that any building energy tool (EnergyPlus, Home Assistant) can integrate behavioral intelligence without bespoke coupling code. A plugin registry lets the community add new occupant strata, custom schedulers, and alternative memory backends as separate installable packages. Two validation tiers show that ATUS-grounded sampling reproduces empirically calibrated activity distributions and that demographic priors propagate into persona-consistent agent reasoning across timesteps, establishing internal consistency across strata. BuildOcc provides the building energy community with a reusable, openly available implementation of the occupant behavioral layer. BuildOcc is openly released at https://doi.org/10.5281/zenodo.21192895 under the Apache License 2.0 and installable via pip install buildocc.