arXiv cs.CL· Zhivar Sourati, Marianne Menglin Liu, Zheng Wang, Rongguang Wang, Sai Ashish Somayajula, Tao Sheng, Kyu J. Han, Sujith Ravi, Dan Roth·· 2 天前AI 评分26
相同上下文，不同智能体：数据智能体中语义层、编排与压缩的行为研究
Same Context, Different Agents: A Behavioral Study of Semantic Layers, Orchestration and Compaction in Data Agents
AI 导读
研究在五个 benchmark 的 1,514 个长周期任务上，用七款 LLM 分析语义层、编排、压缩三种上下文工程技术单独及组合的效果。无这些技术的数据智能体分为调查者、过早作答者和提前放弃者三类行为组，每种技术只有匹配对应行为组才能转化为准确率提升；对调查者反而有害，编排会使其过度自信并损失 5 个百分点。
正文 · 原文
Abstract:Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but their success depends on context. Three context-engineering techniques (CETs) help by shaping it: semantic layers describe the data, orchestration splits work among agents, and compaction condenses interaction history. Existing studies validate each CET alone, leaving open how agent behavior shapes its effect. We present a comprehensive analysis of the three CETs, alone and combined, with seven large language models (LLMs) on 1,514 long-horizon tasks from five benchmarks, covering behavior, accuracy and cost. We find that data agents without CETs form three behavior groups: investigators, premature answerers that answer without inspecting data, and early stoppers that give up. Each CET delivers its known benefit, from more investigation to smaller prompts, but only the behavior group it matches turns that benefit into accuracy, such as premature answerers under orchestration. For investigators, the same CETs can hurt: the semantic layer stops them from looking, orchestration makes them overconfident, costing 5 percentage points, and compaction makes them repeat steps. Combining CETs yields smaller gains and losses than their sum. We derive guidance for choosing CETs by agent behavior, task demands and accuracy-cost trade-offs.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.20959 [cs.CL] |
| (or arXiv:2610.20959v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20959 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhivar Sourati [view email]
[v1]
Wed, 14 Oct 2026 21:29:59 UTC (1,195 KB)
来源：arXiv cs.CL · arxiv.org