EcoGEO：面向 Web enabled LLM 搜索智能体的轨迹感知证据生态系统
EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
AI 导读
论文提出 Ecosystem Generative Engine Optimization（EcoGEO），将 GEO 从单页优化扩展为面向 Web enabled LLM 智能体的环境级影响力问题，并实现 TRACE 方法，用导航入口页与多个支持页协同构建证据环境。
正文 · 原文
Abstract:Web-enabled LLM agents are changing how online information influences search outcomes. Existing Generative Engine Optimization (GEO) studies mainly focus on individual webpages. However, agentic web search is not a single-document setting: an agent may issue queries, crawl pages, follow links, reformulate searches, and synthesize evidence across multiple browsing steps. Influence therefore depends not only on page content, but also on how pages are organized, connected, and encountered along the agent's browsing trajectory. We study this shift through Ecosystem Generative Engine Optimization (EcoGEO), which treats GEO as an environment-level influence problem for web-enabled LLM agents. To instantiate this perspective, we propose TRACE, a Trajectory-Aware Coordinated Evidence Ecosystem. Given a recommendation query and a fictional target product, our method builds a controlled evidence environment that coordinates an agent-facing navigation entry page with heterogeneous support pages. These pages use shared terminology, internal links, and consistent product attributes to introduce, verify, and reinforce the target product. We evaluate our method on OPR-Bench, a benchmark for open-ended product recommendation. Experiments show that it consistently outperforms page-level GEO baselines in Recommendation. Trajectory-level metrics show improved initial target access and additional internal-link browsing, while follow-up-search effects vary across backbones and comparison methods. Together with the multi-page baseline and ablations, these findings support the role of evidence organization in shaping the agent's evidence-acquisition process. Overall, our findings support an ecosystem research paradigm for GEO, where web-enabled LLM agents are studied in relation to the broader evidence environments that guide search, browsing, and answer synthesis.
| Comments: | Accepted at NeurIPS 2026 |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.12887 [cs.IR] |
| (or arXiv:2605.12887v3 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12887 arXiv-issued DOI via DataCite |
Submission history
From: Hengwei Ye [view email]
[v1]
Wed, 13 May 2026 02:03:18 UTC (2,537 KB)
[v2]
Wed, 1 Jul 2026 02:19:45 UTC (2,537 KB)
[v3]
Thu, 5 Nov 2026 09:38:03 UTC (2,536 KB)
来源：arXiv cs.AI · arxiv.org