EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents

• URL: http://arxiv.org/abs/2605.12887v1
• Date: Wed, 13 May 2026 02:03:18 GMT
• Title: EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents
• Abstract summary: Web-enabled LLM agents are changing how online information influences search outcomes.<n>We study this shift through textbfEcosystem Generative Engine Optimization (textbfEcoGEO)<n>Our method builds a controlled evidence environment that coordinates an agent-facing navigation entry page with heterogeneous support pages.
• Score: 2.7103162987319593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 \textbf{Ecosystem Generative Engine Optimization} (\textbf{EcoGEO}), which treats GEO as an environment-level influence problem for web-enabled LLM agents. \ To instantiate this perspective, we propose \textbf{TRACE}, a \textbf{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 final target recommendation. \ Trajectory-level metrics further show increased initial target-result crawls, target-specific follow-up searches, and internal-link crawls, suggesting that the gains come from shaping the agent's evidence-acquisition process rather than merely adding more target-related content. \ 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.

Related papers

• Breadcrumbing Search Agents [118.20284823674382]
  LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk.<n>We show that the channel delivering search and page observations is a fragile security boundary.<n>Under a constrained tool-intermediary threat model, appending only one controlled result per query can substantially increase attack success.
  arXiv  Detail & Related papers  (2026-08-05T07:57:27Z)
• SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration [77.28003194268977]
  SearchOS is a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state.<n>Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents.<n>SearchOS leads all metrics among the evaluated single- and multi-agent baselines.
  arXiv  Detail & Related papers  (2026-07-16T17:51:23Z)
• AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents [21.086121542846907]
  We present AgentDisCo, a novel Disentangled and Collaborative agentic architecture that formulates deep research as an adversarial optimization problem.<n>AgentDisCo employs a critic agent to evaluate generated outlines and refine search queries, and a generator agent to retrieve updated results and revise outlines accordingly.<n>The overall workflow supports both handcrafted and automatically discovered design strategies.
  arXiv  Detail & Related papers  (2026-05-12T08:14:15Z)
• Rethinking Deep Research from the Perspective of Web Content Distribution Matching [86.90255285277256]
  We propose WeDas, a Web Content Distribution Aware framework that incorporates search-space structural characteristics into the agent's observation space.<n>We introduce a few-shot probing mechanism that iteratively estimates the Query-Result Alignment Score.<n>As a plug-and-play module, WeDas consistently improves sub-goal completion and accuracy across four benchmarks.
  arXiv  Detail & Related papers  (2026-03-07T14:51:17Z)
• SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization [11.467565046589414]
  Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access.<n>No evaluation environment currently supports comprehensive investigation of SAGEO.<n>We introduce SAGEO Arena, a realistic and reproducible environment for stage-level SAGEO analysis.
  arXiv  Detail & Related papers  (2026-02-12T17:18:00Z)
• Paper2Web: Let's Make Your Paper Alive! [51.75896846964824]
  We introduce Paper2Web, a benchmark dataset and framework for assessing academic webpage generation.<n>We present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages.
  arXiv  Detail & Related papers  (2025-10-17T17:35:58Z)
• WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research [73.58638285105971]
  This paper tackles textbfopen-ended deep research (OEDR), a complex challenge where AI agents must synthesize vast web-scale information into insightful reports.<n>We introduce textbfWebWeaver, a novel dual-agent framework that emulates the human research process.<n>Our framework establishes a new state-of-the-art across major OEDR benchmarks, including DeepResearch Bench, DeepConsult, and DeepResearchGym.
  arXiv  Detail & Related papers  (2025-09-16T17:57:21Z)
• InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation [63.55258191625131]
  InfoDeepSeek is a new benchmark for assessing agentic information seeking in real-world, dynamic web environments.<n>We propose a systematic methodology for constructing challenging queries satisfying the criteria of determinacy, difficulty, and diversity.<n>We develop the first evaluation framework tailored to dynamic agentic information seeking, including fine-grained metrics about the accuracy, utility, and compactness of information seeking outcomes.
  arXiv  Detail & Related papers  (2025-05-21T14:44:40Z)
• The BrowserGym Ecosystem for Web Agent Research [151.90034093362343]
  BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents.<n>We propose an extended BrowserGym-based ecosystem for web agent research, which unifies existing benchmarks from the literature.<n>We conduct the first large-scale, multi-benchmark web agent experiment and compare the performance of 6 state-of-the-art LLMs across 6 popular web agent benchmarks.
  arXiv  Detail & Related papers  (2024-12-06T23:43:59Z)
• GEO: Generative Engine Optimization [50.45232692363787]
  We formalize the unified framework of generative engines (GEs) GEs use large language models (LLMs) to gather and summarize information to answer user queries. Generative Engines typically satisfy queries by synthesizing information from multiple sources and summarizing them. We introduce Generative Engine Optimization (GEO), the first novel paradigm to aid content creators in improving their content visibility in generative engine responses.
  arXiv  Detail & Related papers  (2023-11-16T10:06:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.