PatchScout: Thematic Web Data Collection via Information Foraging
cs.AI, cs.IR
Submitted: 2026-10-30
Updated: 2026-10-30
Comments: 10 pages, 1 figure, to be published in Advances in Neural Information Processing Systems 2026
License: http://creativecommons.org/licenses/by/4.0/
The gist: Researchers often need web corpora that are not answers to a single query, but reusable collections of documents spanning many decentralized sources.
Abstract
Researchers often need web corpora that are not answers to a single query, but reusable collections of documents spanning many decentralized sources. We refer to this problem as thematic web data collection: assembling semantically relevant documents that share a common theme but are scattered across heterogeneous and structurally disconnected regions of the web. Existing approaches, including traversal-based methods and LLM-driven web agents, are limited by local exploration or short-horizon stopping, preventing comprehensive collection. We formulate this task as a long-horizon information foraging problem over query-induced semantic patches, where the central challenge is deciding when to continue local exploitation and when to switch to new regions. We propose PatchScout, a multi-agent framework that instantiates a class of patch-switching policies to balance local exploitation and adaptive patch switching under a fixed budget. Experiments on four live-web topics show that PatchScout substantially improves yield and domain coverage over traversal-based and search-augmented reasoning agent baselines. In an applied social science setting with an incomplete prior collection, PatchScout discovers 102 previously unidentified entities, illustrating its ability to expand existing thematic datasets.
Sources
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- WebGPT: Browser-assisted question-answering with human feedback
- Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents