Pith. sign in

REVIEW 13 cited by

WebWalker: Benchmarking LLMs in Web Traversal

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.07572 v3 pith:6JFR5FCD submitted 2025-01-13 cs.CL cs.AI

Jialong Wu , Wenbiao Yin , Yong Jiang , Zhenglin Wang , Zekun Xi , Runnan Fang , Linhai Zhang , Yulan He
show 3 more authors
Deyu Zhou Pengjun Xie Fei Huang
This is my paper
classification cs.CLcs.AI
keywords llmswebwalkerabilitydemonstratestraversalwebwalkerqaacrossaddress
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented generation (RAG) demonstrates remarkable performance across tasks in open-domain question-answering. However, traditional search engines may retrieve shallow content, limiting the ability of LLMs to handle complex, multi-layered information. To address it, we introduce WebWalkerQA, a benchmark designed to assess the ability of LLMs to perform web traversal. It evaluates the capacity of LLMs to traverse a website's subpages to extract high-quality data systematically. We propose WebWalker, which is a multi-agent framework that mimics human-like web navigation through an explore-critic paradigm. Extensive experimental results show that WebWalkerQA is challenging and demonstrates the effectiveness of RAG combined with WebWalker, through the horizontal and vertical integration in real-world scenarios.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs

    cs.CL 2025-09 conditional novelty 7.0 of 10

    A 7B LLM agent trained with student-led distillation and one-step teacher corrections nearly matches a 72B teacher on reasoning and tool-use benchmarks.

  2. Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

    cs.AI 2025-06 conditional novelty 7.0 of 10

    Mind2Web 2 is a 130-task benchmark for long-horizon agentic search with a tree-structured automated judge, showing OpenAI Deep Research reaches about 50 to 70 percent of human performance.

  3. From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution

    cs.AI 2026-08 conditional novelty 6.0 of 10

    An automatic pipeline evolves simple QA questions into 500 deep-research tasks with DAG-structured, fact-grounded rubrics that discriminate between models.

  4. Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Fetch-then-Explore, which stores fetched pages in a per-question workspace and extracts evidence on demand with grep/read, beats visit-and-read and browsing baselines on BrowseComp across three LLM backbones.

  5. Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents

    cs.CL 2026-07 conditional novelty 6.0 of 10

    A tabular UCB controller trained on task success improves LLM-agent memory use over fixed heuristics, without extra LLM calls.

  6. Open Data Synthesis For Deep Research

    cs.CL 2025-08 conditional novelty 6.0 of 10

    InfoSeek automatically synthesizes hierarchical constraint-satisfaction QA data from webpages; a 3B agent trained on it reaches 16.5% accuracy on BrowseComp-Plus, outperforming Qwen3-32B and Gemini 2.5 Flash.

  7. MetaAgent: Toward Self-Evolving Agent via Tool Meta-Learning

    cs.AI 2025-08 reject novelty 6.0 of 10

    The paper advertises a self-evolving tool-using agent that beats baselines, but the body contains a different math paper, leaving the performance claims unsupported.

  8. SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A history-aware guard model with an LLM judge is reported to cut jailbreak success on mobile agent tasks from 86.1% to 8.4% while keeping task completion unchanged at 77.8%.

  9. GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies

    cs.AI 2025-06 conditional novelty 6.0 of 10

    A new benchmark with 5,318 GUI tasks, including 200 abnormal ones, shows that state-of-the-art GUI agents degrade sharply when real-world anomalies appear.

  10. Contrastive Reinforced Policy Optimization via Privileged Self-Distillation

    cs.LG 2026-07 conditional novelty 5.0 of 10

    CRPO turns on-policy self-distillation into group-wise contrastive learning gated by student–teacher entropy gaps, improving multi-turn agentic LLM post-training over GRPO, ARPO, and OPSD.

  11. LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    LiteResearcher uses a lite virtual world to make agentic RL training scalable and stable, enabling a 4B model to achieve 71.3% on GAIA and 78.0% on Xbench, outperforming larger open-source and commercial systems.

  12. Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents

    cs.LG 2025-09 conditional novelty 5.0 of 10

    EMPG re-weights policy-gradient updates by step-level token entropy, amplifying confident correct actions and muting uncertain ones, and adds a future-clarity bonus.

  13. Deep Research Agents: A Systematic Examination And Roadmap

    cs.AI 2025-06 conditional novelty 4.0 of 10

    A survey that organizes LLM-powered deep research agents into static versus dynamic workflows and single versus multi agent architectures, and reviews their benchmarks and open challenges.

Pith tools