# The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents

arXiv: https://arxiv.org/abs/2603.00801 · HTML: https://mlsanity.com/paper/2603.00801/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 40 references that are in the map.
- First posted on arXiv 28 Feb 2026.

## Builds on (most cited first, 30 of 38)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Cognitive Architectures for Language Agents](https://mlsanity.com/paper/2309.02427/) (2023)
- [TextWorld: A Learning Environment for Text-based Games](https://mlsanity.com/paper/1806.11532/) (2018)
- [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://mlsanity.com/paper/2401.15391/) (2024)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [Corrective Retrieval Augmented Generation](https://mlsanity.com/paper/2401.15884/) (2024)
- [RA-DIT: Retrieval-Augmented Dual Instruction Tuning](https://mlsanity.com/paper/2310.01352/) (2023)
- [WebLINX: Real-World Website Navigation with Multi-Turn Dialogue](https://mlsanity.com/paper/2402.05930/) (2024)
- [An Illusion of Progress? Assessing the Current State of Web Agents](https://mlsanity.com/paper/2504.01382/) (2025)
- [The BrowserGym Ecosystem for Web Agent Research](https://mlsanity.com/paper/2412.05467/) (2024)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [Dissecting Adversarial Robustness of Multimodal LM Agents](https://mlsanity.com/paper/2406.12814/) (2024)
- [Automatic and Universal Prompt Injection Attacks against Large Language Models](https://mlsanity.com/paper/2403.04957/) (2024)
- [SafeArena: Evaluating the Safety of Autonomous Web Agents](https://mlsanity.com/paper/2503.04957/) (2025)

## Built on by (most cited first, 3 of 3)

- [Don't Blindly Trust It: How Unreliable Feedback Breaks Tool-Using LLM Agents](https://mlsanity.com/paper/2606.21409/) (2026)
- [MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments](https://mlsanity.com/paper/2606.19893/) (2026)
- [Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models](https://mlsanity.com/paper/2608.18884/) (2026)

## Abstract (arXiv)

Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial ranking - where misleading information appears prominently in search results - remains poorly understood. Existing benchmarks evaluate functional navigation or static factuality but cannot causally isolate this vulnerability, and current mitigation strategies for retrieval-augmented generation remain largely untested under such conditions. We introduce Synthetic Web Benchmark, a procedurally generated environment comprising thousands of hyperlinked articles with ground-truth labels for credibility and factuality, process-level interaction traces, and contamination filtering to eliminate training-data leakage. By injecting a single high-plausibility misinformation article into a controllable search rank, we measure the causal effect of adversarial exposure in six frontier models. The results reveal catastrophic failures: accuracy collapses despite unlimited access to truthful sources, with minimal search escalation and severe miscalibration. These findings expose fundamental limitations in how current frontier models handle conflicting information, with immediate implications for deployment in high-stakes domains. Our benchmark enables systematic analysis of these failure modes and provides a controlled testbed for evaluating mitigation strategies under adversarial ranking - a gap in current research. This work establishes a reproducible baseline for developing search-robust and epistemically humble agents capable of resisting manipulation in high-stakes domains.