Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

When Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded Tasks

Yisheng Li, Dongming Han, Hongkun Pan, Bingcheng Mao +4 more

Published

Oct 9, 2026

Citations

0

Trust level

Low

Usefulness score

5/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 29, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this as background context only. Do not make protocol decisions from this page alone.

Best use

Background context only

Use if you need

A benchmark-and-metrics comparison anchor.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
5/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Web agents increasingly browse, interpret, and act on web content on behalf of users. In many realistic workflows, however, the visual evidence they consume is not neutral: charts and dashboards can be misleading, shaping judgments without issuing any explicit malicious instruction. Unlike chart question answering, Web Agents treat charts as intermediate evidence whose misinterpretation can propagate into concrete downstream actions --- a reliability risk that remains underexplored. We introduce MisVisAgentBench, the first paired executable benchmark for evaluating how misleading visualizations affect Web Agent execution. It comprises 280 task instances in matched clean--misleading pairs that differ only in chart evidence. We further provide a diagnostic framework that isolates misleading-induced failures from baseline task difficulty and captures execution-level effects such as extra browsing steps and decision hesitation. Across thirteen vision-language Web Agents, replacing clean charts with misleading counterparts reduces the average task success rate by more than 34 percentage points. Moreover, these failures predominantly follow the targeted misleading action branch, suggesting that deceptive charts systematically redirect rather than randomly disrupt agent decisions. These results reveal that visualization robustness is a critical yet understudied dimension of Web Agent safety and reliability.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Web agents increasingly browse, interpret, and act on web content on behalf of users."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"Web agents increasingly browse, interpret, and act on web content on behalf of users."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Web agents increasingly browse, interpret, and act on web content on behalf of users."

Benchmarks / Datasets

partial

Misvisagentbench

Useful for quick benchmark comparison.

"We introduce MisVisAgentBench, the first paired executable benchmark for evaluating how misleading visualizations affect Web Agent execution."

Reported Metrics

partial

Success rate, Task success

Useful for evaluation criteria comparison.

"Across thirteen vision-language Web Agents, replacing clean charts with misleading counterparts reduces the average task success rate by more than 34 percentage points."

Benchmarks and datasets

Misvisagentbench

Reported metrics

success ratetask success
Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
General
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

Web agents increasingly browse, interpret, and act on web content on behalf of users.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Web agents increasingly browse, interpret, and act on web content on behalf of users.
  • In many realistic workflows, however, the visual evidence they consume is not neutral: charts and dashboards can be misleading, shaping judgments without issuing any explicit malicious instruction.
  • Unlike chart question answering, Web Agents treat charts as intermediate evidence whose misinterpretation can propagate into concrete downstream actions --- a reliability risk that remains underexplored.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Web agents increasingly browse, interpret, and act on web content on behalf of users.
  • Unlike chart question answering, Web Agents treat charts as intermediate evidence whose misinterpretation can propagate into concrete downstream actions --- a reliability risk that remains underexplored.
  • We introduce MisVisAgentBench, the first paired executable benchmark for evaluating how misleading visualizations affect Web Agent execution.

Why it matters for eval

  • Web agents increasingly browse, interpret, and act on web content on behalf of users.
  • We introduce MisVisAgentBench, the first paired executable benchmark for evaluating how misleading visualizations affect Web Agent execution.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: Misvisagentbench

  • Metric reporting is present

    Detected: success rate, task success