Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

TimeWarp: Evaluating Web Agents by Revisiting the Past

Md Farhan Ishmam, Kenneth Marino

Published

Mar 5, 2026

Citations

0

Trust level

Moderate

Usefulness score

40/100 (Low)

Extraction confidence

50% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 5, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Demonstrations General Web Browsing

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 for comparison and orientation, not as your only source.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Read the full paper before copying any benchmark, metric, or protocol choices.

Main weakness

The abstract does not clearly name benchmarks or metrics.

Human feedback signal
Detected
From extracted signals
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
40/100
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

The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes? We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that vary in UI, design, and layout. TimeWarp consists of three web environments, each with six UI versions spanning different eras of the internet, paired with a set of complex, realistic tasks requiring different forms of web navigation. Our experiments reveal web agents' vulnerability to changes and the limitations of behavior cloning (BC) on single-version trajectories. To address this, we propose TimeTraj, a simple yet effective algorithm that uses plan distillation to collect trajectories across multiple versions. By training agents on teacher rollouts using our BC-variant, we achieve substantial performance gains: $20.4\%\rightarrow37.7\%$ for Qwen-3 4B and $0\%\rightarrow27.0\%$ for Llama-3.1 8B models. We hope our work helps researchers study generalization across web designs and unlock a new paradigm for collecting plans rather than trajectories, thereby improving the robustness of web agents.

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

strong

Demonstrations

Directly usable for protocol triage.

"The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?"

Evaluation Modes

missing

None explicit

Validate eval design from full paper text.

"The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?"

Quality Controls

missing

Not reported

No explicit QC controls found.

"The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?"

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?"

Reported Metrics

missing

Not extracted

No metric anchors detected.

"The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?"

Benchmarks and datasets

No benchmark or dataset names were extracted from the available abstract.

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
Yes
Feedback types
Demonstrations
Rater population
Not reported
Unit of annotation
Trajectory
Expertise required
General
Evaluation details
Evaluation modes
None
Agentic eval
Web Browsing
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Background context only

Research brief

Metadata summary

The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?

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

Key takeaways

  • The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?
  • We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that vary in UI, design, and layout.
  • TimeWarp consists of three web environments, each with six UI versions spanning different eras of the internet, paired with a set of complex, realistic tasks requiring different forms of web navigation.

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

  • The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?
  • We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that vary in UI, design, and layout.
  • To address this, we propose TimeTraj, a simple yet effective algorithm that uses plan distillation to collect trajectories across multiple versions.

Why it matters for eval

  • The improvement of web agents on current benchmarks raises the question: Do today's agents perform just as well when the web changes?
  • We introduce TimeWarp, a benchmark that emulates the evolving web using containerized environments that vary in UI, design, and layout.

Researcher checklist

  • Human feedback protocol is explicit

    Detected: Demonstrations

  • Evaluation mode is explicit

    No clear evaluation mode extracted.

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Metric reporting is present

    No metric terms extracted.