Skip to content
← Back to explorer

HFEPX Hub

Automatic Metrics + General + Web Browsing Papers

Updated from current HFEPX corpus (Mar 8, 2026). 11 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Mar 8, 2026). 11 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Frequently cited benchmark: BrowseComp. Common metric signal: accuracy. Use this page to compare protocol setup, judge behavior, and labeling design decisions before running new eval experiments. Newest paper in this set is from Feb 18, 2026.

Papers: 11 Last published: Feb 18, 2026 Global RSS Tag RSS
Automatic MetricsGeneralWeb Browsing

Researcher Quick Triage

This hub is best used for protocol triage and replication planning from abstract-level evidence. Quality band: Developing .

All Sampled Papers (11) Replication-Ready Only (3)

High-Signal Coverage

100.0%

11 / 11 sampled papers are not low-signal flagged.

Replication-Ready Set

3

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

  • 3 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 0 papers support judge-vs-human agreement analysis.
  • 0 papers report explicit quality controls (calibration/adjudication/IAA).

Primary action: Start with the top 2 papers in “Start Here”, then validate assumptions in the protocol matrix.

Why This Matters For Eval Research

  • 45.5% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 100% of papers in this hub.
  • BrowseComp is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Quality-control reporting is sparse in this slice; prioritize papers with explicit calibration or adjudication steps.
  • Rater context is mostly domain experts, and annotation is commonly mixed annotation units; use this to scope replication staffing.
  • Stratify by benchmark (BrowseComp vs DROP) before comparing methods.

Benchmark Interpretation

  • BrowseComp appears in 9.1% of hub papers (1/11); use this cohort for benchmark-matched comparisons.
  • DROP appears in 9.1% of hub papers (1/11); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 36.4% of hub papers (4/11); compare with a secondary metric before ranking methods.
  • jailbreak success rate is reported in 18.2% of hub papers (2/11); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (45.5% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (0% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

    Coverage is strong (36.4% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (90.9% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (9.1% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (0% vs 35% target).

Strengths

  • Strong human-feedback signal (45.5% of papers).
  • Most papers provide measurable evaluation context (36.4% benchmarks, 90.9% metrics).
  • Agentic evaluation appears in 100% of papers.

Known Gaps

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (9.1% coverage).
  • Annotation unit is under-specified (0% coverage).

Suggested Next Analyses

  • Stratify by benchmark (BrowseComp vs DROP) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and jailbreak success rate.
Recommended Queries (Expanded)

Recommended Queries

Benchmark Slice: BrowseComp Metric Slice: accuracy Recent High-Signal Papers

Start with These 3

Use these when you need one protocol anchor, one benchmark anchor, and one recent comparison point before reading the wider hub.

Start Here (Best First 6)

Ranked for protocol completeness (human signal, benchmark + metric anchors, quality controls, and judge/human overlap).

Protocol Matrix (Top 12)

Use this to quickly compare protocol ingredients instead of scanning long prose.

Paper HF Signal Eval Modes Benchmarks Metrics QC
MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks

Feb 18, 2026

 Yes
Pairwise Preference
Automatic Metrics Memoryarena Recall Not Reported
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

May 28, 2025

 Yes
Red Team
Automatic Metrics Rtc Bench Jailbreak success rate Not Reported
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Mar 3, 2026

 Yes
Red Team
Automatic Metrics Not Reported Success rate , Jailbreak success rate Not Reported
Modeling Distinct Human Interaction in Web Agents

Feb 19, 2026

 Yes
Pairwise Preference
Automatic Metrics Not Reported Accuracy Not Reported
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

Feb 3, 2026

 No
Not Reported
Automatic Metrics DROP Accuracy Not Reported
BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

Feb 13, 2026

 No
Not Reported
Automatic Metrics , Simulation Env Not Reported Accuracy Not Reported
Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents

Feb 26, 2026

 No
Not Reported
Automatic Metrics Not Reported Precision , Latency Not Reported
Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Feb 19, 2026

 No
Not Reported
Automatic Metrics Not Reported Task success Not Reported
The Automatic Verification of Image-Text Claims (AVerImaTeC) Shared Task

Feb 11, 2026

 No
Not Reported
Automatic Metrics Not Reported Accuracy Not Reported
CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation

Jan 28, 2025

 Yes
Pairwise Preference , Demonstrations
Automatic Metrics Not Reported Success rate , Task success Not Reported
Onboard-Targeted Segmentation of Straylight in Space Camera Sensors

Feb 24, 2026

 No
Not Reported
Automatic Metrics Not Reported Not Reported Not Reported

Protocol Diff (Top Papers)

Fast side-by-side comparison for the highest-ranked papers in this hub.

Signal MemoryArena: Benchmarking Agent Memory in Interdepe… RedTeamCUA: Realistic Adversarial Testing of Comput… MUSE: A Run-Centric Platform for Multimodal Unified…
Human Feedback Pairwise PreferenceRed TeamRed Team
Evaluation Modes Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks MemoryarenaRtc BenchNot reported
Metrics RecallJailbreak success rateSuccess rate, Jailbreak success rate
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownUnknownUnknown
Annotation Unit UnknownUnknownUnknown
Suggested Reading Order (Extended)

This section is intentionally expanded only when needed; use “Start Here” above for a faster pass.

Suggested Reading Order

  1. MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + red-team protocols. Focus: success rate. Abstract: We present MUSE (Multimodal Unified Safety Evaluation), an open-source,.

  2. Spatio-Temporal Token Pruning for Efficient High-Resolution GUI Agents

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: precision. Abstract: Pure-vision GUI agents provide universal interaction capabilities but suffer from severe efficiency bottlenecks.

  3. Onboard-Targeted Segmentation of Straylight in Space Camera Sensors

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Abstract: This study details an artificial intelligence (AI)-based methodology for the semantic segmentation of space camera.

  4. MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + pairwise preferences. Focus: Memoryarena / recall. Abstract: MemoryArena supports evaluation across web navigation, preference-constrained.

  5. RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + red-team protocols. Focus: Rtc-Bench / jailbreak success rate. Abstract: Computer-use agents (CUAs) promise to.

  6. Modeling Distinct Human Interaction in Web Agents

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: accuracy. Abstract: Despite rapid progress in autonomous web.

  7. CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: success rate. Abstract: While much work on web.

  8. BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

    Adds automatic metrics for broader protocol coverage within this hub. Signals: automatic metrics. Focus: accuracy. Abstract: Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use.

Known Limitations

Known Limitations

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (9.1% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Research Utility Snapshot

Human Feedback Mix

  • Pairwise Preference (3)
  • Red Team (2)
  • Demonstrations (1)

Evaluation Modes

  • Automatic Metrics (11)
  • Simulation Env (1)

Top Benchmarks

  • BrowseComp (1)
  • DROP (1)
  • Memoryarena (1)
  • Rtc Bench (1)

Top Metrics

  • Accuracy (4)
  • Jailbreak success rate (2)
  • Success rate (2)
  • Task success (2)

Rater Population Mix

  • Domain Experts (1)

Quality Controls

Coverage diagnostics (sample-based): human-feedback 45.5% · benchmarks 27.3% · metrics 90.9% · quality controls 0.0%.

Top Papers

Related Hubs

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote