Skip to content
← Back to explorer

HFEPX Hub

Web Browsing + Coding (Last 90 Days)

Updated from current HFEPX corpus (Apr 9, 2026). 11 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 9, 2026). 11 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequent quality control: Adjudication. Frequently cited benchmark: BIRD. 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 Mar 31, 2026.

Papers: 11 Last published: Mar 31, 2026 Global RSS Tag RSS
Web BrowsingCodingLast 90d

Researcher Quick Triage

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

High-Signal Coverage

100.0%

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

Replication-Ready Set

2

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

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

Primary action: Use this page for scouting only; collect additional papers before attempting replication-critical comparisons.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 45.5% of papers report explicit human-feedback signals, led by expert verification.
  • automatic metrics appears in 72.7% of papers in this hub.
  • BIRD is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is adjudication (18.2% of papers).
  • Rater context is mostly domain experts, and annotation is commonly multi-dimensional rubrics; use this to scope replication staffing.
  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.

Benchmark Interpretation

  • BIRD appears in 9.1% of hub papers (1/11); use this cohort for benchmark-matched comparisons.
  • Interruptbench 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.
  • cost is reported in 27.3% of hub papers (3/11); 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).

  • Moderate: Papers reporting quality controls

    Coverage is usable but incomplete (18.2% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

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

  • Strong: Papers naming evaluation metrics

    Coverage is strong (72.7% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (18.2% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (18.2% vs 35% target).

Strengths

  • Strong human-feedback signal (45.5% of papers).
  • Most papers provide measurable evaluation context (36.4% benchmarks, 72.7% metrics).
  • Agentic evaluation appears in 100% of papers.

Known Gaps

  • Only 18.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (18.2% coverage).
  • Annotation unit is under-specified (18.2% coverage).

Suggested Next Analyses

  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.
  • Stratify by benchmark (BIRD vs Interruptbench) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

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
Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

Feb 2, 2026

Yes Automatic Metrics Vdr Bench Not Reported Adjudication
When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation

Apr 1, 2026

Yes Simulation Env WebArena , Interruptbench Not Reported Not Reported
CounselReflect: A Toolkit for Auditing Mental-Health Dialogues

Mar 31, 2026

Yes Human Eval Not Reported Not Reported Adjudication
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo

Apr 7, 2026

No
Not Reported
Simulation Env Ludobench Dice Not Reported
LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving

Mar 23, 2026

No
Not Reported
Automatic Metrics BIRD Precision Not Reported
Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development

Mar 4, 2026

Yes Automatic Metrics Not Reported Accuracy , Agreement Not Reported
Sabiá-4 Technical Report

Mar 10, 2026

Yes Automatic Metrics Not Reported Accuracy , Cost Not Reported
AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning

Apr 7, 2026

No
Not Reported
Automatic Metrics Not Reported Accuracy Not Reported
From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion

Apr 2, 2026

No
Not Reported
Automatic Metrics Not Reported Cost Not Reported
A Benchmark for Deep Information Synthesis

Feb 24, 2026

No
Not Reported
Automatic Metrics Not Reported F1 Not Reported
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Feb 25, 2026

No
Not Reported
Automatic Metrics Not Reported Accuracy , Task success Not Reported

Protocol Diff (Top Papers)

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

Signal Vision-DeepResearch Benchmark: Rethinking Visual an… When Users Change Their Mind: Evaluating Interrupti… CounselReflect: A Toolkit for Auditing Mental-Healt…
Human Feedback Expert VerificationCritique EditRubric Rating, Expert Verification
Evaluation Modes Automatic MetricsSimulation EnvHuman Eval
Benchmarks Vdr BenchWebArena, InterruptbenchNot reported
Metrics Not reportedNot reportedNot reported
Quality Controls AdjudicationNot reportedAdjudication
Rater Population Domain ExpertsUnknownDomain Experts
Annotation Unit UnknownUnknownMulti Dim Rubric
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. CounselReflect: A Toolkit for Auditing Mental-Health Dialogues

    Start here for detailed protocol reporting and quality-control evidence. Signals: human evaluation + rubric ratings. Abstract: The system integrates two families of evaluation signals: (i) 12 model-based metrics.

  2. AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics. Focus: accuracy. Abstract: Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool.

  3. LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo

    High citation traction makes this a strong baseline for protocol comparison. Signals: simulation environments. Focus: Ludobench / dice. Abstract: We introduce LudoBench, a benchmark for evaluating LLM strategic.

  4. From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics. Focus: cost. Abstract: While Large Language Models (LLMs) have demonstrated exceptional proficiency in code.

  5. Vision-DeepResearch Benchmark: Rethinking Visual and Textual Search for Multimodal Large Language Models

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + expert verification. Focus: Vdr-Bench. Abstract: Multimodal Large Language Models (MLLMs) have advanced VQA and.

  6. When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation

    Adds simulation environments with critique/edit feedback for broader protocol coverage within this hub. Signals: simulation environments + critique/edit feedback. Focus: WebArena. Abstract: As LLM agents transition from short,.

  7. Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: accuracy. Abstract: We identify self-testing during generation as.

  8. Sabiá-4 Technical Report

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: accuracy. Abstract: The models were developed through a.

Known Limitations

Known Limitations

  • Only 18.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (18.2% 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

  • Expert Verification (2)
  • Pairwise Preference (2)
  • Critique Edit (1)
  • Rubric Rating (1)

Evaluation Modes

  • Automatic Metrics (8)
  • Simulation Env (2)
  • Human Eval (1)

Top Benchmarks

  • BIRD (1)
  • Interruptbench (1)
  • Ludobench (1)
  • Vdr Bench (1)

Top Metrics

  • Accuracy (4)
  • Cost (3)
  • Agreement (1)
  • Dice (1)

Rater Population Mix

  • Domain Experts (2)

Quality Controls

  • Adjudication (2)
Coverage diagnostics (sample-based): human-feedback 45.5% · benchmarks 36.4% · metrics 72.7% · quality controls 18.2%.

Top Papers

Related Hubs

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