Skip to content
← Back to explorer

HFEPX Benchmark Hub

WebArena Ecosystem Benchmark Papers In CS.AI

Updated from current HFEPX corpus (Apr 9, 2026). 19 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Apr 9, 2026). 19 papers are grouped in this benchmark page. Common evaluation modes: Simulation Env, Automatic Metrics. Most common rater population: Domain Experts. Common annotation unit: Trajectory. 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 Mar 22, 2026.

Papers: 19 Last published: Mar 22, 2026 Global RSS

Researcher Quick Triage

Use this page for benchmark-matched method comparisons and eval protocol selection. Quality band: Developing .

High-Signal Coverage

100.0%

19 / 19 sampled papers are not low-signal flagged.

Replication-Ready Set

3

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

0.0%

0 papers report calibration/adjudication/IAA controls.

  • 9 papers explicitly name benchmark datasets in the sampled set.
  • 5 papers report at least one metric term in metadata extraction.
  • Start with the ranked shortlist below before reading all papers.

Primary action: Use this page to map benchmark mentions first; wait for stronger metric/QC coverage before strict comparisons.

Why This Matters (Expanded)

Why This Matters For Eval Research

  • 50% of papers report explicit human-feedback signals, led by demonstration data.
  • simulation environments appears in 36.8% of papers in this hub.
  • BrowseComp is a recurring benchmark anchor for cross-paper comparisons in this page.
Protocol Notes (Expanded)

Protocol Takeaways

  • 1 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • 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 trajectory-level annotation; use this to scope replication staffing.

Benchmark Interpretation

  • BrowseComp appears in 30% of hub papers (3/19); use this cohort for benchmark-matched comparisons.
  • OSWorld appears in 30% of hub papers (3/19); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 20% of hub papers (2/19); compare with a secondary metric before ranking methods.
  • cost is reported in 20% of hub papers (2/19); compare with a secondary metric before ranking methods.

Start Here (Benchmark-Matched First 6)

Ranked by protocol completeness so you can quickly find papers suitable for comparison studies.

Protocol Matrix (Top 10)

Compare protocol ingredients quickly before deep-reading full papers.

Paper Eval Modes Human Feedback Metrics Quality Controls
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Mar 22, 2026

 Human Eval, Llm As Judge Demonstrations Precision, Pass@1 Not reported
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Feb 11, 2026

 Not reported Pairwise Preference Latency, Cost Not reported
Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

Jul 15, 2025

 Automatic Metrics, Simulation Env Pairwise Preference Accuracy Not reported
Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning

Aug 26, 2025

 Automatic Metrics Not reported F1 Not reported
Watch and Learn: Learning to Use Computers from Online Videos

Oct 6, 2025

 Not reported Demonstrations Not reported Not reported
Structured Agent Distillation for Large Language Model

May 20, 2025

 Simulation Env Demonstrations Not reported Not reported
World-Model-Augmented Web Agents with Action Correction

Feb 17, 2026

 Llm As Judge, Simulation Env Not reported Not reported Not reported
Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks

Feb 26, 2026

 Simulation Env Not reported Not reported Not reported
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents

Feb 15, 2026

 Simulation Env Not reported Not reported Not reported
BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

Feb 13, 2026

 Automatic Metrics, Simulation Env Not reported Accuracy Not reported
Researcher Workflow (Detailed)

Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (50% 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 (100% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (50% vs 35% target).

  • Moderate: Papers with known rater population

    Coverage is usable but incomplete (30% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (50% vs 35% target).

Strengths

  • Strong human-feedback signal (50% of papers).
  • Most papers provide measurable evaluation context (100% benchmarks, 50% metrics).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.

Known Gaps

  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • LLM-as-judge appears without enough inter-annotator agreement reporting.

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (BrowseComp vs OSWorld) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.

Recommended Queries

Judge vs Human AgreementBenchmark Slice: BrowseCompMetric Slice: accuracyRecent High-Signal Papers
Known Limitations
  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • LLM-as-judge appears without enough inter-annotator agreement reporting.
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Evaluation Modes

  • Simulation Env (7)
  • Automatic Metrics (3)
  • Llm As Judge (2)
  • Human Eval (1)

Human Feedback Mix

  • Demonstrations (3)
  • Pairwise Preference (2)

Top Benchmarks

  • BrowseComp (3)
  • OSWorld (3)
  • ALFWorld (2)
  • VisualWebArena (2)

Top Metrics

  • Accuracy (2)
  • Cost (2)
  • Agreement (1)
  • F1 (1)

Top Papers On This Benchmark

Related Benchmark Hubs

WebArena Ecosystem Benchmark Papers CS.AI Human Feedback And Eval Papers BrowseComp In CS.AI Papers CS.AI Papers (Last 60 Days) CS.AI Papers (Last 90 Days) WebArena Ecosystem Benchmark Papers In CS.CL GSM8K Or MMLU Or AIME Benchmark Papers (39) MMLU Or AIME Or SWE-bench Benchmark Papers (37) MMLU Or AIME Benchmark Papers (27) GSM8K Or MMLU Or SWE-bench Benchmark Papers (39) GSM8K Or MMLU Benchmark Papers (28) MMLU Or SWE-bench Benchmark Papers (25) MMLU In CS.CL Papers (12) MMLU Benchmark Papers (Last 120 Days) (11) MMLU Benchmark Papers (Last 150 Days) (11) MMLU Benchmark Papers (Last 180 Days) (12) MMLU Benchmark Papers (Last 240 Days) (14) MMLU Benchmark Papers (Last 300 Days) (14) MMLU Benchmark Papers (Last 365 Days) (14) MMLU Benchmark Papers (Last 45 Days) (11) MMLU Benchmark Papers (Last 60 Days) (11) MMLU Benchmark Papers (Last 75 Days) (11) MMLU Benchmark Papers (Last 90 Days) (11) MMLU Benchmark Papers (14)

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

Post a Job Get a Quote