Skip to content
← Back to explorer

HFEPX Benchmark Hub

AIME Or SWE-bench Or WebArena Benchmark Papers

Updated from current HFEPX corpus (Apr 17, 2026). 38 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Apr 17, 2026). 38 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequently cited benchmark: AIME. Common metric signal: pass@1. 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: 38 Last published: Mar 22, 2026 Global RSS

Researcher Quick Triage

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

High-Signal Coverage

100.0%

38 / 38 sampled papers are not low-signal flagged.

Replication-Ready Set

9

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

0.0%

0 papers report calibration/adjudication/IAA controls.

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

Primary action: Start with the top 2 benchmark-matched papers, then compare evaluation modes in the protocol matrix.

Why This Matters (Expanded)

Why This Matters For Eval Research

  • 53.3% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 21.1% of papers in this hub.
  • AIME 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

  • AIME appears in 40% of hub papers (6/38); use this cohort for benchmark-matched comparisons.
  • SWE-bench appears in 33.3% of hub papers (5/38); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • pass@1 is reported in 33.3% of hub papers (5/38); compare with a secondary metric before ranking methods.
  • accuracy is reported in 20% of hub papers (3/38); 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
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

 Automatic Metrics Pairwise Preference Pass@1 Not reported
GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA

Oct 27, 2025

 Automatic Metrics Pairwise Preference Mse Not reported
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation

Oct 5, 2025

 Automatic Metrics, Simulation Env Rubric Rating Accuracy, Pass@k Not reported
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Jun 3, 2025

 Automatic Metrics Critique Edit Pass@1 Not reported
Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis

Mar 23, 2026

 Automatic Metrics Not reported Accuracy, Recall Not reported
When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation

Apr 1, 2026

 Simulation Env Critique Edit Not reported Not reported
SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents

Feb 25, 2026

 Automatic Metrics Not reported Pass@1, Latency Not reported
KLong: Training LLM Agent for Extremely Long-horizon Tasks

Feb 19, 2026

 Not reported Rubric Rating Not reported Not reported
Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models

Feb 21, 2026

 Human Eval Pairwise Preference Not reported Not reported
Researcher Workflow (Detailed)

Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (53.3% 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 (66.7% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (6.7% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (46.7% vs 35% target).

Strengths

  • Strong human-feedback signal (53.3% of papers).
  • Most papers provide measurable evaluation context (100% benchmarks, 66.7% 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.
  • Rater population is under-specified (6.7% coverage).
  • 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 (AIME vs SWE-bench) before comparing methods.
  • Track metric sensitivity by reporting both pass@1 and accuracy.

Recommended Queries

Judge vs Human AgreementBenchmark Slice: AIMEMetric Slice: pass@1Recent High-Signal Papers
Known Limitations
  • Only 0% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (6.7% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Evaluation Modes

  • Automatic Metrics (8)
  • Simulation Env (6)
  • Human Eval (2)
  • Llm As Judge (2)

Human Feedback Mix

  • Pairwise Preference (3)
  • Critique Edit (2)
  • Rubric Rating (2)
  • Demonstrations (1)

Top Benchmarks

  • AIME (6)
  • SWE Bench (5)
  • WebArena (5)
  • SWE Bench Verified (4)

Top Metrics

  • Pass@1 (5)
  • Accuracy (3)
  • Cost (2)
  • Auroc (1)

Top Papers On This Benchmark

Related Benchmark Hubs

AIME Or SWE-bench Benchmark Papers AIME Or WebArena Benchmark Papers AIME Or SWE-bench Or GPQA Benchmark Papers AIME Or SWE-bench Or MATH-500 Benchmark Papers AIME Or SWE-bench Or AlpacaEval Benchmark Papers AIME Or GPQA Or WebArena Benchmark Papers MATH-500 Or GPQA Benchmark Papers (20) MMLU Or AIME Or AlpacaEval Benchmark Papers (48) MMLU Or AIME Or GPQA Benchmark Papers (42) GSM8K Or MMLU Or AIME Benchmark Papers (57) MMLU Or AIME Or MATH-500 Benchmark Papers (46) MMLU Or AIME Or SWE-bench Benchmark Papers (51) MMLU Or AIME Benchmark Papers (39) MMLU Or AlpacaEval Or GPQA Benchmark Papers (39) GSM8K Or MMLU Or AlpacaEval Benchmark Papers (51) MMLU Or MATH-500 Or AlpacaEval Benchmark Papers (44) MMLU Or SWE-bench Or AlpacaEval Benchmark Papers (45) MMLU Or AlpacaEval Benchmark Papers (32) GSM8K Or MMLU Or GPQA Benchmark Papers (48) MMLU Or MATH-500 Or GPQA Benchmark Papers (39) MMLU Or SWE-bench Or GPQA Benchmark Papers (42) MMLU Or GPQA Benchmark Papers (29) GSM8K Or MMLU Or MATH-500 Benchmark Papers (50) GSM8K Or MMLU Or SWE-bench Benchmark Papers (55)
Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now