Skip to content
← Back to explorer

HFEPX Hub

Critique Edit Or Demonstrations Papers

Updated from current HFEPX corpus (Apr 12, 2026). 131 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 131 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Simulation Env. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: GSM8K. 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: 131 Last published: Mar 22, 2026 Global RSS Tag RSS
Critique EditDemonstrations

Researcher Quick Triage

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

Analysis blocks below are computed from the currently loaded sample (60 of 131 total papers in this hub).

High-Signal Coverage

100.0%

60 / 60 sampled papers are not low-signal flagged.

Replication-Ready Set

7

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

  • 7 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 1 papers support judge-vs-human agreement analysis.
  • 4 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.

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 100% of papers report explicit human-feedback signals, led by demonstration data.
  • automatic metrics appears in 22.9% of papers in this hub.
  • GSM8K is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • 1 sampled papers report both human evaluation and LLM-as-judge, supporting direct agreement checks.
  • Most common quality-control signal is rater calibration (1.5% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.

Benchmark Interpretation

  • GSM8K appears in 1.5% of hub papers (2/131); use this cohort for benchmark-matched comparisons.
  • HotpotQA appears in 1.5% of hub papers (2/131); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 10.7% of hub papers (14/131); compare with a secondary metric before ranking methods.
  • cost is reported in 7.6% of hub papers (10/131); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (100% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (3.1% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (19.1% vs 35% target).

  • Moderate: Papers naming evaluation metrics

    Coverage is usable but incomplete (23.7% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (19.1% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (19.8% vs 35% target).

Strengths

  • Strong human-feedback signal (100% of papers).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.

Known Gaps

  • Only 3.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (19.1% coverage).
  • Annotation unit is under-specified (19.8% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (GSM8K vs HotpotQA) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
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
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Mar 22, 2026

Yes Human Eval , Llm As Judge WebArena , ToolBench Precision , Pass@1 Not Reported
HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Feb 15, 2026

Yes Automatic Metrics HLE Accuracy Adjudication
PAVE: Premise-Aware Validation and Editing for Retrieval-Augmented LLMs

Mar 21, 2026

Yes Automatic Metrics Post Retrieval Accuracy Not Reported
ReasonScaffold: A Scaffolded Reasoning-based Annotation Protocol for Human-AI Co-Annotation

Mar 22, 2026

Yes Automatic Metrics Not Reported Accuracy , Agreement Inter Annotator Agreement Reported
Can Large Language Models Replace Human Coders? Introducing ContentBench

Feb 23, 2026

Yes Automatic Metrics ContentBench Agreement , Cost Not Reported
PaperBanana: Automating Academic Illustration for AI Scientists

Jan 30, 2026

Yes Automatic Metrics Paperbananabench Faithfulness , Conciseness Not Reported
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
Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation

Mar 19, 2026

Yes Simulation Env Mapg Bench Not Reported Not Reported
RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

Mar 27, 2026

Yes Not Reported GSM8K Not Reported Not Reported
FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

Oct 2, 2025

Yes Automatic Metrics GSM8K Accuracy Not Reported
Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Jun 3, 2025

Yes Automatic Metrics AIME Pass@1 Not Reported
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization

Mar 30, 2026

Yes Not Reported Kernelbench Not Reported Not Reported

Protocol Diff (Top Papers)

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

Signal AgentHER: Hindsight Experience Replay for LLM Agent… HLE-Verified: A Systematic Verification and Structu… PAVE: Premise-Aware Validation and Editing for Retr…
Human Feedback DemonstrationsExpert Verification, Critique EditCritique Edit
Evaluation Modes Human Eval, Llm As JudgeAutomatic MetricsAutomatic Metrics
Benchmarks WebArena, ToolBenchHLEPost Retrieval
Metrics Precision, Pass@1AccuracyAccuracy
Quality Controls Not reportedAdjudicationNot reported
Rater Population UnknownDomain ExpertsUnknown
Annotation Unit TrajectoryUnknownUnknown
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. Cross-Cultural Expert-Level Art Critique Evaluation with Vision-Language Models

    Start here for detailed protocol reporting and quality-control evidence. Signals: rubric ratings. Abstract: Existing benchmarks assess perception without interpretation, and common evaluation proxies, such as automated metrics and.

  2. How Much LLM Does a Self-Revising Agent Actually Need?

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics + critique/edit feedback. Focus: f1. Abstract: Recent LLM-based agents often place world modeling, planning,.

  3. State-of-the-Art Arabic Language Modeling with Sparse MoE Fine-Tuning and Chain-of-Thought Distillation

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics + demonstration data. Focus: cost. Abstract: This paper introduces Arabic-DeepSeek-R1, an application-driven open-source Arabic.

  4. AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + demonstration data. Focus: WebArena / precision. Abstract: AgentHER realises this idea through a four-stage.

  5. IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation + pairwise preferences. Focus: Writingbench. Abstract: To address this gap, we curate a high-quality dataset.

  6. Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + rubric ratings. Focus: spearman. Abstract: The paradigm of LLM-as-a-judge relies on a critical assumption,.

  7. VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play

    Adds automatic metrics with demonstration data for broader protocol coverage within this hub. Signals: automatic metrics + demonstration data. Focus: win rate. Abstract: Robot sports, characterized by well-defined.

Known Limitations

Known Limitations

  • Only 3.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (19.1% 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

  • Demonstrations (69)
  • Critique Edit (63)
  • Pairwise Preference (9)
  • Rubric Rating (6)

Evaluation Modes

  • Automatic Metrics (30)
  • Simulation Env (15)
  • Human Eval (4)
  • Llm As Judge (3)

Top Benchmarks

  • GSM8K (2)
  • HotpotQA (2)
  • WebArena (2)
  • Windowsagentarena (2)

Top Metrics

  • Accuracy (14)
  • Cost (10)
  • Agreement (4)
  • Latency (3)

Rater Population Mix

  • Domain Experts (23)
  • Mixed (2)

Quality Controls

  • Calibration (2)
  • Adjudication (1)
  • Inter Annotator Agreement Reported (1)
Coverage diagnostics (sample-based): human-feedback 100.0% · benchmarks 31.7% · metrics 48.3% · quality controls 6.7%.

Top Papers

Related Hubs

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.
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.
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.