Skip to content
← Back to explorer

HFEPX Hub

Coding Papers (Last 45 Days)

Updated from current HFEPX corpus (Apr 17, 2026). 69 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 17, 2026). 69 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Multi Dim Rubric. Frequent quality control: Calibration. Frequently cited benchmark: SWE-bench. 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: 69 Last published: Mar 31, 2026 Global RSS Tag RSS
CodingLast 45d

Researcher Quick Triage

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

Analysis blocks below are computed from the currently loaded sample (60 of 69 total papers in this hub).

High-Signal Coverage

100.0%

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

Replication-Ready Set

15

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

  • 15 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 1 papers support judge-vs-human agreement analysis.
  • 5 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

  • 58% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 59.4% of papers in this hub.
  • SWE-bench is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is rater calibration (2.9% of papers).
  • Rater context is mostly domain experts, and annotation is commonly multi-dimensional rubrics; use this to scope replication staffing.
  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.

Benchmark Interpretation

  • SWE-bench appears in 2.9% of hub papers (2/69); use this cohort for benchmark-matched comparisons.
  • AIME appears in 1.4% of hub papers (1/69); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 33.3% of hub papers (23/69); compare with a secondary metric before ranking methods.
  • cost is reported in 21.7% of hub papers (15/69); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (58% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (7.2% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (26.1% 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 (15.9% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (36.2% vs 35% target).

Strengths

  • Strong human-feedback signal (58% of papers).
  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 49.3% of papers.

Known Gaps

  • Only 7.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (15.9% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (SWE-bench vs AIME) 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
Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers

Apr 1, 2026

Yes Automatic Metrics Paperwrite Bench Not Reported Not Reported
Do Phone-Use Agents Respect Your Privacy?

Apr 1, 2026

Yes Automatic Metrics APPS , Myphonebench Task success Not Reported
CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks

Mar 19, 2026

Yes Automatic Metrics Harmbench Not Reported Not Reported
Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

Mar 11, 2026

Yes Human Eval Rinobench Not Reported Gold Questions
StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning

Mar 3, 2026

Yes Automatic Metrics Kernelbench Success rate Not Reported
Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

Mar 16, 2026

Yes Automatic Metrics Esdr Bench Accuracy Not Reported
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

Yes Automatic Metrics SWE Bench , AIME Pass@1 Not Reported
Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith

Mar 25, 2026

No
Not Reported
Human Eval , Llm As Judge Not Reported Accuracy , Kappa Inter Annotator Agreement 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
VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents

Mar 25, 2026

Yes Simulation Env Vehiclemembench Not Reported Not Reported
CounselReflect: A Toolkit for Auditing Mental-Health Dialogues

Mar 31, 2026

Yes Human Eval Not Reported Not Reported Adjudication
PRBench: End-to-end Paper Reproduction in Physics Research

Mar 29, 2026

Yes Automatic Metrics , Simulation Env Not Reported Accuracy , Success rate Not Reported

Protocol Diff (Top Papers)

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

Signal Paper Reconstruction Evaluation: Evaluating Present… Do Phone-Use Agents Respect Your Privacy? CausalRM: Causal-Theoretic Reward Modeling for RLHF…
Human Feedback Rubric RatingPairwise PreferencePairwise Preference
Evaluation Modes Automatic MetricsAutomatic MetricsAutomatic Metrics
Benchmarks Paperwrite BenchAPPS, MyphonebenchHarmbench
Metrics Not reportedTask successNot reported
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownUnknownUnknown
Annotation Unit Multi Dim RubricUnknownUnknown
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. Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

    Start here for detailed protocol reporting and quality-control evidence. Signals: human evaluation + rubric ratings. Focus: Rinobench. Abstract: Yet, evaluation of these approaches remains largely inconsistent and is.

  3. The Detection-Extraction Gap: Models Know the Answer Before They Can Say It

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics. Focus: accuracy. Abstract: Modern reasoning models continue generating long after the answer is already.

  4. Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework

    High citation traction makes this a strong baseline for protocol comparison. Signals: automatic metrics. Focus: recall. Abstract: The rapid growth of scientific literature has made it increasingly difficult.

  5. 88cb4318-cbbe-4401-8783-da7d166744b9

    High citation traction makes this a strong baseline for protocol comparison.

  6. LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge. Focus: lit-ragbench / accuracy. Abstract: We use LLM-as-a-Judge for scoring and report category-wise and overall.

  7. 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,.

  8. VehicleMemBench: An Executable Benchmark for Multi-User Long-Term Memory in In-Vehicle Agents

    Adds simulation environments with pairwise preferences for broader protocol coverage within this hub. Signals: simulation environments + pairwise preferences. Focus: Vehiclemembench. Abstract: This evolution requires agents to continuously.

Known Limitations

Known Limitations

  • Only 7.2% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (15.9% 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 (18)
  • Rubric Rating (9)
  • Critique Edit (8)
  • Expert Verification (7)

Evaluation Modes

  • Automatic Metrics (41)
  • Human Eval (5)
  • Simulation Env (5)
  • Llm As Judge (3)

Top Benchmarks

  • SWE Bench (2)
  • AIME (1)
  • APPS (1)
  • BFCL (1)

Top Metrics

  • Accuracy (23)
  • Cost (15)
  • Agreement (3)
  • Latency (3)

Rater Population Mix

  • Domain Experts (10)
  • Mixed (1)

Quality Controls

  • Calibration (2)
  • Adjudication (1)
  • Gold Questions (1)
  • Inter Annotator Agreement Reported (1)
Coverage diagnostics (sample-based): human-feedback 53.3% · benchmarks 30.0% · metrics 75.0% · quality controls 8.3%.

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.