Skip to content
← Back to explorer

HFEPX Hub

CS.LG + Web Browsing Papers

Updated from current HFEPX corpus (Mar 8, 2026). 10 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Mar 8, 2026). 10 papers are grouped in this hub page. Common evaluation modes: Automatic Metrics, Llm As Judge. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Adjudication. Frequently cited benchmark: DROP. 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 Feb 16, 2026.

Papers: 10 Last published: Feb 16, 2026 Global RSS Tag RSS
Cs.LGWeb Browsing

Researcher Quick Triage

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

All Sampled Papers (10) Replication-Ready Only (1)

High-Signal Coverage

100.0%

10 / 10 sampled papers are not low-signal flagged.

Replication-Ready Set

1

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

0

Papers containing both `human_eval` and `llm_as_judge`.

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

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

Why This Matters For Eval Research

  • 37.5% of papers report explicit human-feedback signals, led by demonstration data.
  • automatic metrics appears in 50% of papers in this hub.
  • DROP is a recurring benchmark anchor for cross-paper comparisons in this page.

Protocol Takeaways

  • Most common quality-control signal is adjudication (10% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.

Benchmark Interpretation

  • DROP appears in 12.5% of hub papers (1/10); use this cohort for benchmark-matched comparisons.
  • Innoeval appears in 12.5% of hub papers (1/10); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 37.5% of hub papers (3/10); compare with a secondary metric before ranking methods.
  • f1 is reported in 12.5% of hub papers (1/10); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Moderate: Papers with explicit human feedback

    Coverage is usable but incomplete (37.5% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (12.5% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (25% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (62.5% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (12.5% vs 35% target).

  • Gap: Papers with known annotation unit

    Coverage is a replication risk (12.5% vs 35% target).

Strengths

  • Agentic evaluation appears in 100% of papers.

Known Gaps

  • Only 12.5% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12.5% coverage).
  • Annotation unit is under-specified (12.5% coverage).

Suggested Next Analyses

  • Pair this hub with a human_eval-heavy hub to validate judge-model calibration.
  • Stratify by benchmark (DROP vs Innoeval) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and f1.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

LLM-as-Judge Protocols Benchmark Slice: DROP Metric Slice: accuracy Recent High-Signal Papers

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
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

Feb 16, 2026

 No
Not Reported
Llm As Judge Innoeval Not Reported Adjudication
MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Mar 3, 2026

 Yes
Red Team
Automatic Metrics Not Reported Success rate , Jailbreak success rate Not Reported
SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

Feb 3, 2026

 No
Not Reported
Automatic Metrics DROP Accuracy Not Reported
TimeWarp: Evaluating Web Agents by Revisiting the Past

Mar 5, 2026

 Yes
Demonstrations
Not Reported Not Reported Not Reported Not Reported
A Benchmark for Deep Information Synthesis

Feb 24, 2026

 No
Not Reported
Automatic Metrics Not Reported F1 Not Reported
Replaying pre-training data improves fine-tuning

Mar 5, 2026

 No
Not Reported
Automatic Metrics Not Reported Accuracy 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
MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

Oct 21, 2025

 Yes
Demonstrations
Simulation Env Not Reported Not Reported Not Reported

Protocol Diff (Top Papers)

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

Signal InnoEval: On Research Idea Evaluation as a Knowledg… MUSE: A Run-Centric Platform for Multimodal Unified… SpatiaLab: Can Vision-Language Models Perform Spati…
Human Feedback Not reportedRed TeamNot reported
Evaluation Modes Llm As JudgeAutomatic MetricsAutomatic Metrics
Benchmarks InnoevalNot reportedDROP
Metrics Not reportedSuccess rate, Jailbreak success rateAccuracy
Quality Controls AdjudicationNot reportedNot reported
Rater Population Domain ExpertsUnknownUnknown
Annotation Unit UnknownUnknownUnknown
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. Replaying pre-training data improves fine-tuning

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics. Focus: accuracy. Abstract: To obtain a language model for a target domain (e.g.

  2. TimeWarp: Evaluating Web Agents by Revisiting the Past

    Start here for detailed protocol reporting and quality-control evidence. Signals: demonstration data. Abstract: The improvement of web agents on current benchmarks raises the question: Do today's agents perform.

  3. MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + red-team protocols. Focus: success rate. Abstract: We present MUSE (Multimodal Unified Safety Evaluation), an open-source,.

  4. InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: LLM-as-judge. Focus: Innoeval. Abstract: However, existing idea evaluation methods often suffer from narrow knowledge horizons, flattened evaluation.

  5. MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: simulation environments + demonstration data. Abstract: Imitation learning from large-scale, diverse human demonstrations has been shown to.

  6. SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?

    Adds automatic metrics for broader protocol coverage within this hub. Signals: automatic metrics. Focus: DROP / accuracy. Abstract: Spatial reasoning is a fundamental aspect of human cognition, yet.

  7. A Benchmark for Deep Information Synthesis

    Adds automatic metrics for broader protocol coverage within this hub. Signals: automatic metrics. Focus: f1. Abstract: When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research agents achieve.

  8. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

    Adds automatic metrics for broader protocol coverage within this hub. Signals: automatic metrics. Focus: accuracy. Abstract: Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation.

Known Limitations

Known Limitations

  • Only 12.5% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (12.5% 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 (2)
  • Red Team (1)

Evaluation Modes

  • Automatic Metrics (5)
  • Llm As Judge (1)
  • Simulation Env (1)

Top Benchmarks

  • DROP (1)
  • Innoeval (1)

Top Metrics

  • Accuracy (3)
  • F1 (1)
  • Jailbreak success rate (1)
  • Success rate (1)

Rater Population Mix

  • Domain Experts (1)

Quality Controls

  • Adjudication (1)
Coverage diagnostics (sample-based): human-feedback 30.0% · benchmarks 30.0% · metrics 50.0% · quality controls 10.0%.

Top Papers

Related Hubs

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

Post a Job Get a Quote