Skip to content
← Back to explorer

HFEPX Hub

CS.AI + Demonstrations Papers

Updated from current HFEPX corpus (Apr 9, 2026). 48 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 9, 2026). 48 papers are grouped in this hub page. Common evaluation modes: Simulation Env, Automatic Metrics. Most common rater population: Domain Experts. Common annotation unit: Trajectory. Frequent quality control: Calibration. Frequently cited benchmark: Windowsagentarena. Common metric signal: cost. 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: 48 Last published: Mar 22, 2026 Global RSS Tag RSS
Cs.AIDemonstrations

Researcher Quick Triage

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

All Sampled Papers (48) Replication-Ready Only (1)

High-Signal Coverage

100.0%

48 / 48 sampled papers are not low-signal flagged.

Replication-Ready Set

1

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

  • 1 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 1 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.

Currently showing only replication-ready papers in ranking and matrix sections (1 papers).

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.
  • simulation environments appears in 20.8% of papers in this hub.
  • Windowsagentarena 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 (2.1% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.

Benchmark Interpretation

  • Windowsagentarena appears in 4.2% of hub papers (2/48); use this cohort for benchmark-matched comparisons.
  • ALFWorld appears in 2.1% of hub papers (1/48); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • cost is reported in 8.3% of hub papers (4/48); compare with a secondary metric before ranking methods.
  • precision is reported in 4.2% of hub papers (2/48); 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 (2.1% vs 30% target).

  • Gap: Papers naming benchmarks/datasets

    Coverage is a replication risk (16.7% vs 35% target).

  • Gap: Papers naming evaluation metrics

    Coverage is a replication risk (18.8% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (20.8% vs 35% target).

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (22.9% 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.
  • Agentic evaluation appears in 31.3% of papers.

Known Gaps

  • Only 2.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (20.8% coverage).
  • Annotation unit is under-specified (22.9% coverage).

Suggested Next Analyses

  • Compare papers that report both human_eval and llm_as_judge to quantify judge-human agreement drift.
  • Stratify by benchmark (Windowsagentarena vs ALFWorld) before comparing methods.
  • Track metric sensitivity by reporting both cost and precision.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

Judge vs Human Agreement Benchmark Slice: Windowsagentarena Metric Slice: cost 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
AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

Mar 22, 2026

 Yes
Demonstrations
Human Eval , Llm As Judge WebArena , ToolBench Precision , Pass@1 Not Reported
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads

    Start here for detailed protocol reporting and quality-control evidence. Signals: demonstration data. Abstract: In-Context Learning (ICL) has been extensively studied in text-only Language Models, but remains largely unexplored.

  2. Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis

    Start here for detailed protocol reporting and quality-control evidence. Signals: demonstration data. Abstract: This paper presents epistemic blinding in the context of an agentic system that uses large.

  3. A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems

    Start here for detailed protocol reporting and quality-control evidence. Signals: demonstration data. Focus: precision. Abstract: Robotic automation has transformed scientific workflows in domains such as chemistry and materials.

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

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: automatic metrics + demonstration data. Focus: win rate. Abstract: Robot sports, characterized by well-defined objectives, explicit rules,.

  6. Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation

    Adds simulation environments with demonstration data for broader protocol coverage within this hub. Signals: simulation environments + demonstration data. Focus: Mapg-Bench. Abstract: Robots collaborating with humans must convert.

  7. RAPTOR: A Foundation Policy for Quadrotor Control

    Adds simulation environments with demonstration data for broader protocol coverage within this hub. Signals: simulation environments + demonstration data. Abstract: Humans are remarkably data-efficient when adapting to new.

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

    Adds simulation environments with demonstration data for broader protocol coverage within this hub. Signals: simulation environments + demonstration data. Abstract: Imitation learning from large-scale, diverse human demonstrations has.

Known Limitations

Known Limitations

  • Only 2.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (20.8% 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 (48)
  • Pairwise Preference (3)
  • Rubric Rating (1)

Evaluation Modes

  • Simulation Env (10)
  • Automatic Metrics (8)
  • Human Eval (1)
  • Llm As Judge (1)

Top Benchmarks

  • Windowsagentarena (2)
  • ALFWorld (1)
  • DROP (1)
  • GPQA (1)

Top Metrics

  • Cost (4)
  • Precision (2)
  • Win rate (2)
  • Accuracy (1)

Rater Population Mix

  • Domain Experts (9)
  • Mixed (1)

Quality Controls

  • Calibration (1)
Coverage diagnostics (sample-based): human-feedback 100.0% · benchmarks 16.7% · metrics 18.8% · quality controls 2.1%.

Top Papers

  • AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling

    Liang Ding · Mar 22, 2026 · Citations: 0

    Demonstrations Human EvalLlm As Judge Long Horizon

    LLM agents fail on the majority of real-world tasks -- GPT-4o succeeds on fewer than 15% of WebArena navigation tasks and below 55% pass@1 on ToolBench (Zhou et al., 2024; Qin et al., 2024) -- yet every failed trajectory is routinely…

Related Hubs

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

Post a Job Get a Quote