Skip to content
← Back to explorer

HFEPX Hub

Long Horizon Papers

Updated from current HFEPX corpus (Apr 12, 2026). 324 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 324 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 Feb 15, 2026.

Papers: 324 Last published: Feb 15, 2026 Global RSS Tag RSS
Long Horizon

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 324 total papers in this hub).

High-Signal Coverage

100.0%

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

Replication-Ready Set

13

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

  • 13 papers are replication-ready (benchmark + metric + explicit evaluation mode).
  • 1 papers support judge-vs-human agreement analysis.
  • 6 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.

Currently showing only replication-ready papers in ranking and matrix sections (13 papers).

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 23.2% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 45.4% 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 (1.2% 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 4.3% of hub papers (9/324); use this cohort for benchmark-matched comparisons.
  • OSWorld appears in 2.4% of hub papers (5/324); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 37.4% of hub papers (79/324); compare with a secondary metric before ranking methods.
  • cost is reported in 17.1% of hub papers (36/324); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (23.2% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.8% vs 30% target).

  • Moderate: Papers naming benchmarks/datasets

    Coverage is usable but incomplete (31.8% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (76.3% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (10% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (51.2% vs 35% target).

Strengths

  • Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
  • Agentic evaluation appears in 100% of papers.

Known Gaps

  • Only 2.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (10% 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 (GSM8K vs OSWorld) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.
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
TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

Apr 8, 2026

Yes Automatic Metrics Tracesafe Bench Accuracy Not Reported
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

Feb 15, 2026

Yes Simulation Env Ad Bench Pass@1 , Pass@3 Not Reported
\$OneMillion-Bench: How Far are Language Agents from Human Experts?

Mar 9, 2026

Yes Automatic Metrics Onemillion Bench Accuracy , Coherence Not Reported
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

Jan 17, 2026

Yes Automatic Metrics Calconflictbench Error rate Not Reported
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

Mar 19, 2026

No
Not Reported
Automatic Metrics GSM8K Accuracy , Calibration error Calibration
Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

Jul 15, 2025

Yes Automatic Metrics , Simulation Env VisualWebArena , OSWorld Accuracy Not Reported
ReDAct: Uncertainty-Aware Deferral for LLM Agents

Apr 8, 2026

No
Not Reported
Simulation Env ALFWorld Cost , Token cost Not Reported
DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents

Mar 14, 2026

No
Not Reported
Automatic Metrics , Simulation Env Deceptarena Faithfulness Not Reported
DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling

Apr 7, 2026

No
Not Reported
Human Eval Insightbench Recall Not Reported
Beyond Rows to Reasoning: Agentic Retrieval for Multimodal Spreadsheet Understanding and Editing

Mar 6, 2026

No
Not Reported
Human Eval , Automatic Metrics Frtr Bench Accuracy , Cost Not Reported
Embodied Task Planning via Graph-Informed Action Generation with Large Language Model

Jan 29, 2026

No
Not Reported
Simulation Env ALFWorld Pass@1 , Cost 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… TraceSafe: A Systematic Assessment of LLM Guardrail… AD-Bench: A Real-World, Trajectory-Aware Advertisin…
Human Feedback DemonstrationsRed TeamExpert Verification
Evaluation Modes Human Eval, Llm As JudgeAutomatic MetricsSimulation Env
Benchmarks WebArena, ToolBenchTracesafe BenchAd Bench
Metrics Precision, Pass@1AccuracyPass@1, Pass@3
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownUnknownDomain Experts
Annotation Unit TrajectoryTrajectoryTrajectory
Suggested Reading Order (Extended)

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

Suggested Reading Order

  1. Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification

    Start here for detailed protocol reporting and quality-control evidence. Signals: automatic metrics + expert verification. Focus: brier score. Abstract: As LLM-powered agents have been used for high-stakes decision-making,.

  2. 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.

  3. AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: simulation environments + expert verification. Focus: Ad-Bench / pass@1. Abstract: While Large Language Model (LLM) agents have.

  4. Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

    Include an LLM-as-judge paper to test judge design and agreement assumptions. Signals: LLM-as-judge + pairwise preferences. Abstract: Grocery shopping further amplifies these difficulties, as user requests are often.

  5. Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

    Adds automatic metrics with pairwise preferences for broader protocol coverage within this hub. Signals: automatic metrics + pairwise preferences. Focus: VisualWebArena / accuracy. Abstract: Multimodal LLMs (MLLMs) offer.

Known Limitations

Known Limitations

  • Only 2.8% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (10% 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 (23)
  • Demonstrations (10)
  • Rubric Rating (8)
  • Expert Verification (6)

Evaluation Modes

  • Automatic Metrics (147)
  • Simulation Env (42)
  • Llm As Judge (7)
  • Human Eval (5)

Top Benchmarks

  • GSM8K (9)
  • OSWorld (5)
  • ALFWorld (4)
  • WebArena (4)

Top Metrics

  • Accuracy (79)
  • Cost (36)
  • Latency (15)
  • Recall (12)

Rater Population Mix

  • Domain Experts (21)

Quality Controls

  • Calibration (4)
  • Adjudication (2)
Coverage diagnostics (sample-based): human-feedback 63.3% · benchmarks 43.3% · metrics 58.3% · quality controls 10.0%.

Top Papers

Related Hubs

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