Skip to content
← Back to explorer

HFEPX Hub

Long Horizon + Simulation Env Papers

Updated from current HFEPX corpus (Apr 12, 2026). 42 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 42 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: Adjudication. Frequently cited benchmark: ALFWorld. 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 Feb 15, 2026.

Papers: 42 Last published: Feb 15, 2026 Global RSS Tag RSS
Long HorizonSimulation Env

Researcher Quick Triage

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

All Sampled Papers (42) Replication-Ready Only (6)

High-Signal Coverage

100.0%

42 / 42 sampled papers are not low-signal flagged.

Replication-Ready Set

6

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

1

Papers containing both `human_eval` and `llm_as_judge`.

  • 6 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: 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 (6 papers).

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

  • 26.2% of papers report explicit human-feedback signals, led by pairwise preferences.
  • simulation environments appears in 100% of papers in this hub.
  • ALFWorld 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 adjudication (2.4% of papers).
  • Rater context is mostly domain experts, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.

Benchmark Interpretation

  • ALFWorld appears in 9.5% of hub papers (4/42); use this cohort for benchmark-matched comparisons.
  • WebArena appears in 9.5% of hub papers (4/42); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • cost is reported in 11.9% of hub papers (5/42); compare with a secondary metric before ranking methods.
  • pass@1 is reported in 9.5% of hub papers (4/42); compare with a secondary metric before ranking methods.
Researcher Checklist (Expanded)

Researcher Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (26.2% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (2.4% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

    Coverage is strong (40.5% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (42.9% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (2.4% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (57.1% vs 35% target).

Strengths

  • Most papers provide measurable evaluation context (40.5% benchmarks, 42.9% metrics).
  • 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 2.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (2.4% 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 (ALFWorld vs WebArena) before comparing methods.
  • Track metric sensitivity by reporting both cost and pass@1.
  • Add inter-annotator agreement checks when reproducing these protocols.
Recommended Queries (Expanded)

Recommended Queries

Judge vs Human Agreement Benchmark Slice: ALFWorld 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
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

Feb 15, 2026

 Yes
Expert Verification
Simulation Env Ad Bench Pass@1 , Pass@3 Not Reported
Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

Jul 15, 2025

 Yes
Pairwise Preference
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
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… AD-Bench: A Real-World, Trajectory-Aware Advertisin… Let's Think in Two Steps: Mitigating Agreement Bias…
Human Feedback DemonstrationsExpert VerificationPairwise Preference
Evaluation Modes Human Eval, Llm As JudgeSimulation EnvAutomatic Metrics, Simulation Env
Benchmarks WebArena, ToolBenchAd BenchVisualWebArena, OSWorld
Metrics Precision, Pass@1Pass@1, Pass@3Accuracy
Quality Controls Not reportedNot reportedNot reported
Rater Population UnknownDomain ExpertsUnknown
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. Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces

    Start here for detailed protocol reporting and quality-control evidence. Signals: simulation environments. Abstract: The emergence of Large Language Models (LLMs) has illuminated the potential for a general-purpose user.

  2. ReDAct: Uncertainty-Aware Deferral for LLM Agents

    Start here for detailed protocol reporting and quality-control evidence. Signals: simulation environments. Focus: ALFWorld / cost. Abstract: Recently, LLM-based agents have become increasingly popular across many applications, including.

  3. From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems

    Start here for detailed protocol reporting and quality-control evidence. Signals: simulation environments. Abstract: While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains.

  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. FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health

    Include a human-eval paper to calibrate against judge-based evaluation settings. Signals: human evaluation. Abstract: Human evaluation further confirms that FrameRef's generated framings measurably affect human judgment.

  6. 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.

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

    Adds simulation environments with expert verification for broader protocol coverage within this hub. Signals: simulation environments + expert verification. Focus: Ad-Bench / pass@1. Abstract: While Large Language Model.

  8. 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 2.4% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (2.4% 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 (5)
  • Demonstrations (4)
  • Critique Edit (1)
  • Expert Verification (1)

Evaluation Modes

  • Simulation Env (42)
  • Automatic Metrics (4)
  • Llm As Judge (3)
  • Human Eval (2)

Top Benchmarks

  • ALFWorld (4)
  • WebArena (4)
  • OSWorld (3)
  • WebShop (2)

Top Metrics

  • Cost (5)
  • Pass@1 (4)
  • Accuracy (3)
  • Coherence (2)

Rater Population Mix

  • Domain Experts (1)

Quality Controls

  • Adjudication (1)
Coverage diagnostics (sample-based): human-feedback 26.2% · benchmarks 40.5% · metrics 40.5% · quality controls 2.4%.

Top Papers

Related Hubs

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

Post a Job Get a Quote