HFEPX Hub

Simulation Env Papers

Updated from current HFEPX corpus (Apr 12, 2026). 188 papers are grouped in this hub page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 188 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: 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: 188 Last published: Feb 15, 2026 Global RSS Tag RSS

Simulation Env

Researcher Quick Triage

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

Analysis blocks below are computed from the currently loaded sample (60 of 188 total papers in this hub).

All Sampled Papers (60) Replication-Ready Only (11)

High-Signal Coverage

100.0%

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

Replication-Ready Set

Benchmark + metric + eval mode explicitly present.

Judge/Human Comparability

Papers containing both `human_eval` and `llm_as_judge`.

11 papers are replication-ready (benchmark + metric + explicit evaluation mode).
1 papers support judge-vs-human agreement analysis.
2 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 (11 papers).

Need evaluators for this research workflow?

Post a Job →

Why This Matters For Eval Research

30% of papers report explicit human-feedback signals, led by demonstration data.
simulation environments appears in 63.8% 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 (0.5% 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 5% of hub papers (6/188); use this cohort for benchmark-matched comparisons.
WebArena appears in 4.2% of hub papers (5/188); use this cohort for benchmark-matched comparisons.

Metric Interpretation

accuracy is reported in 22.5% of hub papers (27/188); compare with a secondary metric before ranking methods.
cost is reported in 8.3% of hub papers (10/188); compare with a secondary metric before ranking methods.

Researcher Checklist (Expanded)

Researcher Checklist

Moderate: Papers with explicit human feedback

Coverage is usable but incomplete (30% vs 45% target).
Gap: Papers reporting quality controls

Coverage is a replication risk (1.7% vs 30% target).
Moderate: Papers naming benchmarks/datasets

Coverage is usable but incomplete (25.8% vs 35% target).
Strong: Papers naming evaluation metrics

Coverage is strong (50% vs 35% target).
Gap: Papers with known rater population

Coverage is a replication risk (12.5% vs 35% target).
Moderate: Papers with known annotation unit

Coverage is usable but incomplete (26.7% vs 35% target).

Strengths

Contains both human-eval and LLM-as-judge protocols for head-to-head methodology comparison.
Agentic evaluation appears in 66.7% of papers.

Known Gaps

Only 1.7% of papers report quality controls; prioritize calibration/adjudication evidence.
Rater population is under-specified (12.5% 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 accuracy and cost.
Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries (Expanded)

Recommended Queries

Judge vs Human Agreement Benchmark Slice: ALFWorld 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.

Strongest protocol reference

AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabe…

Highest protocol score with explicit human/eval signal plus WebArena.

Strongest benchmark reference

AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchm…

Ad-Bench with pass@1 gives a fast comparison anchor.

Strongest recent paper

AJAR: Adaptive Jailbreak Architecture for Red-teaming

Useful for current practice scanning; published Jan 16, 2026.

Start Here (Best First 6)

Ranked for protocol completeness (human signal, benchmark + metric anchors, quality controls, and judge/human overlap).

AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling
Mar 22, 2026 · Citations: 0 · Score: 10.0

HF: Demonstrations · Eval: Human Eval, Llm As Judge · Benchmark: WebArena · Metric: Precision
AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
Feb 15, 2026 · Citations: 0 · Score: 7.5

HF: Expert Verification · Eval: Simulation Env · Benchmark: Ad Bench · Metric: Pass@1
AJAR: Adaptive Jailbreak Architecture for Red-teaming
Jan 16, 2026 · Citations: 0 · Score: 7.5

HF: Red Team · Eval: Simulation Env · Benchmark: Harmbench · Metric: Success rate
Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
Jul 15, 2025 · Citations: 0 · Score: 6.5

HF: Pairwise Preference · Eval: Automatic Metrics, Simulation Env · Benchmark: VisualWebArena · Metric: Accuracy
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
Oct 5, 2025 · Citations: 0 · Score: 6.5

HF: Rubric Rating · Eval: Automatic Metrics, Simulation Env · Benchmark: AIME · Metric: Accuracy
ReDAct: Uncertainty-Aware Deferral for LLM Agents
Apr 8, 2026 · Citations: 0 · Score: 6.0

HF: Not reported · Eval: Simulation Env · Benchmark: ALFWorld · Metric: Cost

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
AJAR: Adaptive Jailbreak Architecture for Red-teaming Jan 16, 2026	Yes Red Team	Simulation Env	Harmbench	Success rate , Jailbreak success rate	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
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation Oct 5, 2025	Yes Rubric Rating	Automatic Metrics , Simulation Env	AIME	Accuracy , Pass@k	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
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo Apr 7, 2026	No Not Reported	Simulation Env	Ludobench	Dice	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
BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion Mar 10, 2026	No Not Reported	Automatic Metrics , Simulation Env	BIRD	Accuracy	Not Reported
Go-Browse: Training Web Agents with Structured Exploration Jun 4, 2025	No Not Reported	Simulation Env	WebArena	Success rate	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…	AJAR: Adaptive Jailbreak Architecture for Red-teami…
Human Feedback	Demonstrations	Expert Verification	Red Team
Evaluation Modes	Human Eval, Llm As Judge	Simulation Env	Simulation Env
Benchmarks	WebArena, ToolBench	Ad Bench	Harmbench
Metrics	Precision, Pass@1	Pass@1, Pass@3	Success rate, Jailbreak success rate
Quality Controls	Not reported	Not reported	Not reported
Rater Population	Unknown	Domain Experts	Unknown
Annotation Unit	Trajectory	Trajectory	Unknown

Research Utility Snapshot

Human Feedback Mix

Demonstrations (12)
Pairwise Preference (9)
Rubric Rating (6)
Expert Verification (4)

Evaluation Modes

Simulation Env (120)
Automatic Metrics (31)
Llm As Judge (7)
Human Eval (4)

Top Benchmarks

ALFWorld (6)
WebArena (5)
OSWorld (3)
WebShop (3)

Top Metrics

Accuracy (27)
Cost (10)
Success rate (8)
Coherence (4)

Rater Population Mix

Domain Experts (14)
Mixed (1)

Quality Controls

Adjudication (1)
Calibration (1)

Coverage diagnostics (sample-based): human-feedback 60.0% · benchmarks 41.7% · metrics 50.0% · quality controls 3.3%.

Top Papers

AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
Lingxiang Hu, Yiding Sun, Tianle Xia, Wenwei Li, Ming Xu · Feb 15, 2026 · Citations: 0

Expert Verification Simulation Env Long Horizon

While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem.
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…
Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification
Moises Andrade, Joonhyuk Cha, Brandon Ho, Vriksha Srihari, Karmesh Yadav · Jul 15, 2025 · Citations: 0

Pairwise Preference Automatic MetricsSimulation Env Long Horizon

We evaluate MLLM verifiers across web navigation, computer use, and robotics, spanning 13+ models, 28+ designs, and thousands of trajectories from diverse agents.
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
Mohsen Hariri, Amirhossein Samandar, Michael Hinczewski, Vipin Chaudhary · Oct 5, 2025 · Citations: 0

Rubric Rating Automatic MetricsSimulation Env

We present a principled Bayesian evaluation framework that replaces Pass@k and average accuracy over N trials (avg@N) with posterior estimates of a model's underlying success probability and credible intervals, yielding stable rankings and…
AJAR: Adaptive Jailbreak Architecture for Red-teaming
Yipu Dou, Wang Yang · Jan 16, 2026 · Citations: 0

Red Team Simulation Env

Large language model (LLM) safety evaluation is moving from content moderation to action security as modern systems gain persistent state, tool access, and autonomous control loops.
ReDAct: Uncertainty-Aware Deferral for LLM Agents
Dzianis Piatrashyn, Nikita Kotelevskii, Kirill Grishchenkov, Nikita Glazkov, Ivan Nasonov · Apr 8, 2026 · Citations: 0

Simulation Env Long Horizon

Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems.
Embodied Task Planning via Graph-Informed Action Generation with Large Language Model
Xiang Li, Ning Yan, Masood Mortazavi · Jan 29, 2026 · Citations: 0

Simulation Env Long Horizon

We propose GiG, a novel planning framework that structures embodied agents' memory using a Graph-in-Graph architecture.
Go-Browse: Training Web Agents with Structured Exploration
Apurva Gandhi, Graham Neubig · Jun 4, 2025 · Citations: 0

Simulation Env Web Browsing

To address this, we propose Go-Browse, a method for automatically collecting diverse and realistic web agent data at scale through structured exploration of web environments.
DeceptGuard :A Constitutional Oversight Framework For Detecting Deception in LLM Agents
Snehasis Mukhopadhyay · Mar 14, 2026 · Citations: 0

Automatic MetricsSimulation Env Long Horizon

We introduce DECEPTGUARD, a unified framework that systematically compares three monitoring regimes: black-box monitors (actions and outputs only), CoT-aware monitors (additionally observing the agent's chain-of-thought reasoning trace),…
BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion
Xinyu Gao, Gang Chen, Javier Alonso-Mora · Mar 10, 2026 · Citations: 0

Automatic MetricsSimulation Env Web Browsing

As a result, they struggle to infer target locations in occluded regions, typically caused by furniture or moving humans.
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo
Ojas Jain, Dhruv Kumar · Apr 7, 2026 · Citations: 0

Simulation Env Multi Agent

We introduce LudoBench, a benchmark for evaluating LLM strategic reasoning in Ludo, a stochastic multi-agent board game whose dice mechanics, piece capture, safe-square navigation, and home-path progression introduce meaningful planning…

Related Hubs

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

Post a Job Get a Quote