Skip to content
← Back to explorer

HFEPX Benchmark Hub

Reasoning & Math Suite Benchmark Papers + Long Horizon

Updated from current HFEPX corpus (Apr 12, 2026). 11 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Apr 12, 2026). 11 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics. 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 Mar 19, 2026.

Papers: 11 Last published: Mar 19, 2026 Global RSS

Researcher Quick Triage

Use this page for benchmark-matched method comparisons and eval protocol selection. Quality band: Developing .

High-Signal Coverage

100.0%

11 / 11 sampled papers are not low-signal flagged.

Replication-Ready Set

10

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

9.1%

1 papers report calibration/adjudication/IAA controls.

  • 11 papers explicitly name benchmark datasets in the sampled set.
  • 10 papers report at least one metric term in metadata extraction.
  • Start with the ranked shortlist below before reading all papers.

Primary action: Start with the top 2 benchmark-matched papers, then compare evaluation modes in the protocol matrix.

Why This Matters (Expanded)

Why This Matters For Eval Research

  • 9.1% of papers report explicit human-feedback signals, led by critique/edit feedback.
  • automatic metrics appears in 90.9% of papers in this hub.
  • GSM8K is a recurring benchmark anchor for cross-paper comparisons in this page.
Protocol Notes (Expanded)

Protocol Takeaways

  • Most common quality-control signal is rater calibration (9.1% of papers).
  • Rater context is mostly unspecified rater pools, and annotation is commonly trajectory-level annotation; use this to scope replication staffing.
  • Stratify by benchmark (GSM8K vs MATH-500) before comparing methods.

Benchmark Interpretation

  • GSM8K appears in 81.8% of hub papers (9/11); use this cohort for benchmark-matched comparisons.
  • MATH-500 appears in 27.3% of hub papers (3/11); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • accuracy is reported in 63.6% of hub papers (7/11); compare with a secondary metric before ranking methods.
  • cost is reported in 45.5% of hub papers (5/11); compare with a secondary metric before ranking methods.

Start Here (Benchmark-Matched First 6)

Ranked by protocol completeness so you can quickly find papers suitable for comparison studies.

Protocol Matrix (Top 10)

Compare protocol ingredients quickly before deep-reading full papers.

Paper Eval Modes Human Feedback Metrics Quality Controls
Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

Mar 19, 2026

Automatic Metrics Not reported Accuracy, Calibration error Calibration
Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents

Apr 9, 2026

Automatic Metrics Not reported Accuracy Not reported
S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models

Apr 1, 2026

Automatic Metrics Not reported Pass@1, Cost Not reported
Top-b: Entropic Regulation of Relative Probability Bands in Autoregressive Language Processes

Mar 15, 2026

Automatic Metrics Not reported Accuracy Not reported
RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

Mar 27, 2026

Not reported Critique Edit Not reported Not reported
Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning

Mar 9, 2026

Automatic Metrics Not reported Accuracy, Cost Not reported
D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models

Feb 25, 2026

Automatic Metrics Not reported Accuracy Not reported
The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Jan 21, 2026

Automatic Metrics Not reported Accuracy Not reported
Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs

Dec 3, 2025

Automatic Metrics Not reported Cost Not reported
SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling

Jun 18, 2025

Automatic Metrics Not reported Accuracy, Precision Not reported
Researcher Workflow (Detailed)

Checklist

  • Gap: Papers with explicit human feedback

    Coverage is a replication risk (9.1% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (9.1% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

    Coverage is strong (100% vs 35% target).

  • Strong: Papers naming evaluation metrics

    Coverage is strong (90.9% vs 35% target).

  • Gap: Papers with known rater population

    Coverage is a replication risk (0% vs 35% target).

  • Strong: Papers with known annotation unit

    Coverage is strong (90.9% vs 35% target).

Strengths

  • Most papers provide measurable evaluation context (100% benchmarks, 90.9% metrics).
  • Agentic evaluation appears in 100% of papers.

Known Gaps

  • Only 9.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (0% coverage).

Suggested Next Analyses

  • Stratify by benchmark (GSM8K vs MATH-500) before comparing methods.
  • Track metric sensitivity by reporting both accuracy and cost.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 9.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (0% coverage).
  • Narrative synthesis is grounded in metadata and abstracts only; full-paper implementation details are not parsed.
Research Utility Snapshot (Detailed)

Evaluation Modes

  • Automatic Metrics (10)

Human Feedback Mix

  • Critique Edit (1)

Top Benchmarks

  • GSM8K (9)
  • MATH 500 (3)
  • GPQA (2)
  • MMLU (2)

Top Metrics

  • Accuracy (7)
  • Cost (5)
  • Inference cost (2)
  • Agreement (1)

Top Papers On This Benchmark

Related Benchmark Hubs

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.