Skip to content
← Back to explorer

HFEPX Benchmark Hub

Coding Evaluation Suite Benchmark Papers In CS.CL

Updated from current HFEPX corpus (Mar 17, 2026). 10 papers are grouped in this benchmark page.

Read Full Context

Updated from current HFEPX corpus (Mar 17, 2026). 10 papers are grouped in this benchmark page. Common evaluation modes: Automatic Metrics, Human Eval. Most common rater population: Domain Experts. Common annotation unit: Pairwise. Frequent quality control: Calibration. Frequently cited benchmark: LiveCodeBench. 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 18, 2026.

Papers: 10 Last published: Feb 18, 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%

10 / 10 sampled papers are not low-signal flagged.

Replication-Ready Set

4

Papers with explicit benchmark + metric + eval mode fields.

Quality Controls

10.0%

1 papers report calibration/adjudication/IAA controls.

  • 9 papers explicitly name benchmark datasets in the sampled set.
  • 5 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

  • 77.8% of papers report explicit human-feedback signals, led by pairwise preferences.
  • automatic metrics appears in 40% of papers in this hub.
  • LiveCodeBench 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 (10% of papers).
  • Rater context is mostly domain experts, and annotation is commonly pairwise annotation; use this to scope replication staffing.
  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.

Benchmark Interpretation

  • LiveCodeBench appears in 55.6% of hub papers (5/10); use this cohort for benchmark-matched comparisons.
  • APPS appears in 33.3% of hub papers (3/10); use this cohort for benchmark-matched comparisons.

Metric Interpretation

  • cost is reported in 22.2% of hub papers (2/10); compare with a secondary metric before ranking methods.
  • accuracy is reported in 11.1% of hub papers (1/10); 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
$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners

Mar 4, 2026

Automatic Metrics Pairwise Preference Pass@1 Not reported
Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences

Feb 25, 2026

Automatic Metrics Pairwise Preference Accuracy Not reported
Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling

Feb 18, 2026

Not reported Expert Verification Not reported Calibration
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

Feb 11, 2026

Not reported Pairwise Preference Latency, Cost Not reported
RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration

Feb 26, 2026

Automatic Metrics Not reported Cost Not reported
Think$^{2}$: Grounded Metacognitive Reasoning in Large Language Models

Feb 21, 2026

Human Eval Pairwise Preference Not reported Not reported
The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Oct 29, 2025

Automatic Metrics Not reported Success rate Not reported
Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning

Sep 26, 2025

Not reported Critique Edit Not reported Not reported
EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation

May 29, 2024

Human Eval Pairwise Preference Not reported Not reported
Distribution-Aware Companding Quantization of Large Language Models

Feb 27, 2026

Not reported Not reported Not reported Not reported
Researcher Workflow (Detailed)

Checklist

  • Strong: Papers with explicit human feedback

    Coverage is strong (77.8% vs 45% target).

  • Gap: Papers reporting quality controls

    Coverage is a replication risk (11.1% vs 30% target).

  • Strong: Papers naming benchmarks/datasets

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

  • Strong: Papers naming evaluation metrics

    Coverage is strong (55.6% vs 35% target).

  • Moderate: Papers with known rater population

    Coverage is usable but incomplete (22.2% vs 35% target).

  • Moderate: Papers with known annotation unit

    Coverage is usable but incomplete (22.2% vs 35% target).

Strengths

  • Strong human-feedback signal (77.8% of papers).
  • Most papers provide measurable evaluation context (100% benchmarks, 55.6% metrics).
  • Agentic evaluation appears in 44.4% of papers.

Known Gaps

  • Only 11.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (22.2% coverage).
  • Annotation unit is under-specified (22.2% coverage).

Suggested Next Analyses

  • Pair this hub with llm_as_judge pages to benchmark automated-vs-human evaluation tradeoffs.
  • Stratify by benchmark (LiveCodeBench vs APPS) before comparing methods.
  • Track metric sensitivity by reporting both cost and accuracy.
  • Add inter-annotator agreement checks when reproducing these protocols.

Recommended Queries

Known Limitations
  • Only 11.1% of papers report quality controls; prioritize calibration/adjudication evidence.
  • Rater population is under-specified (22.2% 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 (4)
  • Human Eval (2)

Human Feedback Mix

  • Pairwise Preference (5)
  • Critique Edit (1)
  • Expert Verification (1)

Top Benchmarks

  • LiveCodeBench (5)
  • APPS (3)
  • AIME (2)
  • BrowseComp (1)

Top Metrics

  • Cost (2)
  • Accuracy (1)
  • Latency (1)
  • Pass@1 (1)

Top Papers On This Benchmark

Related Benchmark Hubs

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