Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering

Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang +1 more

Published

Feb 8, 2026

Citations

0

Trust level

Moderate

Usefulness score

25/100 (Low)

Extraction confidence

55% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Mar 25, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics Coding Long Horizon

Should you rely on this paper?

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Use this for comparison and orientation, not as your only source.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Main weakness

No major weakness surfaced.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
25/100
Adjacent candidate

Treat as adjacent context, not a core eval-method reference.

If you are doing eval pipeline work, start here

Human Eval Papers LLM-as-Judge Papers Pairwise Preference Papers Tool-Use Evaluation Search

Abstract

Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons. While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters. Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection. Recognizing these challenges, we propose AceGRPO with two core components: (1) Evolving Data Buffer that continuously repurposes execution traces into reusable training tasks, and (2) Adaptive Sampling guided by a Learnability Potential function, which dynamically prioritizes tasks at the agent's learning frontier to maximize learning efficiency. Leveraging AceGRPO, our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines (e.g., DeepSeek-V3.2), demonstrating robust capability for sustained iterative optimization. Code is available at https://github.com/yuzhu-cai/AceGRPO.

What we could verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

missing

None explicit

No explicit feedback protocol extracted.

"Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons."

Benchmarks / Datasets

strong

Mle Bench

Useful for quick benchmark comparison.

"Leveraging AceGRPO, our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines (e.g., DeepSeek-V3.2), demonstrating robust capability for sustained iterative optimization."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons."

Benchmarks and datasets

mle-bench

Reported metrics

No metric terms were extracted from the available abstract.

Human feedback details
Uses human feedback
No
Feedback types
None
Rater population
Not reported
Expertise required
Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
Long Horizon
Quality controls
Not reported
Evidence quality
Moderate
Use this page as
Background context only

Research brief

Metadata summary

Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key takeaways

  • Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.
  • While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters.
  • Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection.

Researcher actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended queries

Contribution summary

  • Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.
  • While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters.
  • Although Reinforcement Learning (RL) offers a remedy, applying it to MLE is hindered by prohibitive execution latency and inefficient data selection.

Why it matters for eval

  • Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.
  • While recent LLM-based agents show promise, current prompt-based agents for MLE suffer from behavioral stagnation due to frozen parameters.

Researcher checklist

  • Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Evaluation mode is explicit

    Detected: Automatic Metrics

  • Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Benchmark or dataset anchors are present

    Detected: mle-bench

  • Metric reporting is present

    No metric terms extracted.