Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

Structurally Aligned Subtask-Level Memory for Software Engineering Agents

Kangning Shen, Jingyuan Zhang, Chenxi Sun, Wencong Zeng +1 more

Published

Feb 25, 2026

Citations

0

Trust level

Moderate

Usefulness score

25/100 (Low)

Extraction confidence

50% (Moderate)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Feb 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

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning. However, these approaches typically operate at a coarse instance granularity, treating the entire problem-solving episode as the atomic unit of storage and retrieval. We empirically demonstrate that instance-level memory suffers from a fundamental granularity mismatch, resulting in misguided retrieval when tasks with similar surface descriptions require distinct reasoning logic at specific stages. To address this, we propose Structurally Aligned Subtask-Level Memory, a method that aligns memory storage, retrieval, and updating with the agent's functional decomposition. Extensive experiments on SWE-bench Verified demonstrate that our method consistently outperforms both vanilla agents and strong instance-level memory baselines across diverse backbones, improving mean Pass@1 over the vanilla agent by +4.7 pp on average (e.g., +6.8 pp on Gemini 2.5 Pro). Performance gains grow with more interaction steps, showing that leveraging past experience benefits long-horizon reasoning in complex software engineering tasks.

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.

"Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents."

Benchmarks / Datasets

strong

SWE Bench, Retrieval, Swe Bench

Useful for quick benchmark comparison.

"However, these approaches typically operate at a coarse instance granularity, treating the entire problem-solving episode as the atomic unit of storage and retrieval."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents."

Benchmarks and datasets

SWE-benchretrievalswe-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
Unit of annotation
Trajectory
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

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.

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

Key takeaways

  • Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.
  • Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.
  • However, these approaches typically operate at a coarse instance granularity, treating the entire problem-solving episode as the atomic unit of storage and retrieval.

Researcher actions

  • Compare this paper against others mentioning SWE-bench.
  • Validate inferred eval signals (Long-horizon tasks) against the full paper.
  • 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

SWE-bench

Contribution summary

  • Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.
  • Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.
  • However, these approaches typically operate at a coarse instance granularity, treating the entire problem-solving episode as the atomic unit of storage and retrieval.

Why it matters for eval

  • Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.
  • Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.

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: SWE-bench, retrieval, swe-bench

  • Metric reporting is present

    No metric terms extracted.