Skip to content
OpenTrain AIFor AI Companies

HFEPX · Eval paper review

EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful Evolver

Dastin Huang, Baran Nama, Salaheddin Alzubi

Published

Oct 19, 2026

Citations

0

Trust level

Low

Usefulness score

5/100 (Low)

Extraction confidence

45% (Low)

Derived from extracted protocol signals and abstract evidence.

Rater population

Not reported

Signals refreshed

Oct 19, 2026

Open arXiv Find implementation Shortlist (0) RSS feed

Tags

Automatic Metrics

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 as background context only. Do not make protocol decisions from this page alone.

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

This paper looks adjacent to evaluation work, but not like a strong protocol reference.

Human feedback signal
Not explicit
Not explicit in abstract metadata
Evaluation signal
Detected
Eval setup described
Usefulness for eval research
5/100
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

EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact. The user starts a run by describing a benchmark and supplying a grader, which a benchmark adaptor turns into a benchmark-specific plugin. A solver attempts the tasks, and an evolver reads the solver's training rollouts and rewrites the skills at each epoch. We implement the evolver as one stateful coding agent with a bash tool for the whole run, unlike the two most common designs among the skill optimizers we surveyed: a sequence of single model calls, as in SkillOpt, and an agent that starts afresh each round, as in SkillBoost. We also measure how much the solver's rollouts vary from one attempt to the next, give the evolver several attempts per training task, and accept every epoch's skills instead of selecting among them on noisy scores. With fine-grained ground truth, EvoSkill v2's skills raised the held-out pass rate above the stronger of SkillOpt and SkillBoost by 7.7 percentage points on SpreadsheetBench v2 and by 5.4 on $τ^3$-bench banking. In both benchmarks and both feedback settings, EvoSkill v2's evolver cost less per percentage point of held-out pass rate gained than either baseline's optimizer. EvoSkill v2 also enables a less capable model to improve its own skills, demonstrated by a gain of up to 21.5 percentage points in the $τ^3$-bench banking experiment where Claude Haiku 5.5 powers both solver and evolver.

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.

"EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact."

Evaluation Modes

partial

Automatic Metrics

Includes extracted eval setup.

"EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact."

Quality Controls

missing

Not reported

No explicit QC controls found.

"EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact."

Benchmarks / Datasets

partial

Spreadsheetbench

Useful for quick benchmark comparison.

"With fine-grained ground truth, EvoSkill v2's skills raised the held-out pass rate above the stronger of SkillOpt and SkillBoost by 7.7 percentage points on SpreadsheetBench v2 and by 5.4 on $τ^3$-bench banking."

Reported Metrics

missing

Not extracted

No metric anchors detected.

"EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact."

Benchmarks and datasets

Spreadsheetbench

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 (inferred)
Expertise required
Coding
Evaluation details
Evaluation modes
Automatic Metrics
Agentic eval
None
Quality controls
Not reported
Evidence quality
Low
Use this page as
Background context only

Research brief

Metadata summary

EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact.

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

Key takeaways

  • EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact.
  • The user starts a run by describing a benchmark and supplying a grader, which a benchmark adaptor turns into a benchmark-specific plugin.
  • A solver attempts the tasks, and an evolver reads the solver's training rollouts and rewrites the skills at each epoch.

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

  • EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact.
  • The user starts a run by describing a benchmark and supplying a grader, which a benchmark adaptor turns into a benchmark-specific plugin.
  • We implement the evolver as one stateful coding agent with a bash tool for the whole run, unlike the two most common designs among the skill optimizers we surveyed: a sequence of single model calls, as in SkillOpt, and an agent that starts…

Why it matters for eval

  • EvoSkill v2 is a three-agent system that edits the instructions (skills) an agent is given, leaving its model and harness intact.
  • The user starts a run by describing a benchmark and supplying a grader, which a benchmark adaptor turns into a benchmark-specific plugin.

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: Spreadsheetbench

  • Metric reporting is present

    No metric terms extracted.