Skip to content
AI News HubLIVE
Original source2 min read

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

Summary

GUARD is a closed-loop, grader-free framework that enables continual evolution of an AI agent's editable harness by decomposing tasks into pre-execution self-checks and using directional regret to guide updates, avoiding catastrophic forgetting and memory bloat while cutting token usage.

SourcearXiv AIAuthor: Minghe Zhang, Xuetao Kang, Yifei Ming, Yanfei Chen, Han Yu, Yufan Zhuang, Chen-Yu Lee
GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 17 Nov 2026]

Title:GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

View a PDF of the paper titled GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance, by Minghe Zhang and 6 other authors

View PDF HTML (experimental)

Abstract:Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing without external graders often backfires: reflection and scalar scores conflate what an edit newly broke with what remains unsolved, causing local regressions, skill forgetting, and memory bloat. We introduce GUARD (Grader-free Unsupervised Environment Design [UED] with Adaptive Rule Distillation), a closed-loop framework for reference-free continual harness evolution. Our key insight is to decompose each task into pre-execution self-checks and guide harness updates via directional regret. Each round grades trajectories against these checks, pinning mastered rules while prioritizing newly broken behaviors, and selects among parallel candidate edits by critic-free group-relative fitness. A Soft-HURT gate then promotes an edit only when gains outweigh regressions, scoping specialized fixes to prevent over-triggering and guaranteeing non-regression on its gated buffer. At test time, one frozen harness runs in a single pass. Across benchmarks on memory, skill evolution, continual task streams, and domain reasoning, GUARD consistently improves performance without catastrophic forgetting or memory pollution while substantially cutting deployment token usage.

Comments: Equal contribution: Minghe Zhang and Xuetao Kang. 38 pages, 8 figures, 13 tables

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as: arXiv:2611.23476 [cs.AI]

(or arXiv:2611.23476v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.23476

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Minghe Zhang [view email] [v1] Tue, 17 Nov 2026 20:26:34 UTC (508 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance, by Minghe Zhang and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.AI

new | recent | 2026-11

Change to browse by:

cs cs.LG

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Decomposes tasks into pre-execution self-checks and uses directional regret to separate newly broken behaviors from unsolved ones.
  • Selects among parallel candidate edits via critic-free group-relative fitness, with a Soft-HURT gate ensuring gains outweigh regressions.
  • Consistently improves performance on memory, skill evolution, continual task streams, and domain reasoning benchmarks while reducing deployment token usage.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance | AI News Hub