Skip to content
AI News HubLIVE
Original source2 min read

Third Eye: Beyond Immediate Gains in Recursive Self-Improvement

Summary

The arXiv paper 'Third Eye' argues that evaluating persistent self-updates requires looking beyond immediate performance to outcomes after further native updates. Across five 3-8B backbones on math and code, immediate-selected utility is near zero or negative, and continuation reduces it further; the authors recommend treating persistent self-updates as adaptation transitions with independent scoring and a no-update baseline.

SourcearXiv Machine LearningAuthor: Sujato Dutta, Padala Indira Sneha, Kypu Mahitha, Shashank Vanga, Neeraj Choudhary
Third Eye: Beyond Immediate Gains in Recursive Self-Improvement
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 8 Nov 2026]

Title:Third Eye: Beyond Immediate Gains in Recursive Self-Improvement

View a PDF of the paper titled Third Eye: Beyond Immediate Gains in Recursive Self-Improvement, by Sujato Dutta and 4 other authors

View PDF HTML (experimental)

Abstract:Does a useful self-update remain useful after the model updates again? Third Eye separates immediate performance from the outcome of a further native update. We evaluate five 3-8B backbones on math and code: 64 fresh runs, three candidates per run, and three continuations per candidate. Selection and final scoring use disjoint items. In the balanced Qwen3-4B/Llama-3.2-3B comparison, immediate-selected utility is near zero, but continuation reduces it by 1.78 percentage points (simultaneous 95% interval [0.68, 2.88]). Candidate-averaged immediate utility is already negative: selection partly accounts for the apparently neutral first step. Continuation also lowers utility for SmolLM3-3B and Llama-3.1-8B; Qwen3-8B remains inconclusive. Target and out-of-distribution losses dominate retention changes. Matched recipe and recipient-donor controls identify neither a reliable mitigation nor a single mechanism. The results support evaluating persistent self-updates as adaptation transitions, with independent scoring and a no-update baseline, rather than interpreting immediate performance as their full value.

Subjects:

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

Cite as: arXiv:2611.12988 [cs.LG]

(or arXiv:2611.12988v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2611.12988

arXiv-issued DOI via DataCite

Submission history

From: Sujato Dutta [view email] [v1] Sun, 8 Nov 2026 10:14:16 UTC (159 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Third Eye: Beyond Immediate Gains in Recursive Self-Improvement, by Sujato Dutta and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.LG

new | recent | 2026-11

Change to browse by:

cs cs.AI

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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

  • Third Eye separates immediate performance from the outcome of a further native update
  • In a balanced Qwen3-4B/Llama-3.2-3B comparison, candidate-averaged immediate utility is already negative, and continuation reduces utility by 1.78 percentage points
  • Continuation also lowers utility for SmolLM3-3B and Llama-3.1-8B, while Qwen3-8B remains inconclusive
  • Target and out-of-distribution losses dominate retention changes, and matched recipe and recipient-donor controls identify neither a reliable mitigation nor a single mechanism

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