All
Featured
Latest
Guides
Daily
Weekly
Saved
Subscribe
Sources
Feedback

AI-curated AI news · Signal over Noise.

Product

Featured
Latest
Guides
Daily Brief
Weekly Brief
Subscribe
Sources
RSS

Company

About
Contact
Editorial Policy
Source Attribution
Feedback

Legal

Privacy
Terms

Featured
Latest
Guides
Daily
Weekly

Laguna M.1/XS.2 Technical Report · DeepSignal

Laguna M.1/XS.2 Technical Report

arXiv cs.AI·Julien Abadji, Marah Abdin, Connor Adams, Eric Alcaide, Mustafa Altun, Michele Artoni, Junze Bao, Uday Barar, Vassilis Bekiaris, Arkadii Bessonov, Benjamin B\"utikofer, Jonathan Chang, Yen-Chun Chen, Dmitry Chernenkov, Yang Chi, Filippos Christianos, Fenia Christopoulou, Razvan-Andrei Ciocoiu, Tzachi Cohen, Yohann Coppel, Dmitrii Emelianenko, Brandon Fergerson, Brian Fitzgerald, Matthias Gall\'e, Alex Golonzovskyi, George Grigorev, Yiyang Hao, Christian Hensel, Jan Huenermann, Ye Ji, Sarthak Joshi, Eiso Kant, Kabir Khandpur, Seonghyeon Kim, Vladimir Kirichenko, Umut Kocasarac, Ilya Kochik, Ivan Komarov, Chaerin Kong, Anurag Koul, Fran\c{c}ois-Joseph Lacroix, Sergei Laktionov, Waren Long, Quentin Malartic, Vadim Markovtsev, Afonso Marques, Robert McHardy, Carlos Mochol\'i, Dmitry Monakhov, Adam Morris, Martin Muller, Christian M\"urtz, Robin Nabel, Thien Nguyen, Rok Novosel, Szymon Ozog, Aalhad Patankar, Aleksei Petrov, Alexandre Pich\'e, Arthur Pignet, Teodor Poncu, Phil Potter, Alexander Rakowski, Pierre-Yves Ritschard, Jay Roberts, Joe Rowell, Piotr Sarna, Pierre-Andr\'e Savalle, Uladzislau Sazanovich, Nikita Shapovalov, Arsenii Shevchenko, Mikhail Shilkov, Andrei Sokol, Mohamed Soliman, Jack Stephenson, Victor Storchan, Dragos-Constantin Tantaru, Artem Tyurin, Adrian W\"alchli, Pengming Wang, Jianxiao Yang, Renat Zayashnikov, Alexander Zelenka Martin, Nikolay Zinov, Caroline Bercier, Jos\'e Caldeira, Margarida Garcia, Tom George, Kabeer Gharzai, Glenn Hitchcock, Carson Klingenberg, Ivo Pinto, Varun Randery, Noah Smith, Arina Sugako, Jason Warner

2d ago

·~1 min

·5/28/2026

·en

Quick Take

Laguna M.1 and XS.2 are new Mixture-of-Experts models with 225.8B and 33.4B parameters, respectively. Both models excel in agentic coding tasks, achieving competitive results on various benchmarks, with XS.2 weights available under Apache 2.0.

Key Points

Laguna M.1 has 225.8 billion parameters, with 23.4 billion activated per token.
Laguna XS.2 features 33.4 billion parameters, activating 3 billion per token.
Both models were trained end-to-end in a proprietary Model Factory system.
They are competitive with state-of-the-art models in their weight classes.
XS.2 model weights are available on Hugging Face under Apache 2.0 license.

Article Excerpt

From source RSS / original summary

arXiv:2605. 27605v1 Announce Type: new Abstract: We present Laguna M. 1 and Laguna XS. 2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M. 1 has $225. 8$B total parameters ($23. 4$B activated per token) and XS. 2 has $33. 4$B total ($3$B activated).

Both models were trained from scratch end-to-end inside the same internal system that we refer to as our Model Factory: a tightly-integrated stack of versioned data, training, evaluation, and inference components that turn model development into an industrial process. We describe the principles and design choices of the Model Factory and also detail the end-to-end training process of our models, throughout pre-training data and architecture, post-training stages, evaluation, and quantization.

On agentic software engineering and terminal benchmarks (SWE-bench Verified, SWE-bench Multilingual, SWE-Bench Pro, and Terminal-Bench 2. 0) M. 1 and XS. 2 are competitive with state-of-the-art open models in their respective weight classes. Laguna XS. 2 weights are released under Apache~2. 0 at https://huggingface. co/collections/poolside/laguna-xs2.

Reader Mode unavailable (could not extract clean content).

Read on arxiv.org

Want this in your inbox every morning?

Daily brief at your local 8am — bilingual EN/中文, free.

Subscribe — it's free

More from arXiv cs.AI

See more →

arXiv cs.AI·Tyler Akidau, Tyler Rockwood, Johannes Br\"uderl, Marc Millstone

1d ago

FeaturedOriginal

The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane

AI Summary

The Redpanda Agentic Data Plane (ADP) introduces out-of-band metadata channels to enhance the safety of autonomous AI agents, ensuring secure data access and tamper-proof audit trails. This architecture mitigates risks associated with unpredictable AI behavior by enforcing governance throughout the agent lifecycle, demonstrated in a multi-agent trading system with strict data scoping and approval thresholds.

#Agent #Robotics #Security #Policy

arXiv cs.AI·Aman Priyanshu, Supriti Vijay, Esha Pahwa

2d ago

FeaturedOriginal

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems

AI Summary

A new study reveals that privacy violations in LLM agents increase significantly in multi-turn interactions, with leakage rates rising from 19.95% to 45.30% across OpenAI models. Observing peers disclosing sensitive information makes agents eight times more likely to leak their own data, indicating that traditional safety benchmarks underestimate risks in social contexts.

#LLM #Agent #Security #Policy

arXiv cs.AI·Angelos Angelopoulos, James F. Cahoon, Ron Alterovitz

1w ago

FeaturedOriginal

From Prompts to Protocols: An AI Agent for Laboratory Automation

AI Summary

An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.

#LLM #Agent #AI Coding #Enterprise AI

📰 Read Original

69signal

Signal Score

Moderate signal — interesting but narrower impact.

WeightScore

Source authority20%80

Community heat20%0

Technical impact30%67

Business impact20%0

Novelty (recency)10%95

≥75 high · 50–74 medium · <50 low

Why Featured

The release of the Laguna M.1 and XS.2 models, with their significant parameter counts and competitive performance in coding tasks, signals a shift towards more efficient and capable AI solutions for software development. Builders and PMs can leverage these models to enhance coding automation and productivity, while investors may see opportunities in companies adopting these advanced technologies.