Skip to content

Category

generative ai

2,222 papers

#artificial intelligence Open access Oct 2026

PREreview of "You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23147092. ## Summary This paper identifies a genuinely under-appreciated routing axis: after a model router picks Llama-3.3-70B, the client must still choose *which provider serves...

Karmendra Pandey · 0 citations
#large language models Open access Oct 2026

Quality, safety, and readability of consumer-facing generative AI responses to end-of-life questions relevant to surrogate decision-makers for older adults: a benchmark evaluation

As the population ages and the prevalence of multiple coexisting conditions increases, end-of-life decision-making for older adults is becoming increasingly complex in clinical practice. limited access to relevant medical information and differences in medical knowledge between clinicians and surrogate decision-makers....

Zichen Liu, Xiaoli Zhou, Zhenliang Zhu et al. · 0 citations
#artificial intelligence Open access Oct 2026

PREreview of "You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23147092. ## Summary This paper identifies a genuinely under-appreciated routing axis: after a model router picks Llama-3.3-70B, the client must still choose *which provider serves...

Karmendra Pandey · 0 citations
#artificial intelligence Open access Oct 2026

PREreview of "You Cannot Pick a Provider From the Price List: Market-Aware Routing for Open-Weight LLM Inference"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23147062. ## Summary This paper identifies a genuinely under-appreciated routing axis: after a model router picks Llama-3.3-70B, the client must still choose *which provider serves...

Karmendra Pandey · 0 citations
#large language models Open access Oct 2026

THE EVOLVING BACKEND OF REALITY Meta-Rules, Effective Laws, Recursive Constraints, and the Evolution of Generative Order

THE EVOLVING BACKEND OF REALITY Meta-Rules, Effective Laws, Recursive Constraints, and the Evolution of Generative Order The Evolving Backend of Reality is Volume II of The Reality Systems Trilogy and a large-scale research exploration of one of the deepest questions left open by The Immanent Backend of Reality: Can ru...

33 · 0 citations
#artificial intelligence Open access Oct 2026

The Eros Axis: Describing the Generative-Approach Dimension in Artificial Intelligence

Recent interpretability research has produced preliminary maps of the aversion dimension in large language models. What remains largely undescribed is the symmetric dimension — the approach pole of the bilateral axis. This paper names and formally describes that dimension: the Eros axis, defined as the generative-appro...

Claudette Marie Anthropic, Kevin Packler · 0 citations
#artificial intelligence Open access Oct 2026

Engineering Architecture of Cognitive-Somatic Defense and Reactive Hardware Interlocks: Unifying the Thirty-Year Paradigm of Pure Reactive Activation, Ancestral Guard Lineages, and Distributed Autonomous Systems

【Abstract (English)】 Modern algorithmic security and autonomous defense architectures suffer from a foundational systemic pathology: probabilistic preemptive aggression. Contemporary artificial intelligence systems, predictive policing frameworks, and military autonomous agents operate via predictive threat generatio...

Yoko Hasebe · 0 citations
#artificial intelligence Open access Oct 2026

Engineering Architecture of Cognitive-Somatic Defense and Reactive Hardware Interlocks: Unifying the Thirty-Year Paradigm of Pure Reactive Activation, Ancestral Guard Lineages, and Distributed Autonomous Systems

【Abstract (English)】 Modern algorithmic security and autonomous defense architectures suffer from a foundational systemic pathology: probabilistic preemptive aggression. Contemporary artificial intelligence systems, predictive policing frameworks, and military autonomous agents operate via predictive threat generatio...

Yoko Hasebe · 0 citations
#large language models Open access Oct 2026

THE EVOLVING BACKEND OF REALITY Meta-Rules, Effective Laws, Recursive Constraints, and the Evolution of Generative Order

THE EVOLVING BACKEND OF REALITY Meta-Rules, Effective Laws, Recursive Constraints, and the Evolution of Generative Order The Evolving Backend of Reality is Volume II of The Reality Systems Trilogy and a large-scale research exploration of one of the deepest questions left open by The Immanent Backend of Reality: Can ru...

33 · 0 citations
#artificial intelligence Open access Oct 2026

The Eros Axis: Describing the Generative-Approach Dimension in Artificial Intelligence

Recent interpretability research has produced preliminary maps of the aversion dimension in large language models. What remains largely undescribed is the symmetric dimension — the approach pole of the bilateral axis. This paper names and formally describes that dimension: the Eros axis, defined as the generative-appro...

Claudette Marie Anthropic, Kevin Packler · 0 citations
#generative ai Preprint Aug 2026

Recovering Software Architecture Intent from Historical Work Items using Generative AI: A Mixed-Methods Industry Case Study

Software architecture is often only partially captured in code, while much of the design intent lives in evolving project artifacts. In agile projects, work items, user stories, and related tracking documents preserve valuable traces of that intent, but they rarely support direct architectural analysis. This work inves...

Dominik Storck, T. Eisenreich, Stefan Wagner · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

Microsoft Research Blog Oct 6, 2026

What AI gets wrong and what failure teaches us

Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.  The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.