Skip to content

Category

generative ai

2,222 papers

#generative ai Open access Oct 2026

PREreview of "Self-Correcting Multimodal AI Agents for Reliable Autonomous Decision-Making"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23121066. Peer Review Preprint Title: Self-Correcting Multimodal AI Agents for Reliable Autonomous Decision-Making Authors: Muhammad Umair Younus, Hammad Muneer, Danial Hameed, and...

Jr. Julian Rodriguez · 0 citations
#generative ai Open access Oct 2026

Two Algebraic Thresholds for Relaxations of Stable Metric TSP

Bilu–Linial stability asks whether an optimal solution remains uniquely optimal after every independent multiplicative increase of the input costs by a prescribed factor. For symmetric metric TSP, every 1.8-stable instance is solvable in polynomial time, and both the subtour relaxation and the weaker degree-only cycle-...

Sungsoo Na · 0 citations
#generative ai Open access Oct 2026

Machine Learning – Supported Pedagogy in Computer Engineering: A Proposed Framework for Learner Modeling, Adaptive Support, and Controlled Empirical Evaluation

Computer Engineering courses combine programming, digital logic, mathematics, and hardware laboratories, so students often progress unevenly and instructors have little time for individual feedback. Machine Learning (ML) has recently been explored to predict student performance, personalize learning support, and provid...

Hillary Mae De Guzman · 0 citations
#data science Dataset Open access Oct 2026

Replication Data for: Assessment over Interactive Learning: What Generative AI and ChatGPT Research in Education Prioritises across OpenAlex, Scopus, and Web of Science, 2022-2025

This repository contains the complete replication data, query strings, automated classification outputs, and validation kit for the study: Assessment over Interactive Learning: What Generative AI and ChatGPT Research in Education Prioritises across OpenAlex, Scopus, and Web of Science, 2022-2025Target journal: Interact...

Unais Ali, Syeda Kashaf Kulsoom · 0 citations
#generative ai Open access Oct 2026

What Must Remain Human? Rethinking Business Education for 2030: A Collective Article by the Business Physics AI Lab

Abstract: Generative and agentic artificial intelligence (AI) can now produce market analyses, forecasts, and client presentations in minutes. Polished output therefore reveals little about what a business student understands. This conceptual article asks which human capabilities business education must deliberately de...

Thomas Hormaza Dow, Vinay Kumar, Sébastien Favre et al. · 0 citations
#generative ai Open access Oct 2026

PREreview of "Psychosexual Rehabilitation After Cancer: A Narrative Review of the Intervention Evidence and a Stepped-Care Model for Survivorship Practice"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/23121600. Summary of main findings and contribution This narrative review focuses on an important question: how psychosexual rehabilitation after cancer can be delivered at scale, r...

Ghadeer Asarwi · 0 citations
#generative ai Open access Oct 2026

Weak separation and finite-trace coding: independence of infinite fin-intersecting MAD families

We prove that, under s < ap, an almost disjoint family is fin-intersecting exactly when its cardinality is less than s. A uniform finite-trace coding lemma and complementary splitting labels exclude every sufficiently large candidate, including every infinite MAD family. Together with the published Banakh, Machura and...

Haoxuan Ye · 0 citations
#generative ai Open access Oct 2026

Contract-Preserving Lower-to-Upper Recalibration in Hierarchical Agent Systems: An Integrated Framework

Soft and Hard De-Attraction (SHDA) specifies when verified lower-level recovery can support an upper-level revision without changing the external success contract. This condition is the framework's central axis, contract-preserving correctability: the joint condition, over separately judged coordinates, under which ver...

Bin Seol · 0 citations
#generative ai Open access Oct 2026

Intervention-Disclosure Visibility and Time-Bounded Selective Nondisclosure in Hierarchical Agent Systems

Within Soft and Hard De-Attraction (SHDA), this paper treats intervention disclosure in persistent-state artificial agents as an observer-field-channel-time contract. It separates assignment, valid delivery, existence awareness and field knowledge, records missing measurement as UNKNOWN, and distinguishes disclosure-po...

Bin Seol · 0 citations
#generative ai Open access Oct 2026

Residual Genesis and Dynamic Feedback Route Attribution in Hierarchical Recalibration

Within Soft and Hard De-Attraction (SHDA), cross-level residual differences can arise from observation, translation, weighting and selection as well as state deviations. This paper separates residual values from routes that change future data and specifies model-conditional partial identification of residual sources wi...

Bin Seol · 0 citations
#generative ai Open access Oct 2026

Authority, Typed Lineage, and Atomic Re-entry in Contract-Preserving Recalibration

Within Soft and Hard De-Attraction (SHDA), this paper separates the truth of operational objects from authority to act and specifies a quarantine, review and re-entry lifecycle for persistent-state artificial agents. Re-entry authority is conferred only at a linearizable commit that consumes the reservation and nonce;...

Bin Seol · 0 citations
#generative ai Open access Oct 2026

Paper B: Field Baseline Results. Does presentation format affect blind entity retrieval and brand attribution in production generative engines?

Results for the pre-registered field baseline deposited as version 1.0 of this record (DOI 10.5281/zenodo.22798718, 16 September 2026). This version reports the registered dependent variables, completes Section 9 of the pre-registration from the session logs, and deposits the evidence package. Across 40 confirmatory se...

Artur Ferreira, julio Arévalo Piedra. · 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.