arXiv:2503.13309v3 Announce Type: replace-cross Abstract: Despite advancements in Computer-Aided Diagnosis (CAD) systems, breast cancer remains one of the…
Fully Offline Reinforcement Learning
arXiv:2505.22442v4 Announce Type: replace-cross Abstract: Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on…
LLINBO: Trustworthy LLM-in-the-Loop Bayesian Optimization
arXiv:2505.14756v3 Announce Type: replace-cross Abstract: Bayesian optimization (BO) is a sequential decision-making tool widely used for optimizing…
MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery
arXiv:2610.39714v2 Announce Type: replace Abstract: Molecular discovery requires navigating vast combinatorial search spaces while balancing competing…
What Breaks When Facts Become Stories? The Distortions Source-Agreement Metrics Miss When Models Retell Real Events
arXiv:2610.39500v2 Announce Type: replace Abstract: Language models are now widely used to turn recorded facts into media for public consumption, yet…
Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training
arXiv:2610.38851v2 Announce Type: replace Abstract: In many settings where LLM post-training is desirable, high-quality answers are recognizable but…
EvoTeam: Multi-Agent Collaboration via Evolving Teams
arXiv:2610.39813v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex…
Google Brings Dreambeans’ Personalized AI Stories to India
Google announced on November 3, 2026 that Dreambeans, its experimental Google Labs app for personalized daily story collections, is expanding to people…
Time Will Tell: Harness Time to Denoise Collaborative Filtering
arXiv:2411.09181v2 Announce Type: replace-cross Abstract: Neural graph collaborative filtering is a powerful tool for recommendation due to its superb…
AI News Brief Hourly Summary 2026-11-03 05h : 16 posts
16 posts published in the last hour 03:33MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs 03:33LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery 03:33Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization 03:33SpectRAG: Weighted Chunk Graphs for…
MuSID-KD: Multigranularity Knowledge Distillation for Generative Recommendation with Semantic IDs
arXiv:2610.35218v2 Announce Type: replace Abstract: Generative recommendation with semantic IDs (SIDs) represents each item as a sequence of discrete…
LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery
arXiv:2610.33465v2 Announce Type: replace Abstract: Equation discovery solvers often use different data interfaces, equation representations and…
Logic Hijacking of RAG: Single-Document Poisoning via Local Optimization
arXiv:2610.34829v2 Announce Type: replace Abstract: Single-document corpus poisoning under black-box access poses a severe threat to Retrieval-Augmented…
SpectRAG: Weighted Chunk Graphs for Token-Budgeted Context Selection in Multi-Hop Retrieval-Augmented Generation
arXiv:2610.36991v3 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving…
Google takes Dreambeans to India in bid to bring AI-generated personal stories to the masses
Google’s Dreambeans, its latest AI experiment, now supports 13 Indian languages.
Concordat: Typed Sessions for LLM Agents
arXiv:2610.37461v2 Announce Type: replace Abstract: Agents built on large language models are increasingly allowed to take consequential actions:…
From Prediction to Action: Population Health World Model for Digital Medicine
arXiv:2610.24662v2 Announce Type: replace Abstract: Digital medicine now captures data that traces individual health trajectories and reveals population…
Preparing our next security sprint to harden OpenAI
OpenAI is preparing its next internal security sprint with Cathedral Systems to test and strengthen its defenses using AI.