arXiv:2608.28704v1 Announce Type: new Abstract: AI agents increasingly perform long-term reasoning, planning, tool use, memory integration, and autonomous…
AI News Brief Hourly Summary 2026-09-01 09h : 10 posts
10 posts published in the last hour 06:32How Language Models Choose Sides: Internal Representations of Instruction Hierarchy 06:32Self-Specialized Teachers for Domain Post-Training 06:32A Generalized Optimization Engine (GOE) for Edge AI Inference Acceleration 06:32BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice…
How Language Models Choose Sides: Internal Representations of Instruction Hierarchy
arXiv:2608.28648v1 Announce Type: new Abstract: We study how instruction-tuned LLMs arbitrate direct conflicts between system and user instructions. We…
Self-Specialized Teachers for Domain Post-Training
arXiv:2608.28647v1 Announce Type: new Abstract: Target-only post-training can improve performance in a specialized domain while degrading behaviors that a…
A Generalized Optimization Engine (GOE) for Edge AI Inference Acceleration
arXiv:2608.28652v1 Announce Type: new Abstract: Artificial intelligence (AI) models have demonstrated remarkable capabilities across various domains, yet…
BiasMix-Finance: Post-Generation KYC Guardrails for LLM Portfolio Advice
arXiv:2608.28646v1 Announce Type: new Abstract: Large language models (LLMs) can generate plausible-sounding ETF portfolios while silently violating basic…
From Extraction to Governed Memory: Multi-Agent Knowledge Graph Construction with Domain-Expert Review
arXiv:2608.28642v1 Announce Type: new Abstract: Knowledge graphs used by agentic systems are often treated as flat stores of extracted triples, with…
CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science
arXiv:2608.28631v1 Announce Type: new Abstract: An AI scientist should not grade its own homework. Yet in the systems we examined, the agent that reviews…
AI Scientist Mission Control (AIMC): Visual Analytics for Human Oversight of Autonomous Scientific Discovery
arXiv:2608.28637v1 Announce Type: new Abstract: Autonomous scientific discovery systems can generate large numbers of research ideas, experiments, and…
Self-Evolving Skills via Surrogate-Guided Solve-and-Reproduce
arXiv:2608.28638v1 Announce Type: new Abstract: Agent skills are portable packages of instructions and resources an agent consults at deployment.…
Reward-Oracle MCTS for Formal Theorem Proving: Sample-Efficient Search and the Need for Kernel-Level Proof Auditing
arXiv:2608.28639v1 Announce Type: new Abstract: Formal theorem proving with large language models remains challenging due to the difficulty of navigating…
AutoScientist-Quant: Self-Evolving Coding Agents for Automatic Research in Quantitative Investment
arXiv:2608.28632v1 Announce Type: new Abstract: Large language model agents can discover alphas, yet current methods have three weaknesses. The search…
AI News Brief Hourly Summary 2026-09-01 08h : 12 posts
12 posts published in the last hour 05:33CDEP Agent: Connecting Meteorologically Detected Temporal Compound Events to Real-World Documentary Evidence 05:33TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback 05:32Machine Learning-Enhanced Tabu Search for Tactical Wireless…
CDEP Agent: Connecting Meteorologically Detected Temporal Compound Events to Real-World Documentary Evidence
arXiv:2608.28628v1 Announce Type: new Abstract: Compound drought-to-extreme-precipitation (CDEP) events are recognized in climate science as a growing…
TPvG: A Moral Decision Framework for Large Language Models from One-Shot to Sequential Feedback
arXiv:2608.28610v1 Announce Type: new Abstract: Existing LLM moral evaluations typically present models with isolated moral vignettes and elicit a…
Machine Learning-Enhanced Tabu Search for Tactical Wireless Network Design
arXiv:2608.28627v1 Announce Type: new Abstract: Designing high-performance tactical wireless networks under realistic operational constraints gives rise…
OpenAI Backs California Bill on Youth Safety Rules for Companion Chatbots
OpenAI said on August 31, 2026, that it supports California Senate Bill 1119, legislation that would impose safety obligations on operators of companion…
InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal
arXiv:2608.28612v1 Announce Type: new Abstract: Generating professional scholarly content, such as peer reviews and rebuttals, requires an intricate…