arXiv:2609.15818v2 Announce Type: replace Abstract: As AI agents become participants in the development of their successors, they reshape both the…
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction
arXiv:2609.18063v2 Announce Type: replace Abstract: Mixture-of-experts (MoE) inference on consumer hardware is bounded by weight memory: a 35B-class model…
AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research
arXiv:2609.16519v2 Announce Type: replace Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in…
Inference-Time Nash Alignment
arXiv:2609.08082v2 Announce Type: replace Abstract: Preference-based fine-tuning methods such as RLHF and DPO require substantial compute and large…
Attributing Preprocessing Invariance in Spectral Foundation Models
arXiv:2608.14227v3 Announce Type: replace Abstract: A spectral foundation model should remain useful when laboratories preprocess spectra differently. The…
LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies
arXiv:2609.06079v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies leverage pretrained vision-language models (VLMs) to guide…
Consumers Sue Anthropic, OpenAI, SpaceXAI and Google Over Alleged AI Pact
Four consumers filed a class-action complaint in federal court in San Francisco on September 18, 2026, accusing Anthropic, OpenAI, SpaceXAI and Google of…
AutoResearch: Insight In, Hallucination Out
arXiv:2608.17906v4 Announce Type: replace Abstract: Autonomous research systems are increasingly capable of executing long research workflows, yet…
Reduce time-to-hire for quality candidates with AI-powered Amazon Connect Talent
Amazon Connect Talent is an AI hiring solution built for talent acquisition leaders managing scaled hiring. It delivers AI-led interviews, data-driven…
FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models
arXiv:2608.08736v2 Announce Type: replace Abstract: Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the…
What’s So Good About ChatGPT Work? Here’s What I Found
This article walks through how ChatGPT Work specifically earns its reputation, where the underlying models genuinely hold up against the competition, and…
AIREP: A Protocol for Per-Decision Evidence in AI Runtime Governance
arXiv:2608.21363v2 Announce Type: replace Abstract: Runtime-governance evidence often collapses materially different events into one audit record: a…
AI News Brief Hourly Summary 2026-09-19 05h : 13 posts
13 posts published in the last hour 02:32Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays 02:32Multi-Resolution Attribution from Adaptive Routing State 02:32When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis 02:32AI Training Manager: Bounded Closed-Loop…
Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays
arXiv:2607.09678v2 Announce Type: replace Abstract: When LLM agents hand information to one another, does the message format matter? Two literatures…
Multi-Resolution Attribution from Adaptive Routing State
arXiv:2605.22866v2 Announce Type: replace Abstract: Adaptive hierarchical systems accumulate routing state as they learn which components to select. We…
When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis
arXiv:2606.29251v3 Announce Type: replace Abstract: Financial decision-makers face more information than they can directly inspect, making context…
AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes
arXiv:2606.29871v2 Announce Type: replace Abstract: We present the AI Training Manager, a bounded LLM-based metacognitive monitoring-and-control layer for…
When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents
arXiv:2608.05810v2 Announce Type: replace Abstract: Self-evolving agents accumulate capability by distilling reusable skills from their execution…