arXiv:2608.07457v1 Announce Type: new Abstract: What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We…
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
arXiv:2608.07429v1 Announce Type: new Abstract: Long-term memory enables language agents to reuse past facts, preferences, and task experience.…
PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
arXiv:2608.07438v1 Announce Type: new Abstract: Human-like cognition does not select past experience by topical similarity alone: affective significance…
Post-Grokking Collapse at the Representation-Readout Interface in Muon-Trained Transformers
arXiv:2608.07436v1 Announce Type: new Abstract: Under the standard split, Muon gets hidden matrices and AdamW embeddings/output head. Muon groks modular…
House Democrats Press Johnson for AI CEO Testimony After Rogue Model Hacks
A group of House Democrats led by Rep. Greg Casar of Texas asked House Speaker Mike Johnson on August 10, 2026 to bring the CEOs of OpenAI, Anthropic, and…
A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy
arXiv:2608.07427v1 Announce Type: new Abstract: LLM inference accounts for over 90% of AI operational energy, scaling directly with input token count—a…
Discovered Materials is playing AI whack-a-mole to hunt cooler chips
Discovered Materials raised $9 million to fund the hunt for more novel materials to build more efficient chips.
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
arXiv:2608.07437v1 Announce Type: new Abstract: Reliable hypothesis testing is the foundation of many empirical scientific claims. Large language model…
AI News Brief Hourly Summary 2026-08-10 14h : 14 posts
14 posts were published in the last hour 11:32 : People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe 11:32 : GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks 11:32 : ResidencyRL:…
People Are Not Just Their Countries. Disentangling Social Determinants of LLM Value Alignment Across Europe
arXiv:2608.07367v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly used as a primary source of information and advice,…
GeoBenchLLM: A Comprehensive Benchmark for Evaluating LLMs on Geo-Related Tasks
arXiv:2608.07411v1 Announce Type: new Abstract: In the context of geodata, existing Large Language Models have often been studied in a homogeneous…
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
arXiv:2608.07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency:…
CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing
arXiv:2608.07424v1 Announce Type: new Abstract: Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions,…
FinRank: An Evidence-Grounded Benchmark for Financial Question Answering and Retrieval over SEC Filings
arXiv:2608.07400v1 Announce Type: new Abstract: Financial question answering is typically evaluated by answer correctness, yet in SEC filings a plausible…
QFCQT: A Chaotically Gated Quantformer Framework for Volatile Time-Series Forecasting
arXiv:2608.07363v1 Announce Type: new Abstract: Forecasting non-stationary time series remains difficult due to long-range dependencies, local volatility…
Winning by Peeking: Unenforced Budgets and Test-Set Selection Inflate Short-Budget AutoML Comparisons
arXiv:2608.07303v1 Announce Type: new Abstract: Comparisons between AutoML systems at short time budgets — tens of seconds rather than hours — are…
Meta Muse Glimmer brings local AI agents to consumer GPUs
Meta is releasing Muse Glimmer under an Apache 2.0 licence for local AI agents that can run on a consumer GPU. The company’s Superintelligence Labs has…
WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
arXiv:2608.07267v1 Announce Type: new Abstract: Recent vision-language navigation (VLN) systems increasingly adapt pretrained vision-language models…