“If this was opt-in, nobody would opt in,” Twitch CPO Mike Minton said on a livestream responding to user feedback. “That’s honestly the answer.”
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
arXiv:2608.12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state. An unsafe…
Correct Is Not Governed: Provenance Integrity in Agentic Workflows
arXiv:2608.12761v1 Announce Type: new Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient…
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
arXiv:2608.12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal…
CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
arXiv:2608.12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing…
ARAC: Benchmarking Auto-Research’s Alignment and Completeness on End-to-End Researchs
arXiv:2608.12788v1 Announce Type: new Abstract: The rapid advancement of Auto-Research has surfaced a fundamental evaluation challenge: how can we measure…
PROVE-RT: Generating Mechanized Theorem Prover Scripts for Real-Time Systems using LLMs
arXiv:2608.12762v1 Announce Type: new Abstract: Schedulability analysis is essential for certifying real-time systems, but existing tests are often…
AI News Brief Hourly Summary 2026-08-14 09h : 16 posts
16 posts were published in the last hour 6:32 : Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy 6:32 : On the Expressive Power of Transformers 6:32 : Privacy-Preserving RAG by Concealing Sensitive Information from External…
Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy
arXiv:2608.12674v1 Announce Type: new Abstract: Maintaining price consistency and executing an Every Day Low Price strategy is critical for global…
On the Expressive Power of Transformers
arXiv:2608.12671v1 Announce Type: new Abstract: Multi-layer transformers form the critical component of essentially all large language models (LLMs) in…
Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs
arXiv:2608.12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models…
The Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis
arXiv:2608.12677v1 Announce Type: new Abstract: Detecting infection-related behavioral changes in mosquitoes from video data is challenging because…
CloudSEK Links March LiteLLM Supply Chain Breach to 2,500 Organizations
Threat-intelligence firm CloudSEK said in a report published August 11, 2026 that it has identified more than 2,500 organizations potentially exposed by…
Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies
arXiv:2608.12679v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science. The…
SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries
arXiv:2608.12654v1 Announce Type: new Abstract: Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or…
Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That Ships as a 14MB Binary and Runs a Full Session in 28MB of RAM
Cactus Compute released Needle 2, an open 45M-parameter model for tool calling, device use, and structured extraction. The full model is a single 14MB…
@skills: Attention is all you have
arXiv:2608.12610v1 Announce Type: new Abstract: There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery…
SpaceXAI’s Grok 4.6 matches OpenAI’s best model and undercuts it on price
xAI’s Grok 4.6 scores 61 points on the Artificial Analysis Intelligence Index, tying GPT-5.6 Sol and trailing only Anthropic’s Claude Opus 5. On agentic…