News
AI, cybersecurity, machine learning, scraping & programming news.
113 results on this page · clear filters
KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
Deep search agents solve knowledge-intensive tasks through long-horizon multi-turn interactions. Assigning credit to individual search decisions is fundamentally difficult. Outcome-based reinforcement learning provides only a sing...
Training Reasoning Models to Generate Diverse Scientific Ideas
One of the first steps of a research pipeline is generating ideas. Large Language Models LLMs are increasingly used to automate this step, but most of this work optimizes the quality of individual ideas while overlooking diversity...
Learning to Steer LLM Agents and Multi-Agent Systems
Large language model agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. As execution unfolds, these systems are prone to deviating from the overall goal, a...
Linus Torvalds's first LLM-assisted patch series
Linus Torvalds posted his first LLM-assisted patch series to the Linux kernel mailing list. The series comprises ten patches that enhance folio lookup by identifying when folios are "hot" and applying an RCU (Read-Copy-Update) del...
Why do LLM pelicans look like this?
Frontier AI models remain distant from human designers on design creativity. A new benchmark called Design Creativity Bench evaluates AI models' creativity on UI design tasks. Despite rapid advances in their ability to generate fu...
ChunkAct: Action Chunking for Agentic Robotics
Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidance of a memory and thereby generalizes to new tasks...
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
The problem this paper tackles is the failure of open‑source models to operate autonomously on long‑horizon tasks that span economically valuable work, from multi‑hour computations to multi‑day projects. Such a capability is essen...
PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts
Pixel-space diffusion models have long appealed as an alternative to latent-space approaches, offering direct modeling of raw images without dependence on a learned tokenizer. Yet scaling these models has followed dense strategies...
GPT-6 Astra Helped Me Jailbreak My Kindle
Aim: Screensaver and Custom App Kindle sitting unused, wanted to see whether AI could help find a new use for it. Goal: create custom app covering range of uses, controlled by AI agent on MacBook. Started with small goal: use own...
Launch HN: Agent37 (YC F26) – Low-cost agent sandboxes for running agents
Agent37, a Y Combinator F26 startup, offers sandboxes for running AI agents at under 10% of typical provider costs. Customers pay an average of $0.37 per month per sandbox, and the company now provides a free tier used by more tha...