This Startup Led by an Ex-Apple Designer Thinks a GUI for AI Could Change Everything
Hark's launching its software interface today, called Hark Pro. The hardware is coming. Just not today.
Gizmodo — AI8 min read
AI agents
4,541 stories
Announcing 30+ new programs across Coursera and Udemy to help learners build AI and human skills
Today, on the sidelines of our first Coursera + Udemy Partner & Instructor Forum in Madrid, we announced more than 30 new programs and several exciting platform updates — all designed to help learners and creators better navigate the changing skills landscape.
Andrew Ng’s Machine Learning at Stanford University Blog5 min read
Researchers Are Tracking a Chinese AI 'Agent Fleet'
Independent researchers say they've identified a large "fleet" of AI agents apparently running on Tencent infrastructure and making parallel queries against Alibaba's Amap mapping service.
Slashdot1 min read
AI Voice Agent Compatible With SIP And Existing Telephony: 23 AI Voice Agent SIP Integration Guide: Top Compatible Picks
Enterprise buyers avoid costly SIP failures by choosing an AI voice agent compatible with SIP and existing telephony built for regulated production stacks.
Bland AI Blog34 min read
Give Your Agent Context Before You Buy an AI SRE
We ran the same agent and model on 50 live Kubernetes faults. With read-only cluster context it reached the answer about three times faster, and was slightly more accurate. Here's what it did without that context, and how to run the same test before you buy an AI SRE.
Radar Blog10 min read
Reflection AI Beam: the 501B open weight model, explained
Reflection AI Beam is a 501B parameter open weight model. Size, Reflection's own scores, licence and when you can get it, checked 6 Oct 2026.
Munder Difflin Blog6 min read
Gemini automation: How to use the Zapier Gemini integration (Gemini 3.8 Flash, Gemini Enterprise, and more)
Anyone who lives in the Google ecosystem has probably used Gemini for a quick draft or a fast answer. (Or if you're like me, you've been driven to your limit by the Google Docs popups encouraging you to use AI whenever your cursor strays too close to the bottom of the screen.) But a chat window is…
Zapier AI Blog8 min readAgentic AI with Structured CoT for Enhancing AI's Spatial Intelligence: Visualization and Reasoning of Rotation
Recent studies show that artificial intelligence (AI) with language and vision capabilities still experiences limitations in spatial reasoning. In this paper, we have studied the spatial capabilities of advanced generative AI to understand the rotations of objects in 3D space, utilizing AI's image…
arXiv - cs.AI2 min readTrajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents
LLM agents for clinical text-to-SQL applications reason autonomously over multiple steps but cannot assess whether their own reasoning or outputs can be trusted. In high leverage applications such as healthcare, this presents a critical risk where system mistakes can be costly.
arXiv - cs.CL (NLP)2 min readSelf-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough
Memory poisoning attacks on LLM agents typically assume an external adversary who plants content in the agent's persistent memory to steer its behavior.
arXiv - cs.AI2 min readUnderstanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorrect tools or generating invalid calls.
arXiv - cs.CL (NLP)2 min readAgentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents
Agentic large language model (LLM) systems are commonly implemented as an LLM in a loop with Planning, Memory, Tools, and Control Flow. This application-focused view connects agentic LLM research with deployable systems and leaves open how such systems should be evaluated beyond end-to-end task…
arXiv - cs.AI2 min readEvalResearchBench: Can AI Agents Design Their Own Evaluations?
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites.
arXiv - cs.AI2 min readPlaying social deduction games with reinforcement fine-tuned large language models
Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deduction games to study how RFT changes LLMs' social behaviour.
arXiv - cs.CL (NLP)2 min readAgent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents
Financial LLM agents are often evaluated by comparing their end-to-end returns with those of a baseline and testing the paired difference against zero. This measures whether deploying the agent changes realized performance, but it does not isolate event-selection skill.
arXiv - cs.AI2 min readPB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO
Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locally helpful responses.
arXiv - cs.CL (NLP)2 min readTraining Numerical Intelligence via Auto-Diagnosis and Skill Discovery
AI agents are becoming increasingly capable of generating scientific code, but generating code is not the same as improving the algorithms behind it. For numerical solvers, execution feedback can expose poor performance, but rarely reveals its underlying cause and how to address it.
arXiv - cs.AI2 min readSkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown
Executable Agent Skills combine natural-language instructions and scripts into reusable packages for LLM agents, and revising them requires fixing errors without breaking correct behavior.
arXiv - cs.AI2 min read
Showing 1,638 of 4,541 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts