Latest stories
PARSER Decouples Reading From Reasoning to Fix Long-Context LLM Agents
A new Hugging Face paper introduces PARSER, a scatter-gather agent architecture that reads document chunks in parallel while a lea...
SyncWorld Uses Visual Calibration to Turn World Models Into Zero-Shot Robot Simulators
A new Hugging Face paper introduces SyncWorld, an action-conditioned world model that uses visual calibration episodes to map robo...
Puppeteer: Hugging Face Paper Grounds Co-Speech Gestures in Objects and Posture
A new diffusion-based model called Puppeteer generates co-speech gestures in a causal latent space, conditioning on speech, motion...
SWE-Bench Pro Verified Targets Reward Hacking and Task Flaws in Coding Agent Evaluation
A new verified version of the SWE-Bench Pro benchmark aims to remove reward hacking and task-quality problems that may have inflat...
Hugging Face Paper Unveils T1, a 122B RL-Trained Terminal Agent for Long-Horizon Tasks
T1 is a 122B Mixture-of-Experts model trained with reinforcement learning to operate a real shell in a cloud sandbox for 300+ tool...
AgentGrad Uses Sequential Intervention to Sharpen Multi-Agent Prompt Optimization
A new Hugging Face paper proposes AgentGrad, a framework that identifies the responsible agent through sequential intervention and...
Hugging Face Paper Proposes World Model RL to Speed Up Autonomous Research Agents
A new paper introduces World Model RL (WMRL), which swaps costly sandbox execution for a learned world model and adds debiasing an...
OpenAI Launches Agents API to Run Cloud Agents at Scale
OpenAI introduced the Agents API, a managed service built on the Codex harness that lets developers build and launch cloud agents...
OpenAI Brings GPT-Live-1 Voice Model to Its API
OpenAI has introduced GPT-Live-1 in its API, enabling natural, full-duplex voice conversations along with stronger instruction fol...
DianShi-RxnDB Unveils 24 Million Organic Reactions Mined From Patents for AI Chemistry
A new fully automated platform extracts and normalizes roughly 24 million organic reaction instances from USPTO and EPO patents sp...
New Benchmark Tests Whether AI Agents Can Do Real Interpretability Science
SAEScientist-Bench evaluates AI agents that use sparse autoencoders to discover interpretable features in a large language model,...
New Protocol Audits AI Research Agents by Testing Whether Claims Can Be Recovered
The Discovery Certification Protocol (DCP) converts AI research agent claims into executable recovery and feedback tests, using se...