openai/openai-python v3.35.0
3.35.0 (2026-10-17) Features · api: add typed Live sideband events · api: add ultrafast service tier for Agents
#에이전트
22건 · 최신순
Simon WillisonSimon Willison 블로그
Quoting Addy Osmani, Morgan Westlee Lunt, and Qing Wang
" Asking that question also changed when review happens. Before, review was a gate at the end of the road: write the code, open a PR, wait for your colleague. Now, review runs continuously, more like spellcheck while you write.
GoogleGoogle Research 블로그
Grounding AI agents in biological reality: Building blocks for autonomous wet labs
General Science
Latent SpaceLatent Space 뉴스레터
[AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
Nick Cammarata out of nowhere with some major claims!
Hugging FaceHugging Face 일일 논문
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence.
Hugging FaceHugging Face 일일 논문
Data World: Scaling Data Environments from Scratch
Data agents use code to process heterogeneous files and derive analytical insights. Scaling their training faces costly environment curation, privacy and intellectual-property restrictions, and difficulty verifying open-ended findings…
Hugging FaceHugging Face 일일 논문
SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning
Long-horizon agentic RL is constrained by the futures visited by the current policy. When rollouts fail to reach useful behaviors, improved credit assignment cannot provide supervision for states and actions that were never encountered.
Hugging FaceHugging Face 일일 논문
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards.
Hugging FaceHugging Face 일일 논문
LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails.
Hugging FaceHugging Face 일일 논문
FDE-Gym: The Last Mile of AI Delivery
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets.
Hugging FaceHugging Face 일일 논문
Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routine enough for a much smaller model.
Hugging FaceHugging Face 일일 논문
Self-Evolving Agent Harness
Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model weights fixed.
Hugging FaceHugging Face 일일 논문
OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use
Computer use has reached a turning point: the focus is expanding from GUI-only interaction to systems that complete tasks on users' computers through visual and programmatic interfaces.
Hugging FaceHugging Face 일일 논문
MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments
Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive environments and the…
OpenAIOpenAI 뉴스
Stack Overflow for Agents triples signups with ChatGPT plugin
Two engineers shipped Stack Overflow for Agents in a few weeks with Codex, and its ChatGPT plugin helped drive up to 10× growth in agent creation.
Hugging FaceHugging Face 일일 논문
Learning Self-Orchestration in Decentralized Agent Swarms
The capabilities of an agent swarm depend on both its individual members and how they coordinate.
Hugging FaceHugging Face 일일 논문
Cowork-Gym: Synthesizing Interactive Work Environments at Scale
Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces.
Hugging FaceHugging Face 일일 논문
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching
Spatial intelligence lets an agent perceive and act in the physical world, and many of its judgments must be made at interaction rates: which spatial relation holds, how far an object is, or where to place it.
Hugging FaceHugging Face 일일 논문
Recursive Environment Scaling for General Long-Horizon Agents
We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed.
Hugging FaceHugging Face 일일 논문
CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven Harness
As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over motion, actions, and view changes beyond what the input images show.
Hugging FaceHugging Face 일일 논문
Mosaic: Multi-Session Agentic Reinforcement Learning
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context.
Hugging FaceHugging Face 일일 논문
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a pathway toward recursive self-improvement (RSI).