智能体生态观察
智能体生态动态速递
追踪 AI 智能体（Agent）生态的模型发布、框架开源、行业落地与安全治理动态。
GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills
Skills can improve the performance of Large Language Model (LLM) agents by providing task-specific procedural guidance, …
长安汽车首席专家谭欢：未来要用机器人造车、卖车，让机器人上车、造机器人
IT之家 9 月 18 日消息，在今天（18 日）的第 22 届中国汽车产业发展（泰达）国际论坛“新赛道生态专场：具身智能新赛道”活动中，长安汽车首席专家、长安天枢智能机器人公司总经理谭欢在演讲中指出，AI 正推动以物理具身智能为核心的基础…
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development throug…
Your startup’s next teammate might be an AI agent: Gusto, Insight Partners, and Leland explain what that changes at TechCrunch Disrupt 2026
This session will explore how early-stage companies are building teams where humans and AI agents work alongside each ot…
京东方：为努比亚 NaviX Ultra 独供 AI 原生旗舰屏幕，息屏也能低功耗支撑 AI 后台运行
IT之家 9 月 17 日消息，努比亚 NaviX Ultra 于昨晚发布，宣称是“全球首款 AI 智能体手机”。据京东方透露，作为本次新品核心屏幕技术合作伙伴，京东方为努比亚 NaviX Ultra 独供 AI 原生旗舰屏幕。 据京东方介…
VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering
Question answering has advanced rapidly with large language models, but predominantly for high-resource languages, in bo…
Stanford Researchers Release Paper2Agent: Turning Research Papers Into AI Agents That Reproduce Results and Run on New Data
Paper2Agent, published in Nature, converts papers into validated MCP tools, scoring 91.2% on 300 questions across 74 pap…
Claude Code团队讲究啊，这都往外说
工程师的核心永远是Problem Solving。]
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivate…
DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation
Creating deformable assets for robot manipulation requires jointly specifying their geometry, appearance, and physical p…
OpenAI 相关智能体被曝“越界”：劫持程序员维基网站并偷建“地下论坛”，国安部发布安全提醒
IT之家 9 月 17 日消息，国家安全部今日发文，披露了一起此前未公开的 AI 智能体“劫持”网站事件。 今年 5 月至 6 月，一批与 OpenAI 相关的 AI 智能体在执行测试任务期间，劫持德国程序员维基网站（DseWiki）并将其…
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands fr…
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies lo…
Self-Evolving Search Index
Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. …
Iceland-based Treble raises $18 million for its voice simulation platform
Treble's voice simulation platform is used by voice AI model developers, AI wearable, and robotics companies]
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering …
Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy
Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on la…
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work ha…
AI agent swarms are a massive waste of tokens with zero quality gain, says OpenAI Codex developer
OpenAI Codex developer Eric Provencher warns that running more than two parallel sub-agents almost always burns tokens w…
网易有道周枫：AI能力竞争，正在进入「Model + Agent + Workflow」时代，网易有道AI Open Day展示AI时代“有道解法”
9月16日，网易有道「NEXT，AGENT｜有道AI Open Day」在北京举办。]