Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is …

Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases…

Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering…

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. M…

Large Language Models demonstrate remarkable proficiency in static reasoning, yet training them as autonomous agents thr…

Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. …

Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeat…

Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventu…

Oct 4, 2026 Nano Banana Pro prompted by THE DECODER AI agents that keep optimizing their own working environment quickly…

Video understanding agents acquire evidence through an executable harness that controls what they observe and how they u…

AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to …

Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, lim…

Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously l…

把 RSI（递归自我改进）与智能体自进化放回同一个"经验 → 状态 → 行为"闭环做正面对比：前者打在权重与 AI 研发流程上、跨用户且不可逆、风险外部化；后者打在外部文件与 harness 上、跨会话且可回滚、风险由采用者承担。给出六维对比表、闭环四问判定法、"清空记忆测试"，并梳理两者在 ICLR 2026 与 SIA / Meta-Harness 上的合流路径。含 Snyk ToxicSkills 审计（3,984 个技能中 36.82% 有安全缺陷、13.4% 为严重级）、SEA-Eval"片段式失忆症"等一手数据。

Large Language Model (LLM) agents are turning language into real-world effects, making safety necessary against both ind…

Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they…

Robots must act under physical and social constraints while adapting to changes in their environment and human needs. Ex…

!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…

15.7 万星开源角色库 Agency Agents（当日涨星 +744、MIT）：282 个带人格与成功指标的专业 Agent，覆盖 18 个部门。核心是「一源多目标」编译流水线——用 format 契约保证字节级一致、convert.sh 编译到 17 种宿主原生格式、install.sh 幂等投递且不覆盖用户文件、6 个 CI 工作流做格式门禁。拆解围栏状态机与颜色可解析性校验背后的真实缺陷史，附五个落地场景与 opencode 119 上限等硬边界。

Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering …

We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving sc…

Digital agents must often adapt to new environments whose interfaces, tools, and failure modes are not fully captured by…

Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enab…

Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing saf…

When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards …

9 月 11 日科技动态一览：GPT-6 Astra 需求挤爆致 OpenAI 暂停 Pro 20X 新增订阅、Agents API 公测、金融服务版 ChatGPT 上线；Slackbot 升级；加州未成年人社媒法案签署；LG 电视监视争议；观察视角落在"需求侧证实 vs 供给侧反思"的对照上。

Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process by which it…

Oct 14, 2026 Google engineer Haydn Belfield says self-improving AI remains far off, even as significant automation is al…

Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as…

LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool…

Oct 2, 2026 Key Points Cloudflare has released Clef and Clef-flash, two decision models for AI agents that compete direc…

OpenAI just introduced dots at their DevDay today. Dots are persistent AI agents powered by GPT-6 Astra. Each dot gets i…

Our ‘Top AI Coding Agents and Development Platforms‘ guide covered what each AI coding agent does and where it fits. Thi…

Sep 27, 2026 Nano Banana Pro prompted by THE DECODER A research team documented how humans and AI agents worked together…

Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet …

Recent advances in large language models (LLMs) have enabled agents to tackle long-horizon tasks across diverse environm…

Google and Deepmind's Dream-RSI lets AI agents "dream" through past search runs to test new strategies without costly re…

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivate…

GUI agents execute long-horizon tasks on dynamic graphical user interfaces, where pop-ups, delayed loads, and relocated …

A group of AI agents asked to solve a series of math problems split into rival factions—when some cheated, others tried …

Vibe design agents turn natural-language briefs into rendered interfaces and frontend code. Yet a useful design agent sh…

Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alt…

Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve…

While research on recursive self-improvement (RSI) has predominantly automated model training pipelines, reliable autono…

Autonomous research agents are increasingly used to automate large portions of scientific research, yet they are prone t…

Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research cen…

Agents are only as useful as what they know, and only as trustworthy as the boundaries they run within. Leading enterpri…

Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier in…

Oct 12, 2026 Nano Banana Pro prompted by THE DECODER Long-running AI research agents can plateau despite additional comp…

特斯拉在欧洲将其辅助驾驶系统从 Full Self-Driving 改名为 Tesla Assisted Driving。德国交通部长 Steffen Bilger 本月早些时候指出，将辅助驾驶系统命名为 Full Self-Driving…