New Term Radar

Saved terms stay in this browser and do not sync to your account. Source collection continues on the server without this page being open.

Seven-day figures use the complete UTC window above. Priority is a research triage score, not search volume, market size or a probability of success.

1. ConceptNewly observed

   CGAP

   arXiv:2610.41040v1 Announce Type: new Abstract: LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by trial and error, with no guarantee of an executable plan. We present Capability-Grounded Agentic Planning (CGAP), wh

   First observed Nov 3, 2026 · arXiv

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

2. Named entityInsufficient data

   CleanSlop

   Hello HN! We have recently launched a scanning and remediation system for AI-built web applications. It is fully agentic as well as has a web UI that supports GitHub sign-in. Would love some hackers and tinkerers to try it out. An agent can natively interact with the system when you pass the prompt: "Scan with cleanslop.com" to it within the contex

   First observed Oct 22, 2026 · Hacker News / Product Hunt

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

3. Named entityNewly observed

   Lotse

   First observed Nov 4, 2026 · Hacker News

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

4. Named entityNewly observed

   p-e-w/heretic

   Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more

   First observed Nov 2, 2026 · GitHub Trending

   7d mentions

   0 previous 0

   7d sources

   0

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

5. Named entityNewly observed

   UnleashX

   The AI workforce that turns conversations into outcomes.

   First observed Nov 2, 2026 · Product Hunt

   7d mentions

   0 previous 0

   7d sources

   0

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

6. Named entityNewly observed

   PatchScout

   arXiv:2611.00169v1 Announce Type: new Abstract: Researchers often need web corpora that are not answers to a single query, but reusable collections of documents spanning many decentralized sources. We refer to this problem as thematic web data collection: assembling semantically relevant documents that share a common theme but are scattered across heterogene

   First observed Nov 4, 2026 · arXiv

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

7. Named entityNewly observed

   xescure/slop-node

   ...the first publicly available node software for Keeta. Created with heavy use of AI agents. Not affiliated with Keeta. You can run a replica, a peering node or a (testnet) rep with Docker in a few lines. Mine is running at https://node.xescu.re/api/node/version The true digitalization of finance, especially in cross-border contexts, has stalled. Blockchain

   First observed Nov 2, 2026 · Hacker News

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

8. Named entityNewly observed

   以来被问最多

   整理一下被问最多的 8 个问题： 是不是把图贴进 PPT ？不是，文字是文本框，形状是原生对象。 能改字吗？能，双击就能改。 为什么这么慢？要反复渲染比对，单张十几轮。 所有图都能转吗？不是，写实插画、超长图、手写体效果有限。 扫描件行吗？可以，但原图不清楚的部分不会变清楚。 能批量吗？建议分批，先挑最急的。 需要装软件吗？网页版不用，命令行版需要配环境。 失败了怎么办？会退回，不会白扣。 还有别的问题可以继续问。 工具入口在这里： https://image2ppt.asia?utm_source=v2ex （图片、截图、单页 PDF 都能转成可编辑的 PPTX ，成品无水印。） 相关截图（原图 → 成品）：

   First observed Nov 4, 2026 · V2EX

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

9. Named entityNewly observed

   stass/awklog

   For many of the projects I work on I found myself wanting to use a relational language like Datalog to generate C source from specifications, do verification during build or maintain a task database. However pulling a full blown Souffle or SWI-PL as a build dependency is always a PITA and also an overkill. So I (with the help of Claude) built awklog, a pure

   First observed Nov 2, 2026 · Hacker News

   7d mentions

   1 previous 0

   7d sources

   1

   7d growth

   Not comparable

   Priority

   37 / 100

   Save

10. Named entityNewly observed

    OmniPiano

    arXiv:2611.00243v1 Announce Type: new Abstract: Dexterous robotic manipulation remains a major challenge in robotics, exemplified by piano playing, which requires coordinated control of fingers and provides a demanding testbed for reinforcement learning (RL). Although previous work established a benchmark for robotic piano playing, it is restricted to two ha

    First observed Nov 4, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

11. Named entityNewly observed

    Display 1.0

    Create docs and apps with any agent, in one workspace

    First observed Nov 2, 2026 · Product Hunt

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

12. Named entityNewly observed

    Agent Inbox

    Give your agent an email address, Slack and Telegram handle

    First observed Nov 2, 2026 · Product Hunt

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

13. Named entityNewly observed

    MemU-Bench

    arXiv:2611.00191v1 Announce Type: new Abstract: Existing Graphical User Interface (GUI) benchmarks predominantly rely on precise and stateless user instructions. In everyday usage, however, instructions are often \emph{vague and history-dependent}: users omit the exact details of their past operations because they no longer remember them, leaving the agent t

    First observed Nov 4, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

14. Named entityNewly observed

    Hera

    AI Creative Canvas

    First observed Nov 2, 2026 · Product Hunt

    7d mentions

    0 previous 1

    7d sources

    0

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

15. Named entityNewly observed

    karpathy/nanochat

    The best ChatGPT that $100 can buy.

    First observed Nov 2, 2026 · GitHub Trending

    7d mentions

    0 previous 0

    7d sources

    0

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

16. Named entityNewly observed

    Taurus

    arXiv:2611.00247v1 Announce Type: new Abstract: Dense labels of the aorta in CT are slow to draw, and the public aortic CT datasets that could stand in for them each label different structures under their own conventions. Large language model (LLM) agents can now write code and read images. We asked whether such a model labels these scans better as a free-fo

    First observed Nov 4, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

17. Named entityNewly observed

    Friday Work

    When Claude hits its limit, your task keeps going

    First observed Nov 2, 2026 · Product Hunt

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

18. ConceptNewly observed

    GRASP

    arXiv:2610.41081v1 Announce Type: new Abstract: We study the so-called Minimum Red''Blue Separating Set Problem (MRBSSP) which arises from computational geometry. In particular, we propose a compact Set-Cover ILP formulation, safe preprocessing rules, a Greedy Randomized Adaptive Search Procedure (GRASP), and two exact approaches: one is based on Logic-Based

    First observed Nov 3, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

19. Named entityNewly observed

    CalVLA

    arXiv:2611.00394v1 Announce Type: new Abstract: Can a vision-language-action (VLA) policy signal likely task failure from its own action probabilities? We introduce CalVLA, which shapes native action-token confidence using successful and failed rollouts and an Action-Confidence Alignment (ACal) squared margin-ranking loss. Low-rank adapters update OpenVLA-7B

    First observed Nov 4, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

20. Named entityNewly observed

    Agentic Curation

    First observed Nov 3, 2026 · Hacker News

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

21. Named entityNewly observed

    Xmind 2027

    Your mind map is now an AI thinking partner

    First observed Nov 2, 2026 · Product Hunt

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

22. Named entityNewly observed

    Cedric AI for Meetings

    The first AI agent to present your slides and attend for you

    First observed Nov 2, 2026 · Product Hunt

    7d mentions

    0 previous 1

    7d sources

    0

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

23. Named entityNewly observed

    mgantlett/nomos

    Hi HN, Mark here. If you've pointed Claude Code, Cursor, or OpenCode at a codebase you care about and walked away thinking AI coding tools are a net negative, I pretty much agree with you. Left directly on a working branch, models optimize for shutting the compiler up on the current turn. Hit a tricky failure and they delete the failing assertion, return a h

    First observed Nov 2, 2026 · Hacker News

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

24. ConceptNewly observed

    MRBSSP

    arXiv:2610.41081v1 Announce Type: new Abstract: We study the so-called Minimum Red''Blue Separating Set Problem (MRBSSP) which arises from computational geometry. In particular, we propose a compact Set-Cover ILP formulation, safe preprocessing rules, a Greedy Randomized Adaptive Search Procedure (GRASP), and two exact approaches: one is based on Logic-Based

    First observed Nov 3, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

25. ConceptNewly observed

    BBC

    arXiv:2610.41081v1 Announce Type: new Abstract: We study the so-called Minimum Red''Blue Separating Set Problem (MRBSSP) which arises from computational geometry. In particular, we propose a compact Set-Cover ILP formulation, safe preprocessing rules, a Greedy Randomized Adaptive Search Procedure (GRASP), and two exact approaches: one is based on Logic-Based

    First observed Nov 3, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

26. ConceptNewly observed

    LBBD

    arXiv:2610.41081v1 Announce Type: new Abstract: We study the so-called Minimum Red''Blue Separating Set Problem (MRBSSP) which arises from computational geometry. In particular, we propose a compact Set-Cover ILP formulation, safe preprocessing rules, a Greedy Randomized Adaptive Search Procedure (GRASP), and two exact approaches: one is based on Logic-Based

    First observed Nov 3, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

27. Named entityNewly observed

    要宣传视频

    之前在这里分享过 Pixsolo ，那时它基本只做一件事：App 上架截图，外加一个 AI 生图。 做 App 的时候，除了上架截图，还有一堆图片和视频的杂活：官网要样机图，发布要宣传视频，README 要演示 GIF ，素材要抠图、去杂物，偶尔还要处理拍歪的文件。这段时间我把这些都做成了工具，现在 Pixsolo 一共 10 个工具，新增 8 个。 https://www.pixsolo.com 新加的 5 个免费工具（不扣积分、不加水印，登录就能用） 设备样机 ：图片或录屏套进 iPhone / iPad / Mac / Apple Watch 的真实外壳，导出图片或最高 4K 的 MP4 。全程在浏览器本地处理，文件不上传 3D 设备样机 ：截图或录屏放进可以转动的 3D iPhone 17 Pro Ma

    First observed Nov 4, 2026 · V2EX

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

28. Named entityNewly observed

    FlashProve

    Called FlashProve, the system would let anyone check that an AI response really came from the model it claims to be from.

    First observed Nov 4, 2026 · TechCrunch

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

29. Named entityNewly observed

    Vercel

    First observed Nov 3, 2026 · Hacker News

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save

30. Named entityNewly observed

    Reimagining Text-to-SQL

    arXiv:2611.00171v1 Announce Type: new Abstract: Text-to-SQL systems translate natural language questions into executable SQL queries, democratizing access to relational data. Early approaches relied on handcrafted rules and template matching, while subsequent neural methods introduced encoder-decoder architectures, schema linking, and constrained decoding to

    First observed Nov 4, 2026 · arXiv

    7d mentions

    1 previous 0

    7d sources

    1

    7d growth

    Not comparable

    Priority

    37 / 100

    Save