arXiv ·
SteerSearch: Interactive Search Reasoning with Mid-Response Steering
Public paper from arXiv. Open the source to read the full record.
Home / Browse
All stories
Browse every indexed public story, including items outside the main categories.
10330 public stories
arXiv ·
Not Every User Says It All: Training Tool-Using Agents Beyond Ideal Simulated Users
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Who Speaks, Who Authorizes, Who Acts? Understanding Trust Boundaries in Multi-Agent LLMs
Public paper from arXiv. Open the source to read the full record.
arXiv ·
CME-SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
Public paper from arXiv. Open the source to read the full record.
arXiv ·
The Judge Can Debias Itself: Awareness and Self-Debiasing for Reliable LLM-as-a-Judge
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Continuous Ontology Assurance through External Resources -- An Ontology Engineering Method with a Case Study in Software Language Engineering
Public paper from arXiv. Open the source to read the full record.
arXiv ·
Screening LLM Judges Without Ground Truth: A Preliminary Evaluation of an AI Dental Hygiene Coach
Public paper from arXiv. Open the source to read the full record.
arXiv ·
FlashRT-PAI: Fast Kernels Are Not Fast Pipelines for Physical AI Inference
Public paper from arXiv. Open the source to read the full record.
Hacker News ·
Should agent-memory benchmarks test stale information?
Hacker News recorded 2 points and 0 comments as of Oct 20, 2026 (UTC).
GitHub Issues ·
Strict-mode msgpack deserialization admits Send/Command/Overwrite control types before the allowlist check
Public issue #9356 in langchain-ai/langgraph. The source issue contains the full report and discussion.
Product Hunt ·
Lugh Xtudio
The video studio where AI agents edit with you
Hacker News ·
Show HN: Search for AI-agents and usefulness score
Hacker News recorded 1 points and 0 comments as of Oct 20, 2026 (UTC).
Product Hunt ·
Intel® GPU D-series
Public release from Product Hunt. Open the source to read the full record.
V2EX ·
[推广] 1024 程序员节，我们做了个可以通过 SSH 连接的抽奖小游戏
Public article from V2EX. Open the source to read the full record.
V2EX ·
[问与答] 差点被开门杀
Public article from V2EX. Open the source to read the full record.
V2EX ·
[全球工单系统] 有京东的同事吗, 怎么一周不发货呀, 还整天搪塞我呀?
Public article from V2EX. Open the source to read the full record.
V2EX ·
[推广] GPT Codex Business Team - 按月付 - 席位稳定 - 有质保 - 车位目前不多
Public article from V2EX. Open the source to read the full record.
V2EX ·
[问与答] 在 R2 上挂一个自托管 Releases 下载页
Public article from V2EX. Open the source to read the full record.
V2EX ·
[分享创造] 在 YouTube 听英文播客练听力，一听两小时有点闷，我给字幕加了一只猫
Public article from V2EX. Open the source to read the full record.
V2EX ·
[问与答] 观刘慈欣、孙宇晨访谈有感：如何保持身体健康、尽量让自己活的久一点
Public article from V2EX. Open the source to read the full record.
V2EX ·
[分享创造] [签到助手] 批量自动打开不同网页模拟点击签到
Public article from V2EX. Open the source to read the full record.
V2EX ·
[程序员] 求推荐 mac 型号，或收台二手的 mac
Public article from V2EX. Open the source to read the full record.
V2EX ·
[程序员] cursor devin 订阅都没法用 visa 银联卡付，有稳定质保的代充渠道么？
Public article from V2EX. Open the source to read the full record.
V2EX ·
[问与答] 这年头 windows 的软件高频率扫盘行为是不是有点泛滥啊
Public article from V2EX. Open the source to read the full record.
V2EX ·
[分享创造] [iOS] 做了一个安静的本地 TXT 小说阅读器：月读，无广告、不用注册、iCloud 同步
Public article from V2EX. Open the source to read the full record.
V2EX ·
[Apple] 升级到 MacOS 27 以后， AirPods 连接 Mac 音量自动调整到 50% 的 bug 似乎没有了
Public article from V2EX. Open the source to read the full record.
TechCrunch ·
Walmart’s Flipkart is quietly building a food delivery challenger in India
Public article from TechCrunch. Open the source to read the full record.
V2EX ·
[问与答] 司美格鲁肽可能致盲?
Public article from V2EX. Open the source to read the full record.
V2EX ·
[分享创造] [开源] All API Hub：统一管理 AI 中转站账号、API Key、自动签到和模型比价
Public article from V2EX. Open the source to read the full record.
V2EX ·
[问与答] 部署在 cloudflare 上的 Pages 有 0 成本的方式让中国大陆用户访问吗？
Public article from V2EX. Open the source to read the full record.