今日必看

Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows

arXiv:2610.11482v1 Announce Type: cross Abstract: Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasize textual r

Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System

arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding agent and AI agent. Whether these labels de

From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents

arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated acr

Harness Evolution Hits a Ceiling: When Weight Training Should Begin

arXiv:2610.11655v1 Announce Type: new Abstract: Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the system stronger first, then cross seed and evolved harnesses with base and trained

Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?

arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but LLMs are evolving rapidly, so earlier performance claims may no longer accurate

MAP4CS: A Multi-dimensional Data Pruning Framework for Efficient Code Retriever Fine-tuning

arXiv:2610.11727v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers to evolving code repositories remains ch

NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime

arXiv:2610.10787v1 Announce Type: cross Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can unde

On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents

arXiv:2610.10833v1 Announce Type: new Abstract: We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productively. We evaluate Qwen3.6-27B on five competitions from MLE-B

RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation

arXiv:2610.11358v1 Announce Type: new Abstract: Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding agents and multi-model systems increasingly route a shared context across models: a user may switch models mid-session, or a cascade may escalate a dif

SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction

arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and interaction length. Code assistants require co

StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents

arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain static: the world moves only when the agent acts, the reward is a

TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution

arXiv:2610.10619v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all existing benchmarks still rely on the same decades-old criterion: a solution is corre

The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate

arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is rev

Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations

arXiv:2610.08364v2 Announce Type: replace Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-agent networks. The observability envelop-the range of what

OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences

arXiv:2610.11118v1 Announce Type: new Abstract: The next frontier for artificial general intelligence is tackling unresolved scientific problems, calling for benchmarks that assess progress beyond established knowledge. We introduce OpenProblemBench, a benchmark of 82 unresolved

Grok Bot 可做廉价 X 舆情与竞品监控

📌 一句话摘要 推文称 Grok Bot 可自主搜索、阅读并持续监控 X（行业动态、品牌评价、投诉、竞品），24 小时运行并每日早报，已含在现有付费套餐。 📝 详细摘要 「Grok Bot 刚刚成了最便宜的 X 研究分析师。」可自主搜索、阅读并持续监控：行业在发生什么、用户如何评价品牌、投诉扩大前发现、追踪竞品发布/趋势/爆款；24 小时运行，每天早上自动生成简报，且已包含在现有付费套餐中。 💡 主要观点 持续监控 X 行业、品牌评价、投诉、竞品。 早报自动化 24 小时运行，每天早上出简报。 套餐内含 称已包含在现有付费套餐。 💬 文章金句 Grok

CodeQL 2.27.2 improves C++, Go, Rust, and JavaScript analysis

CodeQL 2.27.2 is now available, adding a C++ regular-expression parser and analysis improvements across several languages. CodeQL is the static analysis engine behind GitHub code scanning, which helps you find and remediate security issues in your code. The Default suite runs 498

Maildun for Mac

Design on-brand emails by hand, with AI, or over MCP Discussion | Link

API Claws by Buda

Build self-improving agent harness with one API Discussion | Link

How Oracle turns days of work into minutes with ChatGPT and Codex

Across recruiting, engineering, and operations, Oracle turns specialist knowledge into fast, repeatable workflows with ChatGPT Work and Codex.

Grok Bot X Scan 图像查找功能演练出处链接

📌 一句话摘要 提供 X 平台利用 Grok Bot 进行复杂多图及病毒级推文快速搜索功能转引源。 📝 详细摘要 提供 Grok 展现多模态 meme 探索、最初起点查找等案例推文的具体出处，用以佐证功能的强悍和对媒体溯源机制的革新作用。 📊 文章信息 AI 初评： 76 来源： AI Will(@FinanceYF5) 作者： AI Will 分类： 个人成长 语言： 中文 阅读时间： 1 分钟 字数： 25 标签： 效率与成长 , 多模态 AI , 个人效率 , 推文串 , Elon Musk 阅读推文

X 平台开放 Grok Bot 图像与 Meme 追溯新特性

📌 一句话摘要 X 推出 X Scan 新功能，允许用户提供图片或视频单帧，由 Grok 自主追溯 Meme 源头及所有相关分类推文。 📝 详细摘要 指出 Grok Bot 新开发的 X Scan 在特定亚文化、社交传播和事实溯源层面的新机制。由于能直接分析图像和视频单帧，甚至能根据指令过滤出比如“所有用此图的 AI 推文”，极具研究价值。 💡 主要观点 多模态多维度反向检索工具将成为社群标配 图像与流行要素的自动跨链路追溯能使普通用户迅速看清热点成因与传播分支，大幅减少信息茧房效应。 📊 文章信息 AI 初评： 85 来源： AI Will(@Fina

AI Is Getting Good at Messing with Cybercriminals

I expect rapid progress but not towards general superintelligence

I’ve often been surprised when I hear from top researchers in industry that they think AI will be better than them at their job in a few years, and I didn’t really know why I doubted it. The explanation I arrived at is that researchers are seeing this massive acceleration in the