今日必看

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

arXiv:2610.18829v1 Announce Type: new Abstract: With the rapid development of multimodal large language models (MLLMs), evaluating their video understanding capabilities has become increasingly important. Existing video understanding benchmarks cover only part of the evaluation d

The EU’s next chapter in AI is agentic

New analysis shows how agentic AI adoption is growing across EU enterprises and small businesses—and where deeper use could unlock more value.

影视飓风 AI 实战课推荐

📌 一句话摘要 推荐影视飓风推出的零基础 AI 生图与视频生成实战课。 📝 详细摘要 该推文简要推荐了影视飓风的 AI 实战课，涵盖生图、视频生成和提示词工程，强调其首日销量突破 10 万份，适合零基础入门用户。 📊 文章信息 AI 初评： 65 来源： LanfAI(@Huahuazo) 作者： LanfAI 分类： 人工智能 语言： 中文 阅读时间： 1 分钟 字数： 75 标签： AI 与智能应用 , 多模态 AI , 学习方法 , 提示工程 , 推文串 阅读推文

SentinelOne cuts malware analysis from weeks to hours

With OpenAI Daybreak, SentinelOne cuts weeks of malware analysis to hours, creating capacity to investigate more threats.

Putting Earth AI to work: Geospatial agents for our planet's biggest challenges

A Self-Defining Operator for Distributed Applications

arXiv:2610.14547v1 Announce Type: cross Abstract: To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but unlike experienced human operators they do not improve as they handle more incid

AIRRI: Towards a Human-Readable, Machine-Resistant Reading Interface

arXiv:2610.18724v1 Announce Type: new Abstract: The rapid advancement of image-to-text extraction systems and large language models (LLMs) poses new challenges for educational assessment by making assignment materials easy to transcribe and solve with minimal human effort. To add

Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study

arXiv:2610.14238v1 Announce Type: cross Abstract: LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a natural setting for AI-for-AI (AI4AI) research. Can agents use experimental feedbac

Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given

arXiv:2610.16911v1 Announce Type: new Abstract: Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding agents, we test the impact of providing two types of resources (an external codebase and benchmark tran

AuthGateBench: Benchmarking LLMs as Authorization Gate

arXiv:2610.16426v1 Announce Type: new Abstract: Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a large language model (LLM). Such systems, adopted in tools lik

Bench2Robust: Scenario-Controlled Recovery for Tool-Using Agents

arXiv:2608.11977v2 Announce Type: replace Abstract: Tool-using LLM agents are typically developed and post-trained in controlled environments with reliable tools, but deployment exposes them to tool failures, API and schema drift, and third-party services outside the developer's

Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs

arXiv:2609.32807v2 Announce Type: replace Abstract: Clinical LLM evaluation often emphasizes answer accuracy; however, accuracy alone does not test counterfactual consistency or demographic robustness. We evaluated six LLMs on 150 MedQA USMLE questions using two automated perturb

Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures

arXiv:2609.27773v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents into harmful executions. However, most evaluation frameworks focus only on

Coding LLMs Can Be Harnessed to Learn Interpretable Models from Data

arXiv:2610.14006v1 Announce Type: cross Abstract: Since compact, interpretable classifiers correspond to simple programs, it is natural to ask if LLM-based coding agents can be used to learn interpretable models from data. In this paper we present a simple harness that repeatedly

Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules

arXiv:2610.14216v1 Announce Type: cross Abstract: Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automatically when the agent reads matching files. We call these fil

Coupled Harness--Model Evolution for Scientific Equation Discovery

arXiv:2610.17740v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's t

Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher

arXiv:2610.18262v1 Announce Type: cross Abstract: Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such instructions in skill files for agents to decode and follow. We evaluate Caesar

FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation

arXiv:2610.18430v1 Announce Type: cross Abstract: Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits. However, this setting is highly vulnerable to backdoor attac

FleetPilot: Fine-Grained Steering Empowers Real-World LLM Personalization

arXiv:2610.14970v1 Announce Type: new Abstract: With the rapid evolution of large language models (LLMs), there is an increasing demand for effective personalization techniques that can adapt model behavior to individual user preferences. Personalized LLMs must infer a user's que

Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses

arXiv:2610.15150v1 Announce Type: new Abstract: Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches, however, largely optimize a single objective and evolve the

Heterogeneous Agentic Coevolution

arXiv:2610.16078v1 Announce Type: new Abstract: Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rely on specialized foundation models that possess strong domai

Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering

arXiv:2610.14960v1 Announce Type: cross Abstract: Can an autonomous AI agent reverse engineer a binary as well as a skilled human analyst? Do they adopt the same strategy, and can agents scale to real-world programs? We compare human and LLM-based software reverse engineering (SR

Interaction-as-a-Judge

arXiv:2610.17895v1 Announce Type: cross Abstract: Coding agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications interactively, current automated LLM evaluations primarily fo

LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation

arXiv:2610.16625v1 Announce Type: new Abstract: Post-route FPGA timing closure remains expert-dependent and computationally expensive. We present LATCH (LLM-Assisted Timing Closure Harness), a two-layer framework that separates large language model (LLM) orchestration from determ