Pai 的 AI 雷达

今日必看

含近几日仍热话题，按时间衰减排序。今天先看 YouMind-OpenLab/awesome-seedance-2-prompts，其次 Show HN: Convertix – A free, client-side QR code generator with customization。并行还有 Hackers abuse Google Ads, Bing redirects to push Claude ClickFix attacks、BetaStreetOmnis/xhs_ai_publisher。

日期
2026/10/11
今日条目
97
往期2026/10/11
全部97编码代理21Agent与工具8个人助理6模型与评测30创作成片11开发与开源4产品接入17
领域机器人具身3生信医疗3金融2安全治理1行业观察9独立开发1

更多资讯

#48

Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking

arXiv:2610.10628v1 Announce Type: cross Abstract: Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing the full potential of multi-agent systems. Meanwhile, availa

推荐理由Agent4RE: A Self-Refining Multi-agent：arXiv:2610.10628v1 Announce Type: cross Abstract: Existing LLM-based approaches。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#49

Agentic-TTT: Training test-time policy for test-time training

arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment e

推荐理由Agentic-TTT: Training test-time policy：arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#50

Beyond Direct Access: Resource Hijacking in LLM Agents

arXiv:2608.15108v2 Announce Type: replace-cross Abstract: Large language model agents are increasingly connected to high-value resources, including external APIs, GPUs and servers, and workflows such as deployment and approval. Existing agent security research mainly focuses on a

推荐理由Beyond Direct Access: Resource：arXiv:2608.15108v2 Announce Type: replace-cross Abstract: Large language model agents。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#51

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

arXiv:2607.10169v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily

推荐理由Beyond Euclidean Clipping: Overcoming：arXiv:2607.10169v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL)。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#52

Beyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review

arXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality and increasing reviewer workload. Large language models (LLMs) have been proposed

推荐理由Beyond Imitation: A Framework：arXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#53

Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation

arXiv:2610.10604v1 Announce Type: cross Abstract: When generating verifiable code, natural language requirements are mapped to machine checked code using LLMs and agentic workflows. A crucial component of this pipeline is specification generation (SpecGen), which produces a forma

推荐理由Beyond Type-checking: Towards Holistic：arXiv:2610.10604v1 Announce Type: cross Abstract: When generating verifiable code。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#54

Closed-loop evaluation of LLM agents for embedded software development

arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is a demanding target because correctness

推荐理由Closed-loop evaluation of LLM agents：arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文
#55

Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction

arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason over it in natural language. However, reinforcement learning

推荐理由Coverage-Aware Reasoning with Medical：arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer。
模型与评测生信医疗arXiv cs.AI 官方
arxiv.org打开原文
#56

Does Rank Still Matter? Position Bias When AI Agents Shop on Our Behalf

arXiv:2608.22697v4 Announce Type: replace Abstract: When shopping is delegated to AI agents, it is unclear whether the ranking advantage documented for humans persists. Across 7,000 sessions with five large language models (LLMs) and varying reasoning effort, we compare AI agents

推荐理由Does Rank Still Matter? Position Bias：arXiv:2608.22697v4 Announce Type: replace Abstract: When shopping is delegated to AI。
模型与评测arXiv cs.AI 官方
arxiv.org打开原文