1
Bayesian control for coding agents
贝叶斯控制理论为代码生成代理注入概率推理，提升行为可靠性与稳定性
arXiv:2606.24453v1 Announce Type: new Abstract: Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive…
2
Tech pundit Cringely cofounds startup '2Brains Inc' to solve LLM hallucinations
科技评论家Cringely联手创办2Brains Inc，专攻大模型“幻觉”难题
Article URL: https://slashdot.org/story/26/06/20/0556251/tech-pundit-cringely-co-founds-startup-2brains-inc-to-solve-llm-hallucinations Comments URL: …
3
Probably raises $9M to build a more reliable kind of AI
初创公司Probably获投900万美元，打造更可靠的AI错误检测引擎，可扩展至会计医疗等领域。
Probably wants to prevent hallucinations and factual errors from reaching users, and achieve accuracy on par with deterministic systems.
4
Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?
大模型能否胜任医生角色的关键考验：最新研究实探LLM在医疗诊断与临床推理评分中的准确性。
arXiv:2604.14892v3 Announce Type: replace-cross Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating t…
5
Human-AI Teaming Through the Lens of Calibration
从校准视角重新审视人机协作，揭示AI预测可靠性如何影响团队决策效率与信任。
arXiv:2606.10906v1 Announce Type: cross Abstract: We study models for human-AI teaming through the lens of statistical calibration. We assume the team…
6
ReclAIm: A Multi-Agent Framework for Monitoring and Correcting Performance Decline in Medical Imaging AI
多智能体框架实时监测并纠正医疗影像AI的模型退化和性能衰退，为临床AI可靠性保驾护航。
arXiv:2510.17004v2 Announce Type: replace-cross Abstract: Purpose: To develop and evaluate a multi-agent framework (ReclAIm) for automated monitoring,…
7
Trust, but Don't Verify: Epistemic Blind Spots in LLM Source Evaluation
揭示大模型在信息验证中的致命盲点：为何AI会轻易信任却放弃核查来源？
arXiv:2606.05403v1 Announce Type: cross Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources t…
8
A Taxonomy of Runtime Faults in Model Context Protocol Servers
首次系统分类MCP服务器运行时故障，揭示LLM工具化过程中的可靠性关键挑战。
arXiv:2606.05339v1 Announce Type: cross Abstract: MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools an…
9
Human Psychometric Questionnaires Mischaracterize LLM Behavior
人类心理问卷真的能测准大模型行为？这项研究用八个开源模型揭开了方法论缺陷。
arXiv:2509.10078v4 Announce Type: replace-cross Abstract: We examine whether human psychometric questionnaires can serve as reliable tools for charact…
10
Auditing LLM Benchmarks with Item Response Theory
用项目反应理论深度剖析LLM基准测试，揭示评估偏差与模型能力真实度量。
arXiv:2605.30504v1 Announce Type: new Abstract: LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors …
11
Ask HN: Is anybody providing deterministic LLMs?
探讨大语言模型确定性输出的可行性与现状，引发对AI可靠性的思考
Comments URL: https://news.ycombinator.com/item?id=48325265 Points: 4 # Comments: 8
12
Claude Opus 4.8 上线：提升 AI 编程可靠性，减少无依据结论
Claude Opus 4.8 更可靠、少幻觉，还能主动纠错，并上线安全漏洞检测工具
IT之家 5 月 29 日消息，Anthropic 今天（5 月 29 日）宣布推出旗舰新模型 Claude Opus 4.8， 主打更强的智能体编程、多领域推理和知识工作能力。 官方表示，相比较 Opus 4.7 模型，本次 Opus 4.8 更新幅度较小，在保持价格不变的情况下，主要提升编程、智…
13
Rust Will Save Linux from AI, Says Greg Kroah-Hartman
Linux内核维护者称Rust可消除超60%安全漏洞，对抗AI时代新挑战。
Article URL: https://www.zdnet.com/article/rust-will-save-linux-from-ai-says-greg-kroah-hartman/ Comments URL: https://news.ycombinator.com/item?id=48…
14
MemFail: Stress-Testing Failure Modes of LLM Memory Systems
用压力测试方法系统揭示LLM记忆系统的关键失效模式，为改进大模型记忆能力提供实证依据。
arXiv:2605.26667v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external memory systems to remain consistent ac…
15
How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective
从不确定性量化角度，首次系统评估LLM在替代人类调查受访者时的可靠性边界，为AI调研应用提供严谨方法论。
arXiv:2502.17773v5 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate survey responses, but synthet…
16
Measuring and mitigating overreliance to build human-compatible AI
探讨如何量化并缓解人类对AI的过度依赖，为构建真正人机兼容的智能系统提供新思路
arXiv:2509.08010v2 Announce Type: replace-cross Abstract: Large language models (LLMs) distinguish themselves from previous technologies by functionin…
17
Why language models hallucinate
OpenAI最新研究揭示语言模型幻觉根源，用更优评估提升AI可靠性与安全性。
OpenAI’s new research explains why language models hallucinate. The findings show how improved evaluations can enhance AI reliability, honesty, and sa…