1
Ressearch AI
为科研打造的AI工作空间，让实验可复现、成果更可靠，科研党值得一试。
AI workspace for reproducible scientific research Discussion | Link
2
3
Show HN: Reproducibility Benchmark a Risk Quantitative Model
开源风险量化模型可复现性基准工具，助力模型审计与验证
Article URL: https://github.com/Fluxara-GOD/fluxara1-audit-verification-pack Comments URL: https://news.ycombinator.com/item?id=49055927 Points: 3 # C…
4
Deterministic Replay for AI Agent Systems
探索AI代理系统中的确定性重放技术，解决大语言模型场景下的可复现与调试难题。
arXiv:2607.16200v1 Announce Type: new Abstract: AI agent systems that couple large language models (LLMs) with external tools and APIs are inherently …
5
Why LLM Decisions Should Be Deterministic
LLM决策的确定性边界关键不是一致性，而是可审计性——每个决策都有可复现的实现。
TL;DR: I originally treated deterministic boundaries around LLMs as a consistency mechanism. I now think their real value is auditability. If the syst…
6
Gypscie: A Cross-Platform AI Artifact Management System
跨平台AI工件管理系统Gypscie，统一管理实验产物，提升AI开发效率与可复现性。
arXiv:2604.10311v2 Announce Type: replace Abstract: Artificial Intelligence (AI) models, encompassing both traditional machine learning (ML) and more …
7
Don't let AI fill in all the important blanks
AI填补空白时，你是在利用杠杆还是逃避思考？关键处亲自动手才能保住可复现性。
Article URL: https://www.0xsid.com/blog/dont-let-ai-fill-all-the-blanks Comments URL: https://news.ycombinator.com/item?id=48751035 Points: 2 # Commen…
8
Necessary but Not Sufficient: Temperature Control and Reproducibility in LLM-as-Judge Safety Evaluations
零温度≠确定性，揭秘大模型裁判在安全评估中的隐藏变量，影响部署决策的严谨性。
arXiv:2606.26185v1 Announce Type: new Abstract: LLM-as-judge ("grader") components are now standard in evaluation harnesses, including safety evaluati…
9
Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models"
复现AlphaEdit知识编辑方法，验证零空间约束在大模型事实修正上的实效与局限
arXiv:2606.26783v1 Announce Type: new Abstract: Fang et al. (2025) introduced a null-space constrained projection, named AlphaEdit, for locate-then-ed…
10
Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL
LLM推理的数值不稳定是隐藏陷阱？HEAL方法为关键任务带来可复现推理，值得技术人深读。
arXiv:2606.21023v1 Announce Type: new Abstract: As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law…
11
A Reproducible Semantic Benchmark for Multivendor DSM-to-CLI Translation
网络设备配置翻译迎来可复现基准，多厂商DSM转CLI的语义评测新标准，用AI打通状态模型与命令行鸿沟。
arXiv:2606.20564v1 Announce Type: cross Abstract: Translating high-level network intents into correct multivendor configurations remains a central cha…
12
SafeRun: Enabling Determinism in LLM Planning for Running
ICML 2026 workshop论文，聚焦如何让LLM在跑步规划中摆脱随机性、实现可复现的确定性输出，提升安全性与可靠性。
arXiv:2606.09027v1 Announce Type: new Abstract: Large Language Models enable flexible natural-language planning but remain unreliable in determinism-c…
13
VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents
VisualLeakBench 为视觉语言代理提供可复现的动作边界传播失败评估，帮助研究人员系统检测和修复模型漏洞。
arXiv:2606.07595v1 Announce Type: new Abstract: Vision-language agents increasingly consume screenshots, documents, and user interfaces before writing…
14
Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds
从Copyleft到AGI可复现构建，重新定义AI开源许可的演进方向。
arXiv:2606.03019v1 Announce Type: cross Abstract: Copyleft, as implemented in licenses such as the GNU General Public License, was a legal hack that u…
15
From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents
一项可复现、可验证的评估框架，让工具调用型LLM智能体的性能对比不再模糊。
arXiv:2605.15104v2 Announce Type: replace Abstract: Voice agents increasingly require reliable tool use from speech, whereas prominent tool-calling be…
16
Hawkeye: Reproducing GPU-Level Non-Determinism
揭秘GPU计算的黑箱，在CPU上精确复现NVIDIA矩阵乘法，解决机器学习非确定性难题。
arXiv:2603.20421v2 Announce Type: replace-cross Abstract: We present Hawkeye, a system for analyzing and reproducing GPU-level arithmetic operations. …