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
Show HN: Referee.Chat - Set the goal. An AI panel works. Referee clears it done
设定目标，AI评审团分工协作，实时查证文献并核对数字，让结果可追溯、可验证。
Article URL: https://referee.chat/ Comments URL: https://news.ycombinator.com/item?id=49293191 Points: 3 # Comments: 0
3
4
JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation
LLM裁判评估生态碎片化？JudgeArena统一框架实现可复现评测。
arXiv:2608.02620v1 Announce Type: new Abstract: LLM-as-a-judge evaluation has become a dominant paradigm for ranking language models, yet the ecosyste…
5
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…
6
Kimi K3 vs Claude Fable 5 and Opus 4.8: a benchmark you can run yourself
自己动手跑基准测试，公平对比Kimi K3与Claude系列，结果不含糊。
Kimi K3 was released this week, and like every model release it's being judged on leaderboard scores and screenshots. But a score is a bit like a foot…
7
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 …
8
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
将论文中的越狱攻击方法转化为可复现的基准测试，填补了LLM安全领域从理论到实践的缺口。
arXiv:2602.24009v4 Announce Type: replace-cross Abstract: Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making …
9
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…
10
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 …
11
Show HN: Open Science, open-source alternative to Claude Science
对抗AI研究封闭化，开源、本地优先、模型无关的科研工作台，MIT许可，完全可复现。
Claude Science just launched. It’s a sign AI research is moving toward centralized, closed systems. So we built the opposite: Open Science: a local fi…
12
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…
13
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…
14
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…
15
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…
16
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…
17
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing
RouteJudge平台让LLM路由可复现且感知用户偏好，有助于精准高效地选择模型，已被ICML 2026研讨接收。
arXiv:2606.18774v1 Announce Type: new Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, wit…
18
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…
19
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…
20
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling
可复现且可靠的声明式模型权重操作方法，为AI模型编辑与升级提供新范式
arXiv:2606.09707v1 Announce Type: new Abstract: As deep learning models scale, managing, inspecting, and modifying large checkpoints has become increa…