1
2000+真实场景搬进仿真！一个导航模型零样本“通吃”四种机器人本体
亮源新创的Physical Al路线清晰了
2
ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations
免费开放的科研平台，让数字孪生仿真触手可及，还支持问卷模拟双模式。
arXiv:2608.20539v1 Announce Type: cross Abstract: Digital twin simulations show promise, but current empirical evidence suggests that the approach sho…
3
Show HN: 3D Engine for Rust Programs
Rust生态新3D引擎，集GUI与可视化于一体，适合仿真与科学计算场景。
I mostly stabilized the API for this 2 years ago. Since then, I've made occasional performance improvements, and feature additions. It's built to supp…
4
Eval4Sim: An Evaluation Framework for Persona Simulation
首个面向LLM人格模拟的评估框架，专测虚拟人设是否忠实还原真实人类行为。
arXiv:2603.02876v2 Announce Type: replace Abstract: Large Language Model personas, explicit profiles specifying a user's attributes, preferences, and …
5
π0引用的中国团队，又出手了：世界仿真器新作发布
给机器人造一个更接近真实的“第二世界”
6
Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement
用仿真反馈驱动大模型在上下文策略中持续优化模拟版图，为芯片设计自动化打开新思路。
arXiv:2608.13767v1 Announce Type: new Abstract: Analog IC layout design remains a labor-intensive iterative process dominated by simulation-driven ref…
7
PatientAct: Theory-Grounded Mental Health Client Simulation
基于理论的AI心理患者模拟，解决AI咨询师训练中“假病人”太合作的问题，还原真实心理诊疗场景。
arXiv:2608.12750v1 Announce Type: cross Abstract: LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapist…
8
Training and Benchmarking Code Generation for Physics-Inspired Animations
揭秘AI如何写物理动画代码，新基准测试与训练方法一睹为快。
arXiv:2602.10840v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, com…
9
算力需求两年涨10倍，机器人为了走进真实物理世界，正在疯狂「吃算力」
机器人吃算力两年猛涨10倍，云端仿真如何破解开发困局？这场黑客松给出了新打法。
少花一半成本，部署效率提升80%！机器人研发可以不用重复造轮子了。
10
Causal Falsification of Digital Twins
用因果推断给数字孪生做“证伪测试”，让仿真模型不再自说自话。
arXiv:2301.07210v5 Announce Type: replace-cross Abstract: Digital twins are simulation-based models designed to predict how a real-world process will …
11
12
13
Show HN: GJK Collision Detection in Any Dimension
专为开发者打造的高维碰撞检测库，将GJK算法推广到任意维度，统一单纯形距离计算，助力复杂物理仿真。
Hey HN! I created a library that extends GJK-based collision to higher dimensions. This approach unifies the math for computing the distance to the or…
14
What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents
用LLM代理模拟买卖双方全链路互动，揭开成交背后的零售动态密码。
arXiv:2604.04468v2 Announce Type: replace Abstract: Evaluating retail strategies before deployment is difficult, as outcomes are determined across mul…
15
LLMs struggle to simulate human belief updates in controlled environments
六款大模型模拟人类信念更新，一对一对照实验揭示仿真失真边界，社科实验需警惕AI替身风险。
arXiv:2607.28347v1 Announce Type: new Abstract: LLMs are increasingly deployed as proxies for human study participants in social science experiments, …
16
Large-Scale ChatBot Validation Through Customer Digital Twin Simulations
用客户数字孪生仿真技术，大规模验证聊天机器人可靠性，开创性评估方法
arXiv:2607.26060v1 Announce Type: cross Abstract: LLM-based chatbots are transforming customer service in regulated domains such as banking, but scala…
17
18
Show HN: I built a transparent terminal wrapper for unobtrusive AI
在终端中嵌入AI助手，不干扰原有操作，一键呼出智能辅助。
I wanted a way to use my existing AI subscriptions as a terminal assistant to analyze shell output or help me with a complicated awk incantation from …
19
Agentic Calibration of Grey-Box Simulation Models: An LLM-Driven Alternative
用大语言模型驱动代理agent替代传统校准方法，实现灰盒仿真模型的精准校准，打开科学计算新思路。
arXiv:2607.18308v1 Announce Type: cross Abstract: Calibration of grey-box simulation models is a constrained optimization problem in which model evalu…
20