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
Executable World Models for ARC-AGI-3 in the Era of Coding Agents
提出可执行世界模型方法，在编码代理时代攻克ARC-AGI-3挑战，为通用人工智能探索新路径。
arXiv:2605.05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executabl…
3
Show HN: AgentToolBench-Code – security benchmark for AI coding agents
首个针对AI编码智能体的安全基准测试，助你评估模型在代码生成中的安全防护能力。
Article URL: https://gist.github.com/allenwu-blip/fa2bd0218b93a1d7aef765817e3c6608 Comments URL: https://news.ycombinator.com/item?id=48274727 Points:…
4
Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery
深入评估编码智能体在数据驱动科学发现中的记忆压缩策略，为AI辅助科研提供新思路。
arXiv:2605.18854v1 Announce Type: new Abstract: Coding agents accumulate extensive context during long-running tasks, yet fixed context windows force …
5
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
全新基准测试聚焦代码智能体在连续软件包版本升级中的能力，比单次任务更贴近真实维护场景。
arXiv:2605.14415v1 Announce Type: cross Abstract: Coding agents powered by large language models are increasingly expected to perform realistic softwa…
6
Coding Agent Is Good As World Simulator
一种通过代码生成构建物理世界模型的智能体框架，利用规划、编码、视觉审查和物理分析代理迭代修正，确保模拟的物理真实性和指令符合度，首次从底层解决了视频世界模型“有形无实”的缺陷。
arXiv:2605.14398v1 Announce Type: new Abstract: World models have emerged as a powerful paradigm for building interactive simulation environments, wit…