Primary sourcearXiv cs.AI
View sourceEvent ·Multi-source
Coding Agents 在广义任务与运动规划上超越手工规划器
论文测试 Claude Code(Opus 5)和 Codex(GPT-5.6 Sol、GPT-6 Astra)能否自动合成可跨实例泛化的任务与运动规划(TAMP)程序。评估覆盖 KinDER 和 PDDLStream 的 28 个模拟环境,共 980 个程序、98,000 个评估回合。在 16 个有规划器可用的环境中,三种编码智能体配置平均成功率达 56% 到 95%,高于手工规划器的 47%。随着物体数量增加,智能体程序保持更高成功率,每个实例平均计算量低一个数量级。论文已公开全部代码和提示词。
Current read
有人拿 Claude Code 和 Codex 写规划程序,成功率达 95%,比手工规划器高还省十倍算力,代码和提示词全开源了。
11 sources58° AI heatLast updated 2026/9/24 17:53:35
Evidence
11 sourcesRelated source 1Tw93
View sourceRelated source 2宝玉
View sourceRelated source 3Blognone
View sourceRelated source 4shao__meng
View sourceRelated source 5lmarena.ai
View sourceRelated source 6SuperTechFans
View sourceRelated source 7Artificial Analysis
View sourceRelated source 8Jerry Liu
View sourceRelated source 9Simon Willison’s Weblog
View sourceRelated source 10orange.ai
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.