清华姚期智团队新作：代数世界模型，让AI像牛顿一样思考
姚期智团队搞了个新框架，思路挺有意思：让AI不从数据里硬拟合，而是像牛顿那样从观测中总结出规律本身。
清华大学姚期智团队提出“代数世界模型”新框架。核心思路是让AI不靠堆数据拟合，而是像牛顿从观测中提炼万有引力定律那样，从数据中归纳出代数化的规律表达。该方法面向世界模型的构建方式，强调符号化推理与规律发现。
清华姚期智团队新作：代数世界模型，让AI像牛顿一样思考
让AI像牛顿一样思考
The deferral-first training trick is the transferable idea: rather than letting an agent freely rewrite rankings, PAMO rewards overrides only when they preserve accuracy. Developers building recommendation or agent systems can apply the same counterfactual masking to any cross-context personalisation task. It also frames the privacy tension of pooling history across apps, a question regulators and platform teams will face as personal agents spread.
The finding reframes novelty filtering as a recall-versus-precision tradeoff: checking whole proposals punishes incremental builds on prior work, which is how most real papers actually happen. Anyone running an automated research-idea pipeline can adopt the claim-level scoring method directly, keeping proposals that extend one known result. The 96%-versus-1.5% rejection gap gives a concrete benchmark for auditing your own filter.
DeepMind 让模型在模拟病人身上练问诊，漏报急性风险从 30.5% 降到 12.9%，做医疗 Agent 的可以看看方法。
The practical shift is reframing skill screening: prompting the scanner LLM to look for missing human oversight outperforms framing the task as malware detection, both in recall and precision. Teams deploying agents that load shared skills should audit their SKILL.md files now and scope every "don't ask" instruction to a specific context like CI. This matters for anyone building on Claude, Codex or other agents that support skills.
The key insight is that memory design, not memory size, is the bottleneck: a single global history barely helps interleaved workloads, while clustering trajectories delivers double-digit reward gains at lower cost. Teams building agents for mixed task streams can try splitting memory into clusters before investing in larger memory systems. One open question the paper leaves untested is whether parallel agents can safely update a shared cluster.
