Agents Learn Their Runtime: Interpreter Persistence as Training-Time Semantics
arXiv:2603.01209v1 Announce Type: new Abstract: Tool-augmented LLMs are increasingly deployed as agents that interleave natural-language reasoning with executable Python actions, as in CodeAct-style frameworks. In …
Victor May, Aaditya Salgarkar, Yishan Wang, Diganta Misra, Huu Nguyen
8 views