Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning 事件

Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuning arXiv:2602.00994v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a single set of parameters to support both reasoning and tool-use behaviors, implicitly assuming that joint training leads to improved overall agent performance. Despite its