CONDESION-BENCH: Conditional Decision-Making of Large Language Models in Compositional Action Space

ArXi:2604.09029v1 Announce Type: cross Large language models have been widely explored as decision- tools in high-stakes domains due to their contextual understanding and reasoning capabilities. However, existing decision-making benchmarks rely on two simplifying assumptions: actions are selected from a finite set of pre-defined candidates, and explicit conditions restricting action feasibility are not incorporated into the decision-making process. These assumptions fail to capture the compositional structure of real-world actions and the explicit conditions that constrain their validity.