TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

ArXi:2605.13414v1 Announce Type: new Deploying language models as autonomous agents requires than per-task accuracy: when an agent faces a queue of problems under a finite token budget, it must decide which to attempt, in what order, and how much compute to commit to each, all before any execution feedback is available. This is the prospective form of metacognitive control studied for decades in human cognition, yet whether language models possess it remains untested. We