SOURCE-LINKED INTELLIGENCE

TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advantage: establishing the true cause of an anomaly often requires costly expert investigation and may remain ambiguous after the fact. We ask whether this asymmetry of verification can instead be engineered. We sample an intervention, inject it into a controlled simulator, and generate the observations it would produce. The hidden intervention provides an oracle

Read original source ↗ Open in workspace

recordType

paper

region

Global