Off-Trajectory Reasoning: Can LRMs Collaborate on Reasoning Trajectory?

Reasoning LRMs are trained to verbalize their thinking process, leading to strong gains on complex tasks. This transparency also opens a promising direction: multiple reasoners can directly collaborate on each other's thinking on a shared trajectory, yielding better inference efficiency and exploration. A key prerequisite, however, is the ability to assess usefulness and build on another model's partial thinking -- we call this off-trajectory reasoning. Our paper investigates a critical question: can standard solo-reasoning training pipelines yield desired off-trajectory behaviors? We propose twin tests that capture the two extremes of the off-trajectory spectrum, namely Recoverability, which tests whether LRMs can backtrack from "distractions" induced by misleading reasoning traces, and Guidability, which tests their ability to build upon correct reasoning from stronger collaborators. Our study evaluates 15 open-weight LRMs (1.5B--32B) and reveals a counterintuitive finding -- "stronger" LRMs on benchmarks are often more fragile under distraction. Moreover, all models tested fail to effectively leverage guiding steps from collaborators on problems beyond their inherent capabilities, with solve rates remaining under 9.2%. Finally, we conduct control studies to isolate the effects of three factors in post-training on these behaviors: the choice of distillation teacher, the use of RL, and data selection strategy. Our results provide actionable insights for training natively strong reasoning collaborators; e.g., we find that sub-optimal recoverability behaviors of teacher models are transferred to distilled students even if the distilled data trajectories are correct. This work lays the groundwork for evaluating multi-model reasoning collaboration and reveals limitations of off-the-shelf LRMs.