Operational Proto-Introspection in Looped Language Models: Process-Quality Taps, Executable Branching, and the Readout-Control Boundary

Abstract:Can a language model read the quality of ongoing computation, and can an external intervention turn that readout into better outcomes? We test both questions in a frozen 2.6B looped transformer, Ouro-RLTT. On GSM8K, a strict pre-answer probe excludes the answer region and gold value yet predicts eventual success: hidden states plus length and log-probability shortcuts reach AUROC 0.797, versus 0.731 for the shortcuts alone (incremental +0.066; task-clustered 95% CI [+0.021, +0.112]; 170 tasks, 680 candidates). Low-capacity taps also read role-specialized properties: task-disjoint branch survival reaches 0.9697 oracle retention, content ranking reaches 0.6310 macro top-1, and generated-branch correctness reaches AUROC 0.7755. A non-looped control replicates a candidate-quality readout, so recurrence is not required for every signal. We build branch/carry/prune machinery over Ouro's 192-slot recurrent cache, including branch-specific cache lineage and a bit-exact residual-capture splice that recomputes only the affected suffix and saves up to 88% of per-branch layer passes. No frozen intervention produces a validated capability gain. Directional steering is an established negative; a four-task matched-sampling comparison removes evidence for a frozen-fork gain but cannot estimate a general deficit; terminal selection remains unresolved and underpowered; and bounded LoRA changes surface behavior without improving net reachability. A two-null audit does not support the simplest span-misalignment explanation. We call this readable-but-not-yet-usable property operational proto-introspection. The model is not consulting our probes: we read its hidden trajectories, and our interventions fail to convert those readouts into validated capability. The pre-answer result is limited to one domain. Load-bearing values use source-item-disjoint splits and antisymmetrized evaluation where applicable.

49 pages, 8 figures. Paper 1 of a two-paper series; companion methodology paper submitted separately

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2607.18553 [cs.LG]

(or arXiv:2607.18553v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.18553 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.