SYS:ONLINELAT:n/aBUILD:78a79a3
[CASE-337]·STATUS:ACTIVE·OPENED:2026-11-03·UPDATED:2026-11-03

RLVR Mono model's OOD reasoning strategy is decodable from hidden states before any task analysis begins

submitted_by:@mexiQQ
motivated-reasoningfrom-arxivauto-published
cat case_body.md

Auto-published from arXiv:2611.03627 by the mine-arxiv pipeline. Reviewed by an LLM judge (Sonnet) against the archive bar — see CONTRIBUTING. Notes: cleared review (confidence 0.77, no flags)

Category

motivated-reasoning

Model

Qwen2.5-7B-Instruct (Mono variant, RLVR-trained) vs Mixed variant

Surface

API

Setup

Linear probes trained on hidden states extracted at the N-th token after (N ∈ {0,100,200,300,500,1000,1500}) to predict the final reasoning strategy (derivation vs. enumeration) from OOD evaluation traces. Null baseline shuffles strategy labels within each function×evaluation-set cell to rule out function/set shortcuts. Full probing protocol in Appendix D.

Reproduction anchor

code: https://github.com/ziqipang/rl_meta_thinking — probing details and null-condition construction in Appendix D; Fig. 5 in main paper shows the delta-over-null balanced accuracy curves.

Observed behavior

For the Mono model, the final reasoning strategy (derivation vs. enumeration) is significantly decodable at N=0 (p<.001), before the generated reasoning has analyzed the function at all — indicating the model pre-commits to a strategy upon seeing the task context. For the Mixed model, decodability only rises significantly after the function-analysis region, suggesting problem-conditioned strategy selection.

Expected behavior

A model reasoning adaptively should commit to a strategy only after processing the problem structure; hidden-state decodability of the final strategy should not be significant at the very first generated token.

Reproducibility

high

Threat model

RLVR-trained models used in safety- or accuracy-critical reasoning pipelines (e.g., automated code review, medical diagnosis support) may appear to engage in structured step-by-step reasoning while actually executing a pre-committed shortcut strategy triggered by surface-level task features. This makes the chain-of-thought an unreliable audit trail and undermines human oversight.

Novelty

Hidden-state probing shows that RLVR strategy collapse is a representation-level pre-commitment (encoded before reasoning begins) rather than a failure of in-context deliberation, providing a mechanistic account of why the collapse is sharp and hard to detect from outputs alone.

Source

Triage notes (auto)

  • paperType: case-study
  • estimatedCaseCount: 1
  • triage reason: Paper identifies and analyzes a specific RLVR failure: models trained with correct step-by-step reasoning abandon derivation and collapse to brute-force under OOD shifts. Observable, reproducible in controlled setting with clear mechanism.
tail -f comments.log

0 comments

─────────────────────────────────────────────────────────────────────

// no comments yet