間接思考のダイナミクス：因果構造に対する実証的考察

非言語的な段階的な思考法は、明示的な文脈的な理由を代わりに複数の内部的な不透明なステップを使用します。しかし、それらの中間計算は、相関に基づく探査を超えて評価することは困難です。この論文では、代表的なパラダイム（たとえば、ココナッツやCODI）を通じて数学的および一般的な推理タスクでの二つの主要な問いの解明に焦点をおいています。 (1) 応答が早期に決定できるステップはどのようにして正しいになるのか、(2) ポアント間で影響がどう伝播し、それらの構造にはどのような違いがあるか、そして（3）中間軌跡では、競合する応答がどの程度継続的に存在し、その出力レベルの-commitmentは代表的なcommitmentとどのように異なるかについて。これらの結果は、統一条件のモードや安定性に敏感な分析 – およびそれに対応するトレーニング/デコーダー目標 – を勧めします。

arXiv:2602.08783v1 Announce Type: new Abstract: Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate computations are difficult to evaluate beyond correlation-based probes. In this paper, we view latent chain-of-thought as a manipulable causal process in representation space by modeling latent steps as variables in a structural causal model (SCM) and analyzing their effects through step-wise $\mathrm{do}$-interventions. We study two representative paradigms (i.e., Coconut and CODI) on both mathematical and general reasoning tasks to investigate three key questions: (1) which steps are causally necessary for correctness and when answers become decidable early; (2) how does influence propagate across steps, and how does this structure compare to explicit CoT; and (3) do intermediate trajectories retain competing answer modes, and how does output-level commitment differ from representational commitment across steps. We find that latent-step budgets behave less like homogeneous extra depth and more like staged functionality with non-local routing, and we identify a persistent gap between early output bias and late representational commitment. These results motivate mode-conditional and stability-aware analyses -- and corresponding training/decoding objectives -- as more reliable tools for interpreting and improving latent reasoning systems.