Papers › Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs

Internal Chain-of-Thought: Empirical Evidence for Layer-wise Subtask Scheduling in LLMs

20 May 2025arXiv:2505.14530archive 2025-07-28

Zhipeng Yang, Junzhuo Li, Siyu Xia, Xuming Hu

We show that large language models (LLMs) exhibit an internal chain-of-thought: they sequentially decompose and execute composite tasks layer-by-layer. Two claims ground our study: (i) distinct subtasks are learned at different network depths, and (ii) these subtasks are executed sequentially across layers. On a benchmark of 15 two-step composite tasks, we employ layer-from context-masking and propose a novel cross-task patching method, confirming (i). To examine claim (ii), we apply LogitLens to decode hidden states, revealing a consistent layerwise execution pattern. We further replicate our analysis on the real-world TRACE benchmark, observing the same stepwise dynamics. Together, our results enhance LLMs transparency by showing their capacity to internally plan and execute subtasks (or instructions), opening avenues for fine-grained, instruction-level activation steering.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yzp11/internal-chain-of-thought officialmentioned in papermentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Scheduling

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Patching

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections