TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens
Interleaves continuous hidden-state reasoning with written tool calls and observations. Learns from explicit tool-use traces through reconstruction and self-distillation, and chooses when to call a tool or answer after each reasoning block.
First public: · Added to this list: November 3, 2026
Cite this paper
Published version
TAC-CoT: Tool-Empowered Implicit Chain-of-Thought via Interleaving Explicit Tokens
Juseon Do, Sangmin Bae, Jeesu Jung, Hwanjun Song
Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026, pp. 32803-32822.
Explore this approach
Internalized reasoning — Learn from worked solutions so that some or all of the reasoning can later happen without writing those steps. Training may use a separate teacher model or progressively remove written steps from the model being trained.
Continuous-state reasoning — Use vectors—lists of numbers—to carry intermediate reasoning from one step to the next, instead of selecting a text token at every step. Some methods use the model's hidden states; others combine several candidate token representations.