Skip to content
conftrace_
2026 EMNLP EMNLP 2026

HybridThink: Learned Interleaving of Continuous and Discrete Reasoning in Large Language Models

AbstractReasoning in Large Language Models (LLMs) is primarily conducted in a discrete token space. Although recent approaches employing continuous concept tokens facilitate abstract reasoning, they introduce significant stability challenges. The accumulation of Out-of-Distribution (OOD) states frequently causes manifold deviation, while the absence of clear boundaries leads to indeterminate termination, often referred to as the anchoring problem. To address these limitations, we propose HybridThink. We formulate mode selection in LLM reasoning as a sequential decision process. A lightweight gating policy is trained with RL to decide at each step whether to propagate a continuous concept token or generate a discrete text token to anchor the semantic trajectory.This learned interleaving limits manifold deviation and resolves the fragility of static rules. Furthermore, we ensure stable convergence through a training strategy that incorporates Error-Centric Experience Replay (ECER) and Inductive Exploration Shaping (IES), prioritizing learning from failure modes, specifically drifting and premature termination. Empirical evaluations on mathematics and coding benchmarks demonstrate that HybridThink outperforms standard CoT and Soft Thinking baselines, achieving superior accuracy with reduced token consumption.

More from EMNLP 2026

All EMNLP 2026 papers →