sequential reasoning
Sequential reasoning involves the logical processing of information over time, where past states influence future decisions. This is particularly relevant in tasks such as planning and temporal forecasting in AI systems.
- A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
- Bridging Time and Linguistics: LLMs as Time Series Analyzer through Symbolization and Segmentation
- Continuous Thought Machines
- DynaAct: Large Language Model Reasoning with Dynamic Action Spaces
- Non-Markovian Discrete Diffusion with Causal Language Models
- On Learning Verifiers and Implications to Chain-of-Thought Reasoning
- Timely Clinical Diagnosis through Active Test Selection
- Transformers Provably Learn Chain-of-Thought Reasoning with Length Generalization