Papers
1–4 of 4Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models
High-quality chain-of-thought has demonstrated strong potential for unlocking the reasoning capabilities of large language models. However, current paradigms typically treat the reasoning process as a...
Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction
Large Language Models (LLMs) have demonstrated impressive capabilities in reasoning and prediction across different domains. Yet, their ability to infer temporal regularities from structured behaviora...
When to Trust the Cheap Check: Weak and Strong Verification for Reasoning
Reasoning with LLMs increasingly unfolds inside a broader verification loop. Internally, systems use cheap checks, such as self-consistency or proxy rewards, which we call weak verification. Externall...
The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models
Scale does not uniformly improve reasoning - it restructures it. Analyzing 25,000+ chain-of-thought trajectories across four domains (Law, Science, Code, Math) and two scales (8B, 70B parameters), we ...