3 papers
cs.LG2026
The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
Ren Zhuang, Ben Wang, Shuifa Sun
Scaling test-time compute enhances long chain-of-thought (CoT) reasoning, yet existing approaches face a fundamental trade-off between computational cost and coverage quality: eith…
cs.LG2025
The Ratchet Effect in Silico: How Interaction Drives Cumulative Intelligence in Large Language Models
Ren Zhuang
Human intelligence scales through cumulative cultural evolution (CCE), a ratchet process in which innovations are retained against entropic drift. Large language model training, by…
cs.CL2025
Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning
Ren Zhuang
Chain-of-Thought (CoT) prompting trades inference speed for reasoning accuracy. Existing compressors force a compromise as static gradient techniques treat tokens independently, se…