Iterative search over reward functions with ranked feedback in GRPO training improves LLM math reasoning, achieving F1 of 0.795 on GSM8K versus 0.609 for baseline.
Chain-of-thought prompting elicits reasoning in large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Distills 3D spatial reasoning from a 7B teacher VLM to a 2.29B student using VGGT encoder, multi-task losses, and Hidden CoT latent tokens, yielding 8.7x lower latency with 54-72% performance retention on ScanNet and 3D-FRONT.
An LLM framework with tailored prompts and a new dataset of 31,165 annotated instances achieves 0.92 positive recall and 0.85 negative recall for detecting 13 smart contract vulnerability categories.
DarwinNet is a tri-layered evolutionary network architecture that synthesizes intents into bytecode via LLM-driven adaptation and tracks maturity with a Protocol Solidification Index to achieve anti-fragility.
citing papers explorer
-
Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT
Distills 3D spatial reasoning from a 7B teacher VLM to a 2.29B student using VGGT encoder, multi-task losses, and Hidden CoT latent tokens, yielding 8.7x lower latency with 54-72% performance retention on ScanNet and 3D-FRONT.