Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Post-Routing Arithmetic in Llama-3: Last-Token Result Writing and Rotation-Structured Digit Directions
Yao Yan
We study three-digit addition in Meta-Llama-3-8B (base) under a one-token readout to characterize how arithmetic answers are finalized after cross-token routing becomes causally ir…
cs.AI2025
Towards a Science of Scaling Agent Systems
Yubin Kim, Ken Gu, Chanwoo Park +17
Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale acr…
cs.AI2025
Addition in Four Movements: Mapping Layer-wise Information Trajectories in LLMs
Yao Yan
Multi-digit addition is a clear probe of the computational power of large language models. To dissect the internal arithmetic processes in LLaMA-3-8B-Instruct, we combine linear pr…