3 papers
cs.AI2026
The Amazing Agent Race: Strong Tool Users, Weak Navigators
Zae Myung Kim, Dongseok Lee, Jaehyung Kim +2
Existing tool-use benchmarks for LLM agents are overwhelmingly linear: our analysis of six benchmarks shows 55 to 100% of instances are simple chains of 2 to 5 steps. We introduce…
cs.LG2025
Training-free LLM Verification via Recycling Few-shot Examples
Dongseok Lee, Jimyung Hong, Dongyoung Kim +1
Although LLMs have achieved remarkable performance, the inherent stochasticity of their reasoning process and varying conclusions present significant challenges. Majority voting or…
math.OC2025
Latent-Space Mean-Field Theory for Deep BitNet-like Training: Constrained Gradient Flows with Smooth Quantization and STE Limits
Dongwon Kim, Dongseok Lee
This work develops a mean-field analysis for the asymptotic behavior of deep BitNet-like architectures as smooth quantization parameters approach zero. We establish that empirical…