15 papers
Rethinking Reward Models for Multi-Domain Test-Time Scaling
Dong Bok Lee, Seanie Lee, Sangwoo Park +12
The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning…
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
Young-Jun Lee, Seungone Kim, Minki Kang +5
Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture? Large Language Models (LLMs) integrated into evolutionary search h…
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Byung-Kwan Lee, Ximing Lu, Shizhe Diao +8
Knowledge distillation transfers a teacher's competence to a small student but is brittle in the small-student regime: forcing the student to imitate logits from a much larger teac…
TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration
Soyeong Jeong, Jinheon Baek, Minki Kang +1
Agents are widely deployed as assistants over documents, tools, and code. However, they typically act only on explicit user requests, which surface only the problems the user has n…
ACON: Optimizing Context Compression for Long-horizon LLM Agents
Minki Kang, Wei-Ning Chen, Dongge Han +5
Large language models (LLMs) are increasingly deployed as agents in dynamic real-world environments, where success depends on maintaining precise records of actions and observation…
T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
Minki Kang, Jongwon Jeong, Jaewoong Cho
Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined te…