Large Language Model (LLM) agents are increasingly deployed under structured generation, where grammar constraints enforce output format at inference time. Whereas existing compression methods target unconstrained generation, we first identify a fundamental mismatch: under structured generation, grammar constraints red...
Moonseok Choi, Jongwon Jeong, Minki Kang et al.· 0 citations
Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web search tool can keep returning the same pages as solutions change. We introduce EvoDuet, a bi-level optimization method that co-evolves sol...
Young-Jun Lee, Jinheon Baek, Soyeong Jeong et al.· 1 citation
Mid-Harness is introduced, which samples and verifies candidate actions before forwarding one for execution, while keeping the generator and harness unchanged, and identifies action scaling as a promising target for test-time compute scaling in terminal agents.
Entropic Advantage Policy Optimization (EAPO) is introduced, an entropy-guided credit assignment method that treats success and failure asymmetrically and promotes more effective exploration, broadening problem coverage and generating more diverse candidate answers.
Woongyeong Yeo, Minki Kang, Chanuk Lee et al.· 0 citations
FlyBy is introduced, a selective querying framework, and 4B and 8B variants are trained to reason first, diagnose what remains unresolved, and, at a knowledge bottleneck, query stronger models whose parametric knowledge extends beyond its own.
Chanuk Lee, Minki Kang, Sangwoo Park et al.· 0 citations
Experiments show that EvolveTrade often improves Sharpe Ratio and Cumulative Return over fixed-policy LLM baselines, achieving the improved SR and CR in most evaluated settings, and suggest that adapting the reusable procedure governing tool use is a key direction for building more robust LLM trading agents.
Sehee Kim, Yumin Choi, Minki Kang et al.· arXiv.org· 1 citation
Zone of Proximal Policy Optimization (ZPPO), inspired by Vygotsky's zone of proximal development, is introduced, which outperforms off/on-policy distillation and GRPO, with the largest gains at the smallest scale.