11 papers
New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
Youngbin Choi, Sehyun Hwang, Suhyeon Jun +4
Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipi…
Groups Don't Move as One: A Bregman Clustering View of Linearized Group Influence
Hyunho Choi, Jaeseung Heo, Youngbin Choi +2
Influence functions provide an efficient alternative to retraining for assessing the effects of removing or reweighting training data. For groups, however, the standard first-order…
The Interplay of Harness Design and Post-Training in LLM Agents
Kyungmin Kim, Youngbin Choi, Seoyeon Lee +3
Tool-integrated LLM agents are often wrapped within a harness: the scaffolding that determines which tools are exposed, how they are described, and what auxiliary information accom…
Interaction-Aware Influence Functions for Group Attribution
Jaeseung Heo, Kyeongheung Yun, Youngbin Choi +3
Influence functions approximate how removing a training example changes a quantity of interest, called the target function, such as a held-out loss. To estimate the influence of a…
Long Live the Librarian! A Persistent Search Sub-Agent for Energy-Efficient Multi-Agent Software Engineering Systems
Seunghyuk Cho, Sunghyun Choi, Jaeseung Heo +4
Multi-agent systems (MAS) have substantially advanced autonomous software engineering (SWE), but their growing inference energy demands raise sustainability concerns. In this paper…
Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation
Seokwon Yoon, Youngbin Choi, Seunghyuk Cho +3
Generative Flow Networks (GFlowNets) learn to sample diverse candidates in proportion to a reward function, making them well-suited for scientific discovery, where exploring multip…
In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration
Youngbin Choi, Minjong Lee, Saemi Moon +4
LLM-generated drafts often contain subtle factual or logical errors, yet prior work shows that models struggle to reliably integrate multi-turn feedback aimed at fixing them. We pr…
Plane Geometry Problem Solving with Multi-modal Reasoning: A Survey
Seunghyuk Cho, Zhenyue Qin, Yang Liu +3
Plane geometry problem solving (PGPS) has recently gained significant attention as a benchmark to assess the multi-modal reasoning capabilities of large vision-language models. Des…
CoPL: Collaborative Preference Learning for Personalizing LLMs
Youngbin Choi, Seunghyuk Cho, Minjong Lee +4
Personalizing large language models (LLMs) is important for aligning outputs with diverse user preferences, yet existing methods struggle with flexibility and generalization. We pr…
GeoDANO: Geometric VLM with Domain Agnostic Vision Encoder
Seunghyuk Cho, Zhenyue Qin, Yang Liu +3
We introduce GeoDANO, a geometric vision-language model (VLM) with a domain-agnostic vision encoder, for solving plane geometry problems. Although VLMs have been employed for solvi…
SpReME: Sparse Regression for Multi-Environment Dynamic Systems
MoonJeong Park, Youngbin Choi, Namhoon Lee +1
Learning dynamical systems is a promising avenue for scientific discoveries. However, capturing the governing dynamics in multiple environments still remains a challenge: model-bas…