8 papers
SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution
Gangda Deng, Zhaoling Chen, Zhongming Yu +11
Real-world software must continuously evolve to meet ever-changing and open-ended requirements. AI agents, increasingly deployed as long-running systems, are now entrusted to drive…
Online Data Selection Is Implicit Alignment
Aoxiong Zeng, Yuxin Yang, Xiangquan Yang
Supervised fine-tuning (SFT) is often treated as a capability-adaptation step, while alignment is attributed to later preference optimization or reinforcement learning. This separa…
The Long-Term Effects of Data Selection in LLM Fine-Tuning
Yuxin Yang, Aoxiong Zeng, Xiangquan Yang
Data selection is increasingly used to reduce the cost of large language model (LLM) fine-tuning, with recent methods prioritizing samples by current utility, diversity, quality, o…
Representation Collapse in Sequential Post-Training of Large Language Models
Yichen Liu, Mingyu Chen, Hao Wang +7
Large language models are now adapted through chains of post-training stages rather than through a single instruction-tuning pass. This paper studies whether such sequential post-t…
SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation
Yuxin Yang, Gangda Deng, Ãmer Faruk Akgül +6
Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning.…
Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
Gangda Deng, Yuxin Yang, Ãmer Faruk Akgül +4
Graph Neural Networks (GNNs) have become essential tools for learning on relational data, yet the performance of a single GNN is often limited by the heterogeneity present in real-…