5 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…
Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
Ãmer Faruk Akgül, Rajgopal Kannan, Willie Neiswanger +1
Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redist…
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-…
LocAgent: Graph-Guided LLM Agents for Code Localization
Zhaoling Chen, Xiangru Tang, Gangda Deng +6
Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to…