7 papers
Immersion in the GitHub Universe: Scaling Coding Agents to Mastery
Jiale Zhao, Guoxin Chen, Fanzhe Meng +11
Achieving mastery in real world software engineering tasks is fundamentally bottlenecked by the scarcity of large scale, high quality training data. Scaling such data has been limi…
Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
Xin Zhao, Naoki Yoshinaga, Yuma Tsuta +1
Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across languages into large language models (LLMs). Although many methods have been proposed to…
Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis
Rui Zou, Mengqi Wei, Yutao Zhu +3
Large Language Models (LLMs) excel in reasoning and generation across domains, but still struggle with identifying and diagnosing complex errors. This stems mainly from training ob…
Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability
Xin Zhao, Zehui Jiang, Naoki Yoshinaga
While feed-forward neurons in pre-trained language models (PLMs) can encode knowledge, past research targeted a small subset of neurons that heavily influence outputs. This leaves…
RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensation
Zhentao Xie, Chengcheng Han, Jinxin Shi +4
Although multi-agent systems based on large language models show strong capabilities on multiple tasks, they are still limited by high computational overhead, information loss, and…
C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
Guoxin Chen, Minpeng Liao, Peiying Yu +5
Retrieval-augmented generation (RAG) systems face a fundamental challenge in aligning independently developed retrievers and large language models (LLMs). Existing approaches typic…