4 papers
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
Lin Shi, Haowei Lin, Zixuan Zhu +123
Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a…
Next Edit Prediction: Learning to Predict Code Edits from Context and Interaction History
Ruofan Lu, Yintong Huo, Meng Zhang +2
The rapid advancement of large language models (LLMs) has led to the widespread adoption of AI-powered coding assistants integrated into a development environment. On one hand, low…
Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks
Ruofan Lu, Yichen Li, Yintong Huo
Autonomous agent systems powered by Large Language Models (LLMs) have demonstrated promising capabilities in automating complex tasks. However, current evaluations largely rely on…
TeacherLM: Teaching to Fish Rather Than Giving the Fish, Language Modeling Likewise
Nan He, Hanyu Lai, Chenyang Zhao +12
Large Language Models (LLMs) exhibit impressive reasoning and data augmentation capabilities in various NLP tasks. However, what about small models? In this work, we propose Teache…