3 citations · 7 across the 13 of their papers we have counts for
14 papers
Steer, Don't Solve: Training Small Critic Models for Large Code Agents
Shubham Gandhi, Yiqing Xie, Atharva Naik +2
Coding tasks are typically complicated and require multiple capabilities, ranging from high-level planning to low-level implementation. While coding agents are optimized for the jo…
Reinforcing Human Behavior Simulation via Verbal Feedback
Weiwei Sun, Xuhui Zhou, Jiarui Liu +13
Humans learn social norms and behaviors from verbal feedback (e.g., a parent saying "that was rude" or a friend explaining "here's why that hurt"). Yet, learning from feedback for…
Mind the Sim2Real Gap in User Simulation for Agentic Tasks
Xuhui Zhou, Weiwei Sun, Qianou Ma +8
As NLP evaluation shifts from static benchmarks to multi-turn interactive settings, LLM-based simulators have become widely used as user proxies, serving two roles: generating user…
Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
Yiqing Xie, Emmy Liu, Gaokai Zhang +7
When assessing the quality of coding agents, predominant benchmarks focus on solving single issues on GitHub, such as SWE-Bench. In contrast, in real use, these agents solve more v…
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models
Chengbing Wang, Wuqiang Zheng, Yang Zhang +5
Large Language Models (LLMs) are increasingly deployed in human-centric applications, yet they often fail to provide substantive emotional support. While Reinforcement Learning (RL…
REPAIR: Robust Editing via Progressive Adaptive Intervention and Reintegration
Yisu Wang, Ming Wang, Haoyuan Song +4
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently ar…
SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
Dhruv Gupta, Gayathri Ganesh Lakshmy, Yiqing Xie
Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis o…
An Empirical Study on Strong-Weak Model Collaboration for Repo-level Code Generation
Shubham Gandhi, Atharva Naik, Yiqing Xie +1
We study cost-efficient collaboration between strong and weak language models for repository-level code generation, where the weak model handles simpler tasks at lower cost, and th…
RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing
Yiqing Xie, Alex Xie, Divyanshu Sheth +3
We present RepoST, a scalable method to construct environments that provide execution feedback for repository-level code generation for both training and evaluation. Unlike existin…
TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
Frank F. Xu, Yufan Song, Boxuan Li +18
We interact with computers on an everyday basis, be it in everyday life or work, and many aspects of work can be done entirely with access to a computer and the Internet. At the sa…
Improving Model Factuality with Fine-grained Critique-based Evaluator
Yiqing Xie, Wenxuan Zhou, Pradyot Prakash +9
Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuali…
CodeRAG-Bench: Can Retrieval Augment Code Generation?
Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu +4
While language models (LMs) have proven remarkably adept at generating code, many programs are challenging for LMs to generate using their parametric knowledge alone. Providing ext…
CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks
Yiqing Xie, Alex Xie, Divyanshu Sheth +3
To adequately test modern code generation systems, evaluation benchmarks must execute and test the code generated by the system. However, these execution and testing requirements h…
Data Augmentation for Code Translation with Comparable Corpora and Multiple References
Yiqing Xie, Atharva Naik, Daniel Fried +1
One major challenge of translating code between programming languages is that parallel training data is often limited. To overcome this challenge, we present two data augmentation…