2 citations · 11 across the 51 of their papers we have counts for
36 papers · 1 filter
Speculative Forking: Turning Idle Wait into Parallel Exploration for Repository Environment Setup
Yuling Shi, Mingchu Zhong, Zhensu Sun +8
Before developers can use a software project, they must first get it to run. This often requires installing the right language runtime, system packages, build tools, and test comma…
SWE-at-Scale: Scalable Issue Synthesis from Historical Bug Fixes
Silin Chen, Zihan Zhang, Xiaodong Gu +7
As coding agents become increasingly capable, robust evaluation requires a broader and more diverse supply of verifiable software engineering (SWE) tasks. However, real-world tasks…
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
Yuling Shi, Zhensu Sun, Junsen Dong +3
Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single pass of a frontier model over an agentic benchmark can cost hun…
Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry
Shengfang Zhai, Leo Marchyok, Yuling Shi +4
Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional…
DeepRepoQA: Code Repository Question Answering with Deep Agent Exploration
Weihan Peng, Yuling Shi, Yingwei Ma +3
Answering developer questions about a software repository is a critical yet under-explored problem in software engineering. While existing repository understanding methods have adv…
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
Jialong Liu, Yuling Shi, Ning Yang +2
Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-traini…
Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?
Silin Chen, Yufei Yang, Xiaodong Gu +3
Repository-level coding benchmarks have become the standard for evaluating coding agents, yet they inherently suffer from data leakage because they are built upon popular open-sour…
Repo0: Design-Driven Zero-to-All Code Generation
Silin Chen, Haoyi Teng, Xiaodong Gu +5
Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold…
SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution
Silin Chen, Han Li, Xiaodong Gu +2
Large language model (LLM) based agents have demonstrated remarkable proficiency in automated software issue resolution, yet they often struggle to resolve issues in a specific rep…
ParaTempo: Efficient Parallel Reasoning via Temporal Confidence
Xuteng Zhang, Wenhao Zeng, Xiaodong Gu +5
Parallel reasoning improves the accuracy and robustness of large reasoning models by exploring multiple solution paths, but its computational cost grows with reasoning depth and br…
SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring
Yuling Shi, Jinghan Xu, Kelin Fu +12
As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under se…
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
Yuhang Wang, Yuling Shi, Shaoqiu Zhang +6
Pruning long context for coding agents has been a vital technology for efficient context management. While existing context pruning methods such as SWE-Pruner realize this by attac…
Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?
Zhi Chen, Zhensu Sun, Yuling Shi +2
Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime a…
Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution
Haotian Lin, Silin Chen, Xiaodong Gu +8
LLM-based coding agents have significantly advanced automated software issue resolution, yet they remain highly prone to factual errors caused by insufficient repository understand…
Mirror-Fusion Attention for Reflection-Aware Self-Supervised Representation Learning
Ruixin Li, Jin Liu, Yuling Shi +1
Most self-supervised learning (SSL) methods encourage invariance across augmentations, but strict flip invariance can suppress informative left--right correspondences in approximat…
FastContext: Training Efficient Repository Explorer for Coding Agents
Shaoqiu Zhang, Maoquan Wang, Yuling Shi +12
Large Language Model (LLM) coding agents have achieved strong results on software engineering tasks, yet repository exploration remains a major bottleneck: locating relevant code c…
Dockerless: Environment-Free Program Verifier for Coding Agents
Wenhao Zeng, Yuling Shi, Xiaodong Gu +10
Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning…
Code Is More Than Text: Uncertainty Estimation for Code Generation
Yuling Shi, Caiqi Zhang, Yuexian Li +4
Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks. Reliable uncertainty estimation (UE…
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Shaoqiu Zhang, Yuhang Wang, Jialiang Liang +8
Repository-level coding benchmarks such as SWE-bench have driven a rapid surge in the capabilities of coding agents. Yet they usually treat coding tasks as a holistic, binary predi…
Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
Miao Wang, Yuling Shi, Yijiang Li +8
Text-based role-playing models can imitate character styles, but often fail to capture scene atmosphere and evolving tension, which are crucial for immersive applications such as V…
LLM Agents Can See Code Repositories
Dongjian Ma, Silin Chen, Yufei Yang +3
Coding agents powered by large language models have demonstrated strong performance on software engineering tasks. Yet most agents consume repositories almost entirely as text, whi…
HEART-Bench: Do LLMs Make Persona-Consistent Decisions?
Weihan Peng, Chenxu Zhang, Qianao Wang +7
LLM agents in interactive entertainment and social applications, including companions, role-play characters, and persona clones, need decisions grounded in personality and past exp…
BadDLM: Backdooring Diffusion Language Models with Diverse Targets
Shengfang Zhai, Xiaoyang Ji, Yuling Shi +6
Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive (AR) language models, enabling parallel generation and bidirectional co…
ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation
Yeheng Chen, Chaoxiang Xie, Yuling Shi +4
LLMs have achieved strong results on both function-level code synthesis and repository-level code modification, yet a capability that falls between these two extremes -- compositio…