87 citations · 206 across the 40 of their papers we have counts for
43 papers
VibeMemBench: Evaluating Memory Systems for Coding Agents on Real Repository Coding Tasks
Liyang Fan, Yingcheng Shi, Yongbin Li +7
Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluations do not show whether those sy…
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Guhong Chen, Yingcheng Shi, Yongbin Li +6
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and s…
ESPO: Early-Stopping Proximal Policy Optimization
Zihang Li, Rui Zhou, Yingcheng Shi +8
When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum hor…
Agentic Reverse Engineering: From I/O to Code with Discovery Agent
Yihong Dong, Jiaru Qian, Haoran Zhang +7
The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science. Fueled by LLMs, NL2Code has achieved tremendous success, yet th…
To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
Wei Cheng, Yongchang Cao, Chen Shen +4
Large Language Models (LLMs) are increasingly used for code editing, yet the prevalent full-code generation paradigm suffers from severe efficiency bottlenecks, posing challenges f…
Think Anywhere in Code Generation
Xue Jiang, Tianyu Zhang, Ge Li +8
Recent advances in reasoning Large Language Models (LLMs) have primarily relied on upfront thinking, where reasoning occurs before final answer. However, this approach suffers from…
Beyond Quantity: Trajectory Diversity Scaling for Code Agents
Guhong Chen, Chenghao Sun, Cheng Fu +16
As code large language models (LLMs) evolve into tool-interactive agents via the Model Context Protocol (MCP), their generalization is increasingly limited by low-quality synthetic…
Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search
Guochang Li, Yuchen Liu, Zhen Qin +7
Repository-level software engineering tasks require large language models (LLMs) to efficiently navigate and extract information from complex codebases through multi-turn tool inte…
InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration
Yunkun Wang, Yue Zhang, Guochang Li +5
Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose. While existing LLM-based self-repair approaches conduct inte…
CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment
Xue Jiang, Yihong Dong, Mengyang Liu +10
While Large Language Models (LLMs) excel at code generation by learning from vast code corpora, a fundamental semantic gap remains between their training on textual patterns and th…
Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model
Yihong Dong, Zhaoyu Ma, Xue Jiang +10
Diffusion language models (DLMs) are emerging as a compelling alternative to the dominant autoregressive paradigm, offering inherent advantages in parallel generation and bidirecti…
RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization
Yihong Dong, Xue Jiang, Yongding Tao +11
Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs). However, it struggles to break thro…
Format-Adapter: Improving Reasoning Capability of LLMs by Adapting Suitable Format
Dingzirui Wang, Xuanliang Zhang, Rongyu Cao +8
Generating and voting multiple answers is an effective method to mitigate reasoning inconsistencies of large language models (LLMs). Prior works have shown that multiple reasoning…
Large Language Model Unlearning for Source Code
Xue Jiang, Yihong Dong, Huangzhao Zhang +9
While Large Language Models (LLMs) excel at code generation, their inherent tendency toward verbatim memorization of training data introduces critical risks like copyright infringe…
Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute
Yingwei Ma, Yongbin Li, Yihong Dong +5
Recent advancements in software engineering agents have demonstrated promising capabilities in automating program improvements. However, their reliance on closed-source or resource…
Do Code LLMs Understand Design Patterns?
Zhenyu Pan, Xuefeng Song, Yunkun Wang +4
Code Large Language Models (LLMs) demonstrate great versatility in adapting to various downstream tasks, including code generation and completion, as well as bug detection and fixi…
ExploraCoder: Advancing code generation for multiple unseen APIs via planning and chained exploration
Yunkun Wang, Yue Zhang, Zhen Qin +5
Large language models face intrinsic limitations in coding with APIs that are unseen in their training corpora. As libraries continuously evolve, it becomes impractical to exhausti…
LLMs as Continuous Learners: Improving the Reproduction of Defective Code in Software Issues
Yalan Lin, Yingwei Ma, Rongyu Cao +4
Reproducing buggy code is the first and crucially important step in issue resolving, as it aids in identifying the underlying problems and validating that generated patches resolve…
Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
Yingwei Ma, Rongyu Cao, Yongchang Cao +7
Recent advancements in LLM-based agents have led to significant progress in automatic software engineering, particularly in software maintenance and evolution. Despite these encour…
In-Context Transfer Learning: Demonstration Synthesis by Transferring Similar Tasks
Dingzirui Wang, Xuanliang Zhang, Qiguang Chen +9
In-context learning (ICL) is an effective approach to help large language models (LLMs) adapt to various tasks by providing demonstrations of the target task. Considering the high…
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
Jia Li, Ge Li, Xuanming Zhang +6
How to evaluate Large Language Models (LLMs) in code generation remains an open question. Existing benchmarks have two limitations - data leakage and lack of domain-specific evalua…
Codev-Bench: How Do LLMs Understand Developer-Centric Code Completion?
Zhenyu Pan, Rongyu Cao, Yongchang Cao +5
Code completion, a key downstream task in code generation, is one of the most frequent and impactful methods for enhancing developer productivity in software development. As intell…
Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining
Jie Cheng, Ruixi Qiao, Yingwei Ma +5
A significant aspiration of offline reinforcement learning (RL) is to develop a generalist agent with high capabilities from large and heterogeneous datasets. However, prior approa…
Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration
Yingwei Ma, Qingping Yang, Rongyu Cao +3
This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue reso…