144 citations · 243 across the 64 of their papers we have counts for
72 papers
SPROUT: Scaling Agentic Reinforcement Learning for Long-Horizon Software Engineering
Mengyang Liu, Weiming Wang, Haixin Nan +6
Reinforcement learning (RL) has driven substantial progress in coding agents by relying on verified successful trajectories as learning signals. However, such trajectories are scar…
Self-Spec Verifiable Code Generation
Jiaru Qian, Yihong Dong, Yongmin Li +3
Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researche…
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
Chun-Wah Hsu, Kai Gong, Yu Wu +12
Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically assume configured organizations…
ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation
Zheng Fang, Dongming Jin, Yihong dong +4
Large Language Models have emerged as programming assistants. However, the efficacy of code generation is constrained by the quality of input requirements, which are frequently amb…
PRAXIS: Graph-Grounded Tacit Knowledge for Domain Code Generation
Xue Jiang, Tianyu Zhang, Lingwei Wu +7
LLM agents have achieved strong performance on general software engineering tasks, yet struggle with domain-specific code generation. We identify the root cause as the agent's lack…
Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models
Xuning He, Zinan Sheng, Qingyuan Shi +5
Diffusion language models (DLMs) can revise earlier predictions as context evolves, but rollback requires costly full-sequence recomputation. Conventional key-value (KV) caching as…
Efficient Grammar-Constrained Decoding via Parser Stack Classification
Yongmin Li, Yihong Dong, Jia Li +1
LLMs are widely used to generate structured output like source code or JSON. Grammar-constrained decoding (GCD) can guarantee the syntactic validity of the generated output, by mas…
Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?
Donghao Fu, Jingxin Li, Xue Jiang +1
Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers. In coding-agent workflows, high-autonomy operation is widely adopt…
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…
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
Zhiyuan Fan, Wenwei Jin, Feng Zhang +4
Experience-driven self-evolving agents aim to overcome the static nature of large language models by distilling reusable experience from past interactions, thus enabling adaptation…
PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents
Xinmiao Huang, Jinwei Hu, Rajarshi Roy +4
Large language model (LLM) agents execute multi-step tasks, but terminal verdicts arrive too late for intervention. Agent traces mix messages, tool calls, and feedback, making it d…
TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering
Yuan Sui, Yulin Chen, Yibo Li +6
When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure…
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…
Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy
Yihong Dong, Jianha Xiao, Xue Jiang +7
The formal reasoning capabilities of LLMs are crucial for advancing automated software engineering. However, existing benchmarks for LLMs lack systematic evaluation based on comput…
RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
Jia Li, Hongyi Deng, Yiran Zhang +9
Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) f…
Do Transformers Have the Ability for Periodicity Generalization?
Huanyu Liu, Ge Li, Yihong Dong +7
Large language models (LLMs) based on the Transformer have demonstrated strong performance across diverse tasks. However, current models still exhibit substantial limitations in ou…
IntentCoding: Amplifying User Intent in Code Generation
Zheng Fang, Yihong Dong, Lili Mou +3
Large Language Models (LLMs) have shown strong capabilities in code generation, but their adherence to fine-grained user intent with multiple constraints remains a significant chal…
KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?
Xue Jiang, Ge Li, Jiaru Qian +12
Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain specialization methods for LLMs to learn and…
VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications
Hao Zhu, Jia Li, Cuiyun Gao +7
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to…
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…
Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models
Yongding Tao, Tian Wang, Yihong Dong +4
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in train…
A Survey on Code Generation with LLM-based Agents
Yihong Dong, Xue Jiang, Jiaru Qian +4
Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code genera…
StackTrans: From Large Language Model to Large Pushdown Automata Model
Kechi Zhang, Ge Li, Jia Li +4
The Transformer architecture has emerged as a landmark advancement within the broad field of artificial intelligence, effectively catalyzing the advent of large language models (LL…