15 papers
When Agent Context Goes Stale: Incoherence in Volatile Agent Context
Yingying Liu, Junzhou Fang, Chenxiong Qian
Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data sources underlying these observa…
FrontierChallenge: Evaluating Scientific Workflow Completion
Liangcai Su, Zhaopeng Feng, Zhuo Chen +14
Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We in…
SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction
Yuanxiang Shi, Jiayi Lin, Xuanyong Lin +8
Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical software exposed. Rigorously me…
MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale
Jiaxi Liang, Yuanxiang Shi, Zezhou Yang +1
Modern large-scale software systems often suffer from pervasive memory inefficiencies (e.g., bloat, churn), leading to excessive resource costs and performance degradation. Existin…
GMP: A Benchmark for Content Moderation under Co-occurring Violations and Dynamic Rules
Houde Dong, Yifei She, Kai Ye +3
Online content moderation is essential for maintaining a healthy digital environment, and reliance on AI for this task continues to grow. Consider a user comment using national ste…
XGuardian: Towards Explainable and Generalized AI Anti-Cheat on FPS Games
Jiayi Zhang, Chenxin Sun, Chenxiong Qian
Aim-assist cheats are the most prevalent and infamous form of cheating in First-Person Shooter (FPS) games, which help cheaters illegally reveal the opponent's location and auto-ai…
CodeFuse-CommitEval: Towards Benchmarking LLM's Power on Commit Message and Code Change Inconsistency Detection
Qingyu Zhang, Puzhuo Liu, Peng Di +1
Version control relies on commit messages to convey the rationale for code changes, but these messages are often low quality and, more critically, inconsistent with their diffs-kno…
R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning
Jiayi Lin, Liangcai Su, Junzhe Li +1
Fuzzing is effective for vulnerability discovery but struggles with complex targets such as compilers, interpreters, and database engines, which accept textual input that must sati…
Scaling Agents via Continual Pre-training
Liangcai Su, Zhen Zhang, Guangyu Li +19
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approache…
How Far Are We from True Unlearnability?
Kai Ye, Liangcai Su, Chenxiong Qian
High-quality data plays an indispensable role in the era of large models, but the use of unauthorized data for model training greatly damages the interests of data owners. To overc…
ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation
Kai Ye, Liangcai Su, Chenxiong Qian
Code generation has emerged as a pivotal capability of Large Language Models(LLMs), revolutionizing development efficiency for programmers of all skill levels. However, the complex…
Bones of Contention: Exploring Query-Efficient Attacks against Skeleton Recognition Systems
Yuxin Cao, Kai Ye, Derui Wang +4
Skeleton action recognition models have secured more attention than video-based ones in various applications due to privacy preservation and lower storage requirements. Skeleton da…
CONGRA: Benchmarking Automatic Conflict Resolution
Qingyu Zhang, Liangcai Su, Kai Ye +1
Resolving conflicts from merging different software versions is a challenging task. To reduce the overhead of manual merging, researchers develop various program analysis-based too…
Identify As A Human Does: A Pathfinder of Next-Generation Anti-Cheat Framework for First-Person Shooter Games
Jiayi Zhang, Chenxin Sun, Yue Gu +4
The gaming industry has experienced substantial growth, but cheating in online games poses a significant threat to the integrity of the gaming experience. Cheating, particularly in…
WizardMerge -- Save Us From Merging Without Any Clues
Qingyu Zhang, Junzhe Li, Jiayi Lin +3
Modern software development necessitates efficient version-oriented collaboration among developers. While Git is the most popular version control system, it generates unsatisfactor…