11 papers
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Binghai Wang, Chenlong Zhang, Dayiheng Liu +10
A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop strong…
Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection
Runang He, Tongya Zheng, Huiling Peng +6
Ever-evolving transaction patterns have significantly hindered anomaly detection on emerging cryptocurrency blockchains due to the vast number of addresses and diverse anomalous be…
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
Zhezheng Hao, Tianfu Wang, Huanshuo Dong +7
LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures durin…
Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation
Jiawei Chen, Xiaofan Gui, Shikai Fang +4
Parameterizing high-fidelity "digital twins" of batteries is a critical yet challenging inverse problem that hinders the pace of battery innovation. Prevailing methods formulate th…
MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
Tianzhuo Yang, Zihan Shen, Zirui Mi +7
Action-conditioned world models are increasingly used as scalable simulators for robot learning, yet current evaluations provide limited evidence that their predictions are reliabl…
LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks
Jiayong Wan, Jiawei Chen, Zhaoxia Yin +2
Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous interaction with the environment can lead to in-context reward hacking (ICRH), a phe…
NeuroSCA: Neuro-Symbolic Constraint Abstraction for Smart Contract Hybrid Fuzzing
Haochen Liang, Jiawei Chen, Hideya Ochiai
Hybrid fuzzing combines greybox fuzzing's throughput with the precision of symbolic execution to uncover deep smart contract vulnerabilities. However, its effectiveness is often li…
Qwen3-Coder-Next Technical Report
Ruisheng Cao, Mouxiang Chen, Jiawei Chen +17
We present Qwen3-Coder-Next, an open-weight language model specialized for coding agents. Qwen3-Coder-Next is an 80-billion-parameter model that activates only 3 billion parameters…
SWE-Universe: Scale Real-World Verifiable Environments to Millions
Mouxiang Chen, Lei Zhang, Yunlong Feng +16
We propose SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (…
MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
Lei Zhang, Mouxiang Chen, Ruisheng Cao +16
The rapid development of interactive and autonomous AI systems signals our entry into the agentic era. Training and evaluating agents on complex agentic tasks such as software engi…
SWE-RM: Execution-free Feedback For Software Engineering Agents
KaShun Shum, Binyuan Hui, Jiawei Chen +6
Execution-based feedback like unit testing is widely used in the development of coding agents through test-time scaling (TTS) and reinforcement learning (RL). This paradigm require…