8 papers
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
Xiaojian Liu, Han Xu, Jianqiang Xia +6
The paper proposes SCOPE-RL, a two-stage reinforcement learning framework that adds dense, verifiable rewards to both pre‑success and post‑success reasoning steps of large language…
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
Rui Miao, Yixin Liu, Yili Wang +5
The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through int…
Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
Xin He, Yili Wang, Yiwei Dai +1
Over-smoothing remains a fundamental challenge in deep Graph Neural Networks (GNNs), where repeated message passing causes node representations to become indistinguishable. While e…
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…
HyperD: Hybrid Periodicity Decoupling Framework for Traffic Forecasting
Minlan Shao, Zijian Zhang, Yili Wang +3
Accurate traffic forecasting plays a vital role in intelligent transportation systems, enabling applications such as congestion control, route planning, and urban mobility optimiza…
Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling
Xu Shen, Yixin Liu, Yili Wang +5
Out-of-distribution (OOD) generalization has emerged as a critical challenge in graph learning, as real-world graph data often exhibit diverse and shifting environments that tradit…