4 papers
PAGE-RAG: Evidence-Grounded Adaptive Graph Retrieval for Long-Document Question Answering
Xingyu Chen, Junxiu An, Jun Guo +1
GraphRAG improves long-document question answering by introducing structured representations beyond conventional retrieval. However, automatically constructed graphs are inherently…
LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing
Shaofeng Qin, Li Wang
Constructive neural routing solvers usually score the next action by matching a decoder context to candidate embeddings, hiding deterministic one-step consequences such as travel,…
Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Hanxiao Li +13
In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. Howev…
KG-Augmented Executable CoT for Mathematical Coding
Xingyu Chen, Junxiu An, Jun Guo +2
In recent years, large language models (LLMs) have excelled in natural language processing tasks but face significant challenges in complex reasoning tasks such as mathematical rea…