7 papers
RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering
Yuyang Li, Zihe Yan, Tobias Käfer
Multi-hop question-answering systems often use expensive retrieval on every question. They may decompose the question, run several retrieval rounds, or search through bridge entiti…
Learning Agent-Compatible Context Management for Long-Horizon Tasks
Lu Yi, Runlin Lei, Liuyi Yao +6
LLM agents increasingly face long-horizon tasks such as web search and deep research in real-world applications, where accumulated context can cause long-context degradation and re…
EviMem: Evidence-Gap-Driven Iterative Retrieval for Long-Term Conversational Memory
Yuyang Li, Yime He, Zeyu Zhang +1
Long-term conversational memory requires retrieving evidence scattered across multiple sessions, yet single-pass retrieval fails on temporal and multi-hop questions. Existing itera…
Sim-and-Human Co-training for Data-Efficient and Generalizable Robotic Manipulation
Kaipeng Fang, Weiqing Liang, Yuyang Li +5
Synthetic simulation data and real-world human data provide scalable alternatives to circumvent the prohibitive costs of robot data collection. However, these sources suffer from t…
AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
Jinghang Shi, Xiaoyu Tang, Yang Huang +4
Astronomical image interpretation presents a significant challenge for applying multimodal large language models (MLLMs) to specialized scientific tasks. Existing benchmarks focus…
SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completion
Mengxue Yang, Chun Yang, Jiaqi Zhu +4
Link prediction in knowledge graphs requires integrating structural information and semantic context to infer missing entities. While large language models offer strong generative…