YS
Yangqiu Song
cs.CLcs.AIcs.LGcs.CRcs.IRcs.CVcs.SIstat.MLcs.DBcs.LO
On Valency
published · living versionsW_cm26k9vk·v1 · currentpublished
From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
with Jiaqi Wang, Yisen Gao, Huayang Shi, Junhao Hou +5
1 version
W_s3knahgg·v1published
Preprints & journals
271 papers in the corpus · 2011–2026Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds2610.11552v1 · Yisen Gao, Yue Guo, Qing Zong et al.2026 · 0 citationsarXiv
Towards In-Parameter Memory Augmentation for Large Language Models2610.08630v1 · Haoyu Huang, Zhongwei Xie, Jiaxin Bai et al.2026 · 0 citationsarXiv
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe2610.03092v3 · Weihan Li, Tianshi Zheng, Yangqiu Song et al.2026 · 0 citationsarXiv
SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown2610.04008v2 · Yuxuan Liu, Haoran Li, Yuhao Zhang et al.2026 · 0 citationsarXiv
CorrGRPO: Correlation-Normalized GRPO for Multi-Reward Learning2609.36820v1 · Wenbin Hu, Huihao Jing, Haochen Shi et al.2026 · 0 citationsarXiv
AuthorityLens: Rethinking LLM-Based Agent Systems Through the Lens of Authority2609.32378v1 · Shaojin Chen, Huihao Jing, Wun Yu Chan et al.2026 · 0 citationsarXiv
SoFT: Soft Targets for Generalizable LLM Fine-Tuning2609.32493v2 · Huihao Jing, Wenbin Hu, Shaojin Chen et al.2026 · 0 citationsarXiv
AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era2609.07611v1 · Yunxiang Mo, Tianshi Zheng, Yisen Gao et al.2026 · 0 citationsarXiv
E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation2608.30730v1 · Wei Fan, Xinjie Shen, Xudong Guo et al.2026 · 0 citationsarXiv
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos2608.26355v1 · Baixuan Xu, Yinyui Xu, Tianshi Zheng et al.2026 · 0 citationsarXiv
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence2608.21156v2 · Yuyuan Feng, Zhishang Xiang, Chaobin Yang et al.2026 · 0 citationsarXiv
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design2608.10299v1 · Qing Zong, Jiayu Liu, Junhao Shen et al.2026 · 0 citationsarXiv
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds2608.02636v1 · Yuxuan Liu, Zhaochen Su, Yuhao Zhang et al.2026 · 0 citationsarXiv
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning2607.26465v2 · Kawai Chung, Chunkit Chan, Yauwai Yim et al.2026 · 0 citationsarXiv
RLPF: Reinforcement Learning from Performance Feedback for Code Generation2607.27271v1 · Huihao Jing, Haozhe Cui, Wenbin Hu et al.2026 · 0 citationsarXiv
EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World2607.17250v1 · Qing Zong, Yue Guo, Mengxin Yang et al.2026 · 0 citationsarXiv
Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions2607.12406v2 · Huihao Jing, Wenbin Hu, Shaojin Chen et al.2026 · 0 citationsarXiv
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding2606.20873v1 · Yueming Wang, Tianshi Zheng, Jiaxin Bai et al.2026 · 0 citationsarXiv
SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents2606.16591v2 · Qiao Xiao, Haochen Shi, Yisen Gao et al.2026 · 0 citationsarXiv
SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection2606.05787v1 · Tsun On Kwok, Xi Yang, Ki Sen Hung et al.2026 · 0 citationsarXiv
Steering LLM Viewpoints through Fabricated Evidence Injection2606.06244v1 · Xi Yang, Chang Liu, Zhenglin Huang et al.2026 · 0 citationsarXiv
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision2606.01139v4 · Yuxuan Liu, Zhaochen Su, Lingyun Xie et al.2026 · 0 citationsarXiv
PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments2605.30880v4 · Jiaxin Bai, Yue Guo, Yifei Dong et al.2026 · 0 citationsarXiv
One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs2605.31370v2 · Yisen Gao, Yixi Cai, Tianshi Zheng et al.2026 · 0 citationsarXiv
Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models2605.27243v3 · Aaron Branson Cigres Li, Zhaowei Wang, Yu Zhao et al.2026 · 0 citationsarXiv
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning2605.25920v2 · Wei Fan, Yining Zhou, Mufan Zhang et al.2026 · 0 citationsarXiv
Neural Scalable Symbolic Search Framework for Complex Logical Queries with Multiple Free Variables2605.25985v2 · Weizhi Fei, Hang Yin, Zihao Wang et al.2026 · 0 citationsarXiv
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models2605.14906v1 · Xiyu Ren, Zhaowei Wang, Yiming Du et al.2026 · 0 citationsarXiv
KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning2605.14907v2 · Yisen Gao, Jiaxin Bai, Haoyu Huang et al.2026 · 0 citationsarXiv
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context2605.13831v2 · Zhaowei Wang, Lishu Luo, Haodong Duan et al.2026 · 0 citationsarXiv
PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization2605.15222v2 · Huihao Jing, Wenbin Hu, Shaojin Chen et al.2026 · 0 citationsarXiv
DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning2605.10488v2 · Haoyu Huang, Jiaxin Bai, Shujie Liu et al.2026 · 0 citationsarXiv
MedHorizon: Towards Long-context Medical Video Understanding in the Wild2605.06537v2 · Bodong Du, Bowen Liu, Yang Yu et al.2026 · 0 citationsarXiv
SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning2605.01489v2 · Tianshi Zheng, Rui Wang, Xiyun Li et al.2026 · 0 citationsarXiv
Divide-then-Diagnose: Weaving Clinician-Inspired Contexts for Ultra-Long Capsule Endoscopy Videos2604.21814v1 · Bowen Liu, Li Yang, Shanshan Song et al.2026 · 0 citationsarXiv
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries2604.15717v1 · Ki Sen Hung, Xi Yang, Chang Liu et al.2026 · 0 citationsarXiv
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents2604.12284v2 · Yulin Chen, Tri Cao, Haoran Li et al.2026 · 0 citationsarXiv
ContextLens: Modeling Imperfect Privacy and Safety Context for Legal Compliance2604.12308v1 · Haoran Li, Yulin Chen, Huihao Jing et al.2026 · 0 citationsarXiv
GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety2605.20203v1 · Changxuan Fan, Xi Yang, Yueyuan Zheng et al.2026 · 0 citationsarXiv
Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification2603.26348v1 · Shuai Lv, Chang Liu, Feng Tang et al.2026 · 0 citationsarXiv
Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards2603.24709v2 · Cheng Jiayang, Xin Liu, Zhihan Zhang et al.2026 · 0 citationsarXiv
OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset2603.13933v2 · Wenbin Hu, Huihao Jing, Haochen Shi et al.2026 · 0 citationsarXiv
ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement2603.03742v2 · Zijin Hong, Hao Chen, Zheng Yuan et al.2026 · 1 citationarXiv
AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations2603.01966v1 · Cheng Jiayang, Dongyu Ru, Lin Qiu et al.2026 · 0 citationsarXiv
NGDBench: Towards Neural Graph Data Management2603.05529v2 · Yufei Li, Yisen Gao, Jiaxuan Xiong et al.2026 · 0 citationsarXiv
NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training2602.21597v1 · Zhongwei Xie, Jiaxin Bai, Shujie Liu et al.2026 · 0 citationsarXiv
HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning2601.22448v2 · Weiqi Wang, Xin Liu, Binxuan Huang et al.2026 · 0 citationsarXiv
Do Reasoning Models Enhance Embedding Models?2601.21192v1 · Wun Yu Chan, Shaojin Chen, Huihao Jing et al.2026 · 0 citationsarXiv
is Theoretically Large Enough for Embedding-based Top- Retrieval2601.20844v3 · Zihao Wang, Hang Yin, Lihui Liu et al.2026 · 0 citationsarXiv
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems2601.11004v4 · Jiayu Liu, Rui Wang, Qing Zong et al.2026 · 0 citationsarXiv
Career total: 544 works. 271 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.