PX
Pengjun Xie
cs.CLcs.AIcs.IRcs.LGcs.CVcs.MAcs.HCcs.CRcs.CYcs.DC
On Valency
published · living versionsW_63v4r7sy·v1 · currentpublished
Natural Jammers: When Non-Robust Features Become Antagonistic
with Jiaming Zhang, Fuyao Zhang, Wei Yang Bryan Lim
1 version
Preprints & journals
133 papers in the corpus · 2020–2026Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents2610.20845v1 · Yujie Feng, Xiaobin Wang, Jinluan Yang et al.2026 · 0 citationsarXiv
Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits2610.13438v2 · Xi Chen, Ruixue Ding, Zhigaoyuan Wang et al.2026 · 0 citationsarXiv
When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation2610.12061v1 · Yiruo Cheng, Shen Huang, Xiaoshuai Song et al.2026 · 0 citationsarXiv
Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents2609.34296v1 · Yingjian Zhu, Zhenyi Wang, Jiaxin Guo et al.2026 · 0 citationsarXiv
ArenaFlow: From Trajectory Ranking to Hierarchical Credit Propagation for Open-Ended Agent RL2609.21378v1 · Qiang Zhang, Ruixue Ding, Fanrui Zhang et al.2026 · 0 citationsarXiv
CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation2609.04083v1 · Tingyu Song, Mingxin Li, Yanzhao Zhang et al.2026 · 0 citationsarXiv
MemoryWalker: Stop Training Agents on Contexts They Never Saw2609.00865v1 · Zinco J, Xunjie Zhu, Shen Huang et al.2026 · 0 citationsarXiv
ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning2609.01058v1 · Fanrui Zhang, Ruixue Ding, Qiang Zhang et al.2026 · 0 citationsarXiv
UEmbed: Unified Sparse and Dense Multimodal Embeddings2608.02583v1 · Tingyu Song, Mingxin Li, Yanzhao Zhang et al.2026 · 0 citationsarXiv
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response2607.26791v1 · Lehan Wang, Boli Chen, Ruixue Ding et al.2026 · 0 citationsarXiv
CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding2606.11864v3 · Fuwei Zhang, Yanzhao Zhang, Mingxin Li et al.2026 · 1 citationarXiv
SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization2606.06079v1 · Qi Zhang, Zhaopeng Feng, Xiaonan Shi et al.2026 · 0 citationsarXiv
EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended Generation2605.29847v2 · Xin Guan, Xiaomeng Hu, Shen Huang et al.2026 · 0 citationsarXiv
FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence2605.08820v2 · Xinyu Yan, Boyang Chen, Jiaming Zhang et al.2026 · 0 citationsarXiv
DeltaMem: Towards Agentic Memory Management via Reinforcement Learning2604.01560v1 · Qi Zhang, Shen Huang, Chu Liu et al.2026 · 0 citationsarXiv
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents2603.27490v1 · Zhaopeng Feng, Liangcai Su, Zhen Zhang et al.2026 · 0 citationsarXiv
LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval2603.01425v1 · Jiajie Jin, Yanzhao Zhang, Mingxin Li et al.2026 · 0 citationsarXiv
MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models2602.23798v2 · Tiantong Wang, Xinyu Yan, Tiantong Wu et al.2026 · 0 citationsarXiv
DiffuRank: Effective Document Reranking with Diffusion Language Models2602.12528v1 · Qi Liu, Kun Ai, Jiaxin Mao et al.2026 · 0 citationsarXiv
VimRAG: Navigating Massive Visual Context in Retrieval-Augmented Generation via Multimodal Memory Graph2602.12735v2 · Qiuchen Wang, Shihang Wang, Yu Zeng et al.2026 · 0 citationsarXiv
Efficient Multimodal Planning Agent for Visual Question-Answering2601.20676v1 · Zhuo Chen, Xinyu Geng, Xinyu Wang et al.2026 · 0 citationsarXiv
U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents2601.18285v1 · Jin Su, Runnan Fang, Yeqiu Li et al.2026 · 0 citationsarXiv
Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing2601.16125v1 · Tingyu Song, Yanzhao Zhang, Mingxin Li et al.2026 · 0 citationsarXiv
Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning2601.10306v2 · Xin Guan, Zijian Li, Shen Huang et al.2026 · 0 citationsarXiv
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking2601.06487v3 · Qiang Zhang, Boli Chen, Fanrui Zhang et al.2026 · 0 citationsarXiv
Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking2601.04720v2 · Mingxin Li, Yanzhao Zhang, Dingkun Long et al.2026 · 2 citationsarXiv
WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning2601.03164v2 · Xinmiao Yu, Liwen Zhang, Xiaocheng Feng et al.2026 · 0 citationsarXiv
Nested Browser-Use Learning for Agentic Information Seeking2512.23647v1 · Baixuan Li, Jialong Wu, Wenbiao Yin et al.2025 · 0 citationsarXiv
AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning2512.22857v1 · Shihao Cai, Runnan Fang, Jialong Wu et al.2025 · 0 citationsarXiv
Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum2510.27571v1 · Zhuoning Guo, Mingxin Li, Yanzhao Zhang et al.2025 · 0 citationsarXiv
Repurposing Synthetic Data for Fine-grained Search Agent Supervision2510.24694v2 · Yida Zhao, Kuan Li, Xixi Wu et al.2025 · 0 citationsarXiv
AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis2510.24695v1 · Xuanzhong Chen, Zile Qiao, Guoxin Chen et al.2025 · 0 citationsarXiv
WebLeaper: Empowering Efficiency and Efficacy in WebAgent via Enabling Info-Rich Seeking2510.24697v1 · Zhengwei Tao, Haiyang Shen, Baixuan Li et al.2025 · 0 citationsarXiv
ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking2510.24698v1 · Baixuan Li, Dingchu Zhang, Jialong Wu et al.2025 · 0 citationsarXiv
AgentFold: Long-Horizon Web Agents with Proactive Context Management2510.24699v1 · Rui Ye, Zhongwang Zhang, Kuan Li et al.2025 · 0 citationsarXiv
Tongyi DeepResearch Technical Report2510.24701v3 · Tongyi DeepResearch Team: Baixuan Li, Bo Zhang, Dingchu Zhang et al.2025 · 0 citationsarXiv
BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents2510.23458v2 · Litu Ou, Kuan Li, Huifeng Yin et al.2025 · 0 citationsarXiv
E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search2510.22733v3 · Qi Liu, Yanzhao Zhang, Mingxin Li et al.2025 · 0 citationsarXiv
Qwen3Guard Technical Report2510.14276v1 · Haiquan Zhao, Chenhan Yuan, Fei Huang et al.2025 · 0 citationsarXiv
Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking2510.14824v1 · Ziqi Dai, Xin Zhang, Mingxin Li et al.2025 · 0 citationsarXiv
Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics2510.05137v3 · Maojia Song, Renhang Liu, Xinyu Wang et al.2025 · 0 citationsarXiv
Scaling Generalist Data-Analytic Agents2509.25084v3 · Shuofei Qiao, Yanqiu Zhao, Zhisong Qiu et al.2025 · 1 citationarXiv
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning2509.13305v1 · Kuan Li, Zhongwang Zhang, Huifeng Yin et al.2025 · 0 citationsarXiv
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents2509.13309v2 · Zile Qiao, Guoxin Chen, Xuanzhong Chen et al.2025 · 0 citationsarXiv
Scaling Agents via Continual Pre-training2509.13310v1 · Liangcai Su, Zhen Zhang, Guangyu Li et al.2025 · 0 citationsarXiv
Towards General Agentic Intelligence via Environment Scaling2509.13311v1 · Runnan Fang, Shihao Cai, Baixuan Li et al.2025 · 1 citationarXiv
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research2509.13312v3 · Zijian Li, Xin Guan, Bo Zhang et al.2025 · 1 citationarXiv
DecoupleSearch: Decouple Planning and Search via Hierarchical Reward Modeling2510.21712v2 · Hao Sun, Zile Qiao, Bo Wang et al.2025 · 0 citationsarXiv
ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking2509.00520v1 · Yuzheng Cai, Yanzhao Zhang, Dingkun Long et al.2025 · 0 citationsarXiv
Memp: Exploring Agent Procedural Memory2508.06433v4 · Runnan Fang, Yuan Liang, Xiaobin Wang et al.2025 · 0 citationsarXiv
Career total: 186 works. 133 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.