JP
Jeff Z. Pan
cs.AIcs.CLcs.LGcs.CVcs.IRcs.DBcs.MAcs.MMcs.CYcs.HC
On Valency
published · living versionsW_x6tubak8·v1 · currentpublished
ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents
with Xinying Qian, Ying Zhang, Yu Zhao, Xubo Liu +1
1 version
Preprints & journals
123 papers in the corpus · 2011–2026Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents2610.10179v1 · Wenyu Huang, Xinyu Hou, Pavlos Vougiouklis et al.2026 · 0 citationsarXiv
SkillFM: Generating Skills for LLM Agents via Latent Flow Matching2609.39382v1 · Zuming Zhang, Jie He, Yizhe Zhang et al.2026 · 0 citationsarXiv
Self-Play Search Distillation for Large Language Model Reasoning2609.30936v1 · Lorenzo Molfetta, Wai-Chung Kwan, Giacomo Frisoni et al.2026 · 0 citationsarXiv
Mitigating Context Interference for Reliable and Efficient Search Agents2608.10743v1 · Boyang Xue, Bin Wu, Shuofei Qiao et al.2026 · 0 citationsarXiv
OmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image Generation2607.25641v1 · Yajing Xu, Yarong Lan, Jiaoyan Chen et al.2026 · 0 citationsarXiv
CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering2607.24236v2 · Zhichao Yan, Shizhao Li, Jiapu Wang et al.2026 · 0 citationsarXiv
KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering2607.22652v1 · Yike Wu, Nan Hu, Guilin Qi et al.2026 · 0 citationsarXiv
Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games2606.16070v2 · Yifei Dong, Mingen Zheng, Linquan Wu et al.2026 · 0 citationsarXiv
Corrigendum to "Collaborate Large and Small Language Models for Multi-Modal Emergency Rumor Detection" [Neural Networks 190, 2025, 107625].42287980 · Yan, Youcheng, Liu, Jinshuo, Deng, Juan et al.2026 · 0 citationsNeural networks : the official journal of the International Neural Network Society. 2026;204:109233
Bridging the Agent-World Gap: Text World Models for LLM-based Agents2606.09032v1 · Yixia Li, Hongru Wang, Peng Lai et al.2026 · 0 citationsarXiv
Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback2606.09748v1 · Rishabh Sabharwal, Hongru Wang, Amos Storkey 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
AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents2606.20625v2 · Hang Yu, Zifan Zheng, Chun Gan et al.2026 · 0 citationsarXiv
Terminal-World: Scaling Terminal-Agent Environments via Agent Skills2605.20876v1 · Zihao Cheng, Hongru Wang, Zeming Liu et al.2026 · 0 citationsarXiv
SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research2605.22878v2 · Shuofei Qiao, Yunxiang Wei, Busheng Zhang et al.2026 · 0 citationsarXiv
MMCOMET: A Large-Scale Multimodal Commonsense Knowledge Graph for Contextual Reasoning2603.01055v1 · Eileen Wang, Hiba Arnaout, Dhita Pratama et al.2026 · 0 citationsarXiv
SkillNet: Create, Evaluate, and Connect AI Skills2603.04448v3 · Yuan Liang, Ruobin Zhong, Haoming Xu et al.2026 · 1 citationarXiv
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem2602.14367v2 · Shuofei Qiao, Yunxiang Wei, Xuehai Wang et al.2026 · 0 citationsarXiv
Chain Of Thought Compression: A Theoretical Analysis2601.21576v2 · Juncai Li, Ru Li, Yuxiang Zhou et al.2026 · 0 citationsarXiv
Beyond Factual Accuracy: Evaluating Global Reasoning Integrity in RAG Systems with LogicScore2601.15050v5 · Zhichao Yan, Yunxiao Zhao, Jiapu Wang et al.2026 · 0 citationsarXiv
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency2601.05905v2 · Haoming Xu, Ningyuan Zhao, Yunzhi Yao et al.2026 · 0 citationsarXiv
Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents2512.20092v1 · Yiming Du, Baojun Wang, Yifan Xiang et al.2025 · 0 citationsarXiv
Consistency-Aware Editing for Entity-level Unlearning in Language Models2601.08840v1 · Xiaoqi Han, V'ictor Guti'errez-Basulto, Ru Li et al.2025 · 0 citationsarXiv
CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning2511.18659v3 · Jie He, Richard He Bai, Sinead Williamson et al.2025 · 0 citationsarXiv
Uncovering and Mitigating Transient Blindness in Multimodal Model Editing2511.13243v1 · Xiaoqi Han, Ru Li, Ran Yi et al.2025 · 0 citationsarXiv
OpenSIR: Open-Ended Self-Improving Reasoner2511.00602v4 · Wai-Chung Kwan, Joshua Ong Jun Leang, Pavlos Vougiouklis et al.2025 · 0 citationsarXiv
Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs2510.20691v3 · Yanlin Song, Ben Liu, V'ictor Guti'errez-Basulto et al.2025 · 1 citationarXiv
AQE-RF: An Adaptive Quantifier Extension and Rule-Filtering Graph Network for Logical Reasoning of Text.40742873 · Wang, Meng, Liu, Jinshuo, Gutierrez-Basulto, Victor et al.2025 · 0 citationsIEEE transactions on neural networks and learning systems. 2025;36(10):18517-18529
Decomposing and Revising What Language Models Generate2509.00765v1 · Zhichao Yan, Jiaoyan Chen, Jiapu Wang et al.2025 · 0 citationsarXiv
Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning2508.19828v5 · Sikuan Yan, Xiufeng Yang, Zuchao Huang et al.2025 · 12 citationsarXiv
Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities2508.01290v1 · Zhichao Yan, Jiapu Wang, Jiaoyan Chen et al.2025 · 0 citationsarXiv
From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs2507.22716v2 · Jie He, Victor Guti'errez-Basulto, Jeff Z. Pan2025 · 0 citationsarXiv
Dark Side of Modalities: Reinforced Multimodal Distillation for Multimodal Knowledge Graph Reasoning2507.20738v1 · Yu Zhao, Ying Zhang, Xuhui Sui et al.2025 · 0 citationsarXiv
Millions of -s: Extending GraphRAG to Millions of Documents2507.17399v1 · Zhili Shen, Chenxin Diao, Pascual Merita et al.2025 · 0 citationsarXiv
Synergizing a knowledge graph and large language model for relay catalysis pathway recommendation.40860016 · Fu, Fei, Li, Qing-Qing, Wang, Fangrong et al.2025 · 15 citationsNational science review. 2025;12(8):nwaf271
Collaborate large and small language models for multi-modal emergency rumor detection.40499301 · Yan, Youcheng, Liu, Jinshuo, Deng, Juan et al.2025 · 5 citationsNeural networks : the official journal of the International Neural Network Society. 2025;190:107625
A Controllable Examination for Long-Context Language Models2506.02921v2 · Yijun Yang, Zeyu Huang, Wenhao Zhu et al.2025 · 0 citationsarXiv
Multi-level Mixture of Experts for Multimodal Entity Linking2507.07108v1 · Zhiwei Hu, V'ictor Guti'errez-Basulto, Zhiliang Xiang et al.2025 · 4 citationsarXiv
MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents2505.20231v2 · Yiming Du, Bingbing Wang, Yang He et al.2025 · 1 citationarXiv
Long-Form Information Alignment Evaluation Beyond Atomic Facts2505.15792v1 · Danna Zheng, Mirella Lapata, Jeff Z. Pan2025 · 1 citationarXiv
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst2505.14116v1 · Hongru Wang, Deng Cai, Wanjun Zhong et al.2025 · 0 citationsarXiv
Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges2505.13328v1 · Hongru Wang, Wenyu Huang, Yufei Wang et al.2025 · 2 citationsarXiv
Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context Permutation2505.11754v1 · Wenyu Huang, Pavlos Vougiouklis, Mirella Lapata et al.2025 · 0 citationsarXiv
Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics2505.00675v3 · Yiming Du, Wenyu Huang, Danna Zheng et al.2025 · 1 citationarXiv
Multi-modal Knowledge Graph Generation with Semantics-enriched Prompts2504.13631v1 · Yajing Xu, Zhiqiang Liu, Jiaoyan Chen et al.2025 · 0 citationsarXiv
ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning2503.19470v3 · Mingyang Chen, Linzhuang Sun, Tianpeng Li et al.2025 · 12 citationsarXiv
N2C2: Nearest Neighbor Enhanced Confidence Calibration for Cross-Lingual In-Context Learning2503.09218v1 · Jie He, Simon Yu, Deyi Xiong et al.2025 · 0 citationsarXiv
STCKGE:Continual Knowledge Graph Embedding Based on Spatial Transformation2503.08189v2 · Xinyan Wang, Jinshuo Liu, Kaijian Xie et al.2025 · 2 citationsarXiv
Similarity-Based Domain Adaptation with LLMs2503.05281v1 · Jie He, Wendi Zhou, Xiang Lorraine Li et al.2025 · 0 citationsarXiv
An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs2502.20175v1 · Kaustubh Vyas, Damien Graux, S'ebastien Montella et al.2025 · 0 citationsarXiv
Career total: 620 works. 123 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.