FF
Fuli Feng
cs.IRcs.CLcs.AIcs.LGcs.CVstat.MLcs.MMPeptidesbioinformaticsComplementarity Determining Regions
On Valency
published · living versionsW_jtc2exp6·v1 · currentpublished
Learning Calibrated Confidence for Multi-Agent Collaboration
with Chenxiao Fan, Chongming Gao, Gangyi Zhang, Yaxin Gong +7
1 version
W_595m2nmx·v1published
W_fnqsu8ft·v1published
W_cgnsvegp·v1published
Preprints & journals
195 papers in the corpus · 2018–2026Learning to Steer LLM Agents and Multi-Agent Systems2610.22316v1 · Leyang Shen, Yaxin Gong, Yang Zhang et al.2026 · 0 citationsarXiv
Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents2610.13058v1 · Ziang Ye, Wentao Shi, Lei Chen et al.2026 · 0 citationsarXiv
Learning to Accumulate Knowledge with Mutual Information2610.10042v1 · Yuyang Zhao, Lizi Liao, Leyang Shen et al.2026 · 0 citationsarXiv
HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence2610.02920v1 · Xiqiao Xiong, Moxin Li, Zhixin Ma et al.2026 · 0 citationsarXiv
HARDE: Optimizing Agent Harnesses for Runtime Risk Detection and Execution Control2609.38291v1 · Zhuo Liu, Moxin Li, Zhixin Ma et al.2026 · 0 citationsarXiv
Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts2609.34857v1 · Chenxiao Fan, Chongming Gao, Gangyi Zhang et al.2026 · 0 citationsarXiv
Self-Evolving Memory for Generative Recommendation2609.15598v1 · Xinyu Lin, Zhuosong Jiang, Zixiao Suo et al.2026 · 0 citationsarXiv
Answer Probing-Guided Search for Diverse Solution Exploration of LLMs2608.30345v1 · Yi Fang, Que Shen, Chengpeng Li et al.2026 · 0 citationsarXiv
PrefReward: Learning User Preference Matrix for Personalized Text Generation2607.21067v1 · Yue Wu, Chengbing Wang, Yimeng Bai et al.2026 · 0 citationsarXiv
RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation2607.15730v1 · Ziyi Zhao, Xiaoyou Zhou, Xiao Lv et al.2026 · 0 citationsarXiv
Optimizing Visual Generative Models via Distribution-wise Rewards2607.02291v1 · Ruihang Li, Mengde Xu, Shuyang Gu et al.2026 · 0 citationsarXiv
Intuition-Guided Latent Reasoning for LLM-Based Recommendation2606.27684v1 · Chang Liu, Yimeng Bai, Xiaoyan Zhao et al.2026 · 0 citationsarXiv
ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning2605.23454v2 · Xiaoyuan Li, Keqin Bao, Moxin Li et al.2026 · 0 citationsarXiv
Unified Data Selection for LLM Reasoning2605.22389v1 · Xiaoyuan Li, Yubo Ma, Chengpeng Li et al.2026 · 0 citationsarXiv
On Predicting the Post-training Potential of Pre-trained LLMs2605.11978v1 · Xiaoyuan Li, Yubo Ma, Kexin Yang et al.2026 · 0 citationsarXiv
SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation2605.12022v1 · Xiaoyuan Li, Yuzhe Wang, Moxin Li et al.2026 · 0 citationsarXiv
SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs2605.12039v2 · Xiaoyuan Li, Moxin Li, Keqin Bao et al.2026 · 0 citationsarXiv
UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation2605.12088v2 · Yiyan Xu, Qiulin Wang, Wenjie Wang et al.2026 · 0 citationsarXiv
TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems2605.09539v1 · Chen Xu, Yicheng Hu, Ruizi Wang et al.2026 · 0 citationsarXiv
Benchmarking TCR-pMHC structure prediction: a unified evaluation and CDR3-based functional insights.42248582 · Lu, Jiadong, Zhu, Xinyuan, Hu, Xinting et al.2026 · 3 citationsBriefings in bioinformatics. 2026;27(3)
Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders2604.22504v1 · Wentao Shi, Qifan Wang, Chen Chen et al.2026 · 0 citationsarXiv
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation2604.18240v1 · Wentao Shi, Yu Wang, Yuyang Zhao et al.2026 · 0 citationsarXiv
KnitLoRA: bridging low-rank adaptation as interwoven layers for deeper semantic reasoning.41992040 · Qiu, Hongjie, Ning, Youyou, Li, Jinqiang et al.2026 · 1 citationScientific reports. 2026;16(1)
Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation2603.10673v3 · Yaxin Gong, Chongming Gao, Chenxiao Fan et al.2026 · 0 citationsarXiv
AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignment2603.26680v2 · Jianfei Xiao, Xiang Yu, Chengbing Wang et al.2026 · 1 citationarXiv
Verifiable Reasoning for LLM-based Generative Recommendation2603.07725v1 · Xinyu Lin, Hanqing Zeng, Hanchao Yu et al.2026 · 1 citationarXiv
MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval2603.13349v1 · Fengbin Zhu, Zijing Cai, Yuzhe Wang et al.2026 · 0 citationsarXiv
NextAds: Towards Next-generation Personalized Video Advertising2603.02137v2 · Yiyan Xu, Ruoxuan Xia, Wuqiang Zheng et al.2026 · 0 citationsarXiv
Uncertainty-aware Generative Recommendation2602.11719v2 · Chenxiao Fan, Chongming Gao, Yaxin Gong et al.2026 · 0 citationsarXiv
Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowledge Discovery2603.03322v2 · Chaoqun Yang, Xinyu Lin, Shulin Li et al.2026 · 0 citationsarXiv
Bringing Reasoning to Generative Recommendation Through the Lens of Cascaded Ranking2602.03692v2 · Xinyu Lin, Pengyuan Liu, Wenjie Wang et al.2026 · 2 citationsarXiv
Towards Sample-Efficient and Stable Reinforcement Learning for LLM-based Recommendation2602.00632v1 · Hongxun Ding, Keqin Bao, Jizhi Zhang et al.2026 · 0 citationsarXiv
One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment2601.18731v2 · Hongru Cai, Yongqi Li, Tiezheng Yu et al.2026 · 0 citationsarXiv
Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs2601.12034v1 · Ziyi Zhao, Chongming Gao, Yang Zhang et al.2026 · 0 citationsarXiv
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models2601.10532v2 · Chengbing Wang, Wuqiang Zheng, Yang Zhang et al.2026 · 0 citationsarXiv
Controllable LLM Reasoning via Sparse Autoencoder-Based Steering2601.03595v2 · Yi Fang, Wenjie Wang, Mingfeng Xue et al.2026 · 0 citationsarXiv
AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning2512.22857v1 · Shihao Cai, Runnan Fang, Jialong Wu et al.2025 · 0 citationsarXiv
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards2512.07761v3 · Xiqiao Xiong, Ouxiang Li, Zhuo Liu et al.2025 · 0 citationsarXiv
MGFRec: Towards Reinforced Reasoning Recommendation with Multiple Groundings and Feedback2510.22888v2 · Shihao Cai, Chongming Gao, Haoyan Liu et al.2025 · 2 citationsarXiv
Bi-Level Optimization for Generative Recommendation: Bridging Tokenization and Generation2510.21242v2 · Yimeng Bai, Chang Liu, Yang Zhang et al.2025 · 0 citationsarXiv
Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation2509.11524v1 · Chengbing Wang, Yang Zhang, Zhicheng Wang et al.2025 · 2 citationsarXiv
Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?2509.03516v3 · Ouxiang Li, Yuan Wang, Xinting Hu et al.2025 · 0 citationsarXiv
AppAgent-Pro: A Proactive GUI Agent System for Multidomain Information Integration and User Assistance2508.18689v2 · Yuyang Zhao, Wentao Shi, Fuli Feng et al.2025 · 0 citationsProceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025), ACM, 2025
Navigating Through Paper Flood: Advancing LLM-based Paper Evaluation through Domain-Aware Retrieval and Latent Reasoning2508.05129v2 · Wuqiang Zheng, Yiyan Xu, Xinyu Lin et al.2025 · 0 citationsarXiv
Latent Inter-User Difference Modeling for LLM Personalization2507.20849v2 · Yilun Qiu, Tianhao Shi, Xiaoyan Zhao et al.2025 · 4 citationsarXiv
MathOPEval: A Fine-grained Evaluation Benchmark for Visual Operations of MLLMs in Mathematical Reasoning2507.18140v3 · Xiaoyuan Li, Moxin Li, Wenjie Wang et al.2025 · 0 citationsarXiv
SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs2507.14894v2 · Boyi Deng, Yu Wan, Baosong Yang et al.2025 · 0 citationsarXiv
Teaching LLM to Reason: Reinforcement Learning from Algorithmic Problems without Code2507.07498v2 · Keqin Bao, Nuo Chen, Xiaoyuan Li et al.2025 · 0 citationsarXiv
VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation2507.06899v2 · Ziang Ye, Yang Zhang, Wentao Shi et al.2025 · 0 citationsarXiv
Boosting Parameter Efficiency in LLM-Based Recommendation through Sophisticated Pruning2507.07064v1 · Shanle Zheng, Keqin Bao, Jizhi Zhang et al.2025 · 0 citationsarXiv
Career total: 340 works. 195 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.