JP
Jiaxin Pei
cs.AIcs.CLcs.CYcs.HCcs.LGcs.MAcs.SEcs.NIcs.CEcs.CR
On Valency
published · living versionsW_dm5xu66x·v1 · currentpublished
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
with Yijiang River Dong, Zexue He, Cheng Yu, Tiancheng Hu +7
1 version
Preprints & journals
22 papers in the corpus · 2025–2026Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use2610.31272v1 · Yijiang River Dong, Zexue He, Cheng Yu et al.2026 · 0 citationsarXivon Valency
SWE-VERIFIER: Selective Verification for Cost-Efficient Coding Agents2610.30284v1 · Kaijian Zou, Vaibhav Chennareddy, Yunxiang Zhang et al.2026 · 0 citationsarXiv
Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?2610.22155v3 · Jingyu Tang, Xu Yang, Zhehao Zhang et al.2026 · 0 citationsarXiv
AI Should Facilitate Democratic Deliberation at Scale2609.20059v1 · Jos'e Ram'on Enr'iquez, Jiaxin Pei, Alex Pentland2026 · 0 citationsProceedings of the 43 rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026
AISPA: User-Centric System Prompt Auditing for Large Language Model Applications2607.28617v2 · Xiangning Lin, Shenzhe Zhu, Shu Yang et al.2026 · 0 citationsarXiv
Humanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing2607.21758v1 · Shenzhe Zhu, Haoqian Zhang, Xu Yang et al.2026 · 0 citationsarXiv
Interactive Task Alignment as a POMDP2607.16412v1 · Andy Dai, Zexue He, Zhenyu Zhang et al.2026 · 0 citationsarXiv
ProACT: Towards Breakdown-Aware Proactive Agent in Multi-User Collaboration2607.03730v1 · Shu Yang, Difei Xu, Jiaxin Pei et al.2026 · 0 citationsarXiv
ChainSWE: Benchmarking Coding Agents on Multi-Bug Software Maintenance2607.02606v2 · Qirui Jin, Lingching Tung, Kenan Li et al.2026 · 0 citationsarXiv
BAGEN: Are LLM Agents Budget-Aware?2606.00198v1 · Yuxiang Lin, Zihan Wang, Mengyang Liu et al.2026 · 1 citationarXiv
Interactive Evaluation Requires a Design Science2605.17829v1 · Keyang Xuan, Peiyang Song, Pan Lu et al.2026 · 0 citationsarXiv
SWE-Edit: Rethinking Code Editing for Efficient SWE-Agent2604.26102v2 · Yikai Zhang, Jiaxin Pei, Kenan Li et al.2026 · 0 citationsarXiv
The Last Human-Written Paper: Agent-Native Research Artifacts2604.24658v3 · Jiachen Liu, Jiaxin Pei, Jintao Huang et al.2026 · 0 citationsarXiv
How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks2604.22750v3 · Longju Bai, Zhemin Huang, Xingyao Wang et al.2026 · 3 citationsarXiv
Quantifying Trust: Financial Risk Management for Trustworthy AI Agents2604.03976v2 · Wenyue Hua, Tianyi Peng, Chi Wang et al.2026 · 0 citationsarXiv
Multi-User Large Language Model Agents2604.08567v2 · Shu Yang, Shenzhe Zhu, Hao Zhu et al.2026 · 0 citationsarXiv
CooperBench: Why Coding Agents Cannot be Your Teammates Yet2601.13295v2 · Arpandeep Khatua, Hao Zhu, Peter Tran et al.2026 · 0 citationsarXiv
Permission Manifests for Web Agents2601.02371v2 · Samuele Marro, Alan Chan, Xinxing Ren et al.2025 · 0 citationsarXiv
Benchmarking Overton Pluralism in LLMs2512.01351v2 · Elinor Poole-Dayan, Jiayi Wu, Taylor Sorensen et al.2025 · 0 citationsarXiv
Identity Management for Agentic AI: The new frontier of authorization, authentication, and security for an AI agent world2510.25819v1 · Tobin South, Subramanya Nagabhushanaradhya, Ayesha Dissanayaka et al.2025 · 0 citationsOpenID Foundation Whitepaper, 2025
ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents2510.23822v1 · Zhenyu Zhang, Tianyi Chen, Weiran Xu et al.2025 · 0 citations39th Conference on Neural Information Processing Systems (NeurIPS 2025)
The Automated but Risky Game: Modeling and Benchmarking Agent-to-Agent Negotiations and Transactions in Consumer Markets2506.00073v4 · Shenzhe Zhu, Jiao Sun, Yi Nian et al.2025 · 0 citationsarXiv
Career total: 26 works. 22 are in this corpus.
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.