CQ
Cheng Qian
cs.CLcs.AIcs.LGcs.CVcs.GTcs.HCcs.MA
On Valency
published · living versionsW_s3knahgg·v1 · currentpublished
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
with Rui Wang, Zishen Lai, Jiayu Liu, Jeonghwan Kim +13
1 version
Preprints & journals
18 papers in the corpus · 2024–2026AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments2610.25950v1 · Rui Wang, Zishen Lai, Jiayu Liu et al.2026 · 0 citationsarXivon Valency
AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning2610.22194v1 · Bingxiang He, Pengqi Sun, Shihao Peng et al.2026 · 0 citationsarXiv
Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training2609.40111v2 · Kunlun Zhu, Xuyan Ye, Yibo Li et al.2026 · 0 citationsarXiv
Popular Knowledge Propagates More Errors in LLM Knowledge Updating2609.08067v1 · Yuji Zhang, Weibing Wang, Cheng Qian et al.2026 · 0 citationsarXiv
Rethinking On-Policy Distillation of Large Language Models II: One Training Example2609.04172v1 · Zixuan Fu, Bingxiang He, Yuxin Zuo et al.2026 · 0 citationsarXiv
Evaluating the Hidden Costs of Personalization in Large Language Models2608.28833v1 · Yumeng Wang, Yuchen Wu, Cheng Qian et al.2026 · 0 citationsarXiv
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses2608.12307v1 · Cheng Qian, Wenting Zhao, Liangwei Yang et al.2026 · 0 citationsarXiv
Long-Horizon Embodied Decision-Making via Multimodal Memory Compression2608.01456v1 · Bingxuan Li, Rui Yang, Cheng Qian et al.2026 · 0 citationsarXiv
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning2607.21971v2 · Shujin Wu, Cheng Qian, Xiusi Chen et al.2026 · 0 citationsarXiv
How Far Can Unsupervised RLVR Scale LLM Training?2603.08660v1 · Bingxiang He, Yuxin Zuo, Zeyuan Liu et al.2026 · 0 citationsarXiv
Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data2602.21320v1 · Emre Can Acikgoz, Cheng Qian, Jonas Hubotter et al.2026 · 0 citationsarXiv
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning2601.11957v4 · Bingxuan Li, Jeonghwan Kim, Cheng Qian et al.2026 · 0 citationsarXiv
Current Agents Fail to Leverage World Model as Tool for Foresight2601.03905v2 · Cheng Qian, Emre Can Acikgoz, Bingxuan Li et al.2026 · 0 citationsarXiv
From Word to World: Can Large Language Models be Implicit Text-based World Models?2512.18832v2 · Yixia Li, Hongru Wang, Jiahao Qiu et al.2025 · 0 citationsarXiv
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents2511.02734v3 · Jiayu Liu, Cheng Qian, Zhaochen Su et al.2025 · 1 citationarXiv
ShortageSim: Simulating Drug Shortages under Information Asymmetry2509.01813v3 · Mingxuan Cui, Yilan Jiang, Duo Zhou et al.2025 · 0 citationsarXiv
ToolRL: Reward is All Tool Learning Needs2504.13958v1 · Cheng Qian, Emre Can Acikgoz, Qi He et al.2025 · 9 citationsarXiv
Aligning LLMs with Individual Preferences via Interaction2410.03642v2 · Shujin Wu, May Fung, Cheng Qian et al.2024 · 0 citationsarXiv
Career total: 24 works. 18 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.