BD
Bryan Dai
cs.AIcs.CLcs.LGcs.SEcs.CVcs.IRcs.ARcs.CRcs.DBcs.HC
On Valency
published · living versionsW_eeq3w9uy·v1 · currentpublished
Multiscale Policy Optimization for Long-Horizon LLM Agents
with Tao Ren, Hui Yang, Jia Deng, Tingyang Chen +14
1 version
W_cpfgmpf4·v1published
W_j4fhuxv6·v2published
Preprints & journals
36 papers in the corpus · 2025–2026IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems2610.30949v1 · A. Jian Yang, An Huang, Bo Dan et al.2026 · 0 citationsarXiv
ProductWebBench: Evaluating Website Continuity Beyond Task Completion2610.31118v1 · Jiajun Wu, Jian Yang, Yaxin Du et al.2026 · 0 citationsarXivon Valency
Harness Scaling for Generalizable Agentic Reinforcement Learning2610.29458v2 · Fei Bai, Huatong Song, Chuan Hao et al.2026 · 0 citationsarXivon Valency
When Can LLM Reasoning Reliably Reuse Intermediate Results?2610.27662v1 · Deyuan Liu, Zecheng Wang, Xuanyi Liu et al.2026 · 0 citationsarXiv
RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents2610.22507v1 · Yunqi Liu, Peiyu Wang, Bingli Wang et al.2026 · 0 citationsarXiv
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding2610.19849v1 · Boyuan Sun, Deshui Miao, Wenzhao Gao et al.2026 · 0 citationsarXiv
AutoDataBench: A Data-centric Testbed for Accelerating Auto Research2609.40097v1 · Ruifeng Yuan, Yizhi Li, Yaxin Du et al.2026 · 0 citationsarXiv
SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization2609.14320v1 · Zian Liu, Yiwen Hu, Zican Dong et al.2026 · 0 citationsarXiv
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild2608.23181v3 · Jian Yang, Haau-Sing Li, Shawn Guo et al.2026 · 0 citationsarXiv
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models2608.16647v3 · Zhaoyi Li, Deyang Kong, Yuan Wei et al.2026 · 0 citationsarXiv
ClawGym II: Exploring Black-Box RL on Agent Harness2608.16798v1 · Huatong Song, Fei Bai, Ming Yang et al.2026 · 0 citationsarXiv
Hyperball May Not Be a Free Lunch2607.22444v1 · Yihao Xiao, Jialong Sun, Zitian Gao et al.2026 · 0 citationsarXiv
Best-of-Evidence: Best-of-N Selection under Partial Verification2607.20950v1 · Cenwei Zhang, Teng Fang, Yuxia Wang et al.2026 · 0 citationsarXiv
Loop the Loopies!2607.16051v3 · Zitian Gao, Yilong Chen, Yihao Xiao et al.2026 · 0 citationsarXiv
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling2606.18023v1 · Jian Yang, Shawn Guo, Wei Zhang et al.2026 · 0 citationsarXiv
HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents2606.13663v1 · Yaxin Du, Yifan Zhou, Yujie Ge et al.2026 · 0 citationsarXiv
UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA2606.11740v1 · Mengzhuo Chen, Yan Shu, Chi Liu et al.2026 · 0 citationsarXiv
Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher2606.13710v2 · Hongming Piao, Chi Liu, Mengzhuo Chen et al.2026 · 0 citationsarXiv
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection2605.30288v2 · Haowen Wang, Yaxin Du, Jian Yang et al.2026 · 0 citationsarXiv
LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving2605.13137v2 · Guoxiong Gao, Zeming Sun, Jiedong Jiang et al.2026 · 0 citationsarXiv
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy2605.10344v2 · George Wu, Nan Jing, Qing Yi et al.2026 · 0 citationsarXiv
ClawGym: A Scalable Framework for Building Effective Claw Agents2604.26904v3 · Fei Bai, Huatong Song, Shuang Sun et al.2026 · 0 citationsarXiv
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling2604.21724v2 · Yilong Chen, Yanxi Xie, Zitian Gao et al.2026 · 0 citationsarXiv
Matlas: A Semantic Search Engine for Mathematics2604.17484v1 · Haocheng Ju, Leheng Chen, Peihao Wu et al.2026 · 0 citationsarXiv
Automated Conjecture Resolution with Formal Verification2604.03789v2 · Haocheng Ju, Guoxiong Gao, Jiedong Jiang et al.2026 · 0 citationsarXiv
InCoder-32B-Thinking: Industrial Code World Model for Thinking2604.03144v1 · Jian Yang, Wei Zhang, Jiajun Wu et al.2026 · 0 citationsarXiv
Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization2603.24093v1 · Fei Bai, Zhipeng Chen, Chuan Hao et al.2026 · 0 citationsarXiv
IQuest-Coder-V1 Technical Report2603.16733v1 · Jian Yang, Wei Zhang, Shawn Guo et al.2026 · 0 citationsarXiv
InCoder-32B: Code Foundation Model for Industrial Scenarios2603.16790v3 · Jian Yang, Wei Zhang, Jiajun Wu et al.2026 · 0 citationsarXiv
CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs2602.07080v1 · Yicheng He, Zheng Zhao, Zhou Kaiyu et al.2026 · 0 citationsarXiv
Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments2602.01244v3 · Siwei Wu, Yizhi Li, Yuyang Song et al.2026 · 1 citationarXiv
AGRO-SQL: Agentic Group-Relative Optimization with High-Fidelity Data Synthesis2512.23366v1 · Cehua Yang, Dongyu Xiao, Junming Lin et al.2025 · 0 citationsarXiv
M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation2512.22628v1 · Fanglin Xu, Wei Zhang, Jian Yang et al.2025 · 0 citationsarXiv
Context as a Tool: Context Management for Long-Horizon SWE-Agents2512.22087v1 · Shukai Liu, Jian Yang, Bo Jiang et al.2025 · 1 citationarXiv
Universal Reasoning Model2512.14693v3 · Zitian Gao, Lynx Chen, Yihao Xiao et al.2025 · 0 citationsarXiv
Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMs2511.00916v1 · Yan Shu, Chi Liu, Robin Chen et al.2025 · 0 citationsarXiv
Career total: 39 works. 36 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.