TZ
Tianshi Zheng
cs.CLcs.AIcs.LGcs.CVcs.DBcs.SE
On Valency
published · living versionsW_78vhtbmk·v1 · currentpublished
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
with Zhongwei Xie, Yiming Du, Jiaxin Bai, Baixuan Xu +8
1 version
W_s3knahgg·v1published
Preprints & journals
47 papers in the corpus · 2023–2026AdaExploreBench: 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
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents2610.24960v1 · Zhongwei Xie, Yiming Du, Jiaxin Bai et al.2026 · 0 citationsarXivon Valency
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition2610.14966v1 · Yuxuan Liu, Zhaochen Su, Hangyu Guo et al.2026 · 0 citationsarXiv
When Should an In-Context Learner Expand Its Hypothesis Space?2610.09471v4 · Weihan Li, Xinlei Chen, Junhao Wu et al.2026 · 0 citationsarXiv
Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State2610.05292v1 · Weihan Li, Tianshi Zheng, Junhao Wu et al.2026 · 0 citationsarXiv
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe2610.03092v3 · Weihan Li, Tianshi Zheng, Yangqiu Song et al.2026 · 0 citationsarXiv
Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?2609.22850v4 · Weihan Li, Xinlei Chen, Yuhan Song et al.2026 · 0 citationsarXiv
AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era2609.07611v1 · Yunxiang Mo, Tianshi Zheng, Yisen Gao et al.2026 · 0 citationsarXiv
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos2608.26355v1 · Baixuan Xu, Yinyui Xu, Tianshi Zheng et al.2026 · 0 citationsarXiv
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning2607.26465v2 · Kawai Chung, Chunkit Chan, Yauwai Yim et al.2026 · 0 citationsarXiv
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding2606.20873v1 · Yueming Wang, Tianshi Zheng, Jiaxin Bai et al.2026 · 0 citationsarXiv
SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents2606.16591v2 · Qiao Xiao, Haochen Shi, Yisen Gao 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
One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs2605.31370v2 · Yisen Gao, Yixi Cai, Tianshi Zheng et al.2026 · 0 citationsarXiv
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning2605.25920v2 · Wei Fan, Yining Zhou, Mufan Zhang et al.2026 · 0 citationsarXiv
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models2605.14906v1 · Xiyu Ren, Zhaowei Wang, Yiming Du et al.2026 · 0 citationsarXiv
SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning2605.01489v2 · Tianshi Zheng, Rui Wang, Xiyun Li et al.2026 · 0 citationsarXiv
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems2601.11004v4 · Jiayu Liu, Rui Wang, Qing Zong et al.2026 · 0 citationsarXiv
SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generation2511.02854v1 · Yixiang Chen, Tianshi Zheng, Shijue Huang et al.2025 · 0 citationsarXiv
CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?2510.24505v1 · Qing Zong, Jiayu Liu, Tianshi Zheng et al.2025 · 0 citationsarXiv
AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction2510.15339v3 · Hong Ting Tsang, Jiaxin Bai, Haoyu Huang et al.2025 · 1 citationarXiv
DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay2510.10117v1 · Yunxiang Mo, Tianshi Zheng, Qing Zong et al.2025 · 0 citationsarXiv
The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas2510.07091v1 · Baixuan Xu, Tianshi Zheng, Zhaowei Wang et al.2025 · 0 citationsarXiv
NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents2510.07172v3 · Tianshi Zheng, Kelvin Kiu-Wai Tam, Newt Hue-Nam K. Nguyen et al.2025 · 0 citationsarXiv
LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game2510.04980v1 · Fangzhou Liang, Tianshi Zheng, Chunkit Chan et al.2025 · 0 citationsarXiv
Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework2508.12257v1 · Zheye Deng, Chunkit Chan, Tianshi Zheng et al.2025 · 0 citationsarXiv
Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty2508.08992v5 · Rui Wang, Qihan Lin, Jiayu Liu et al.2025 · 0 citationsarXiv
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training2508.00414v3 · Tianqing Fang, Zhisong Zhang, Xiaoyang Wang et al.2025 · 0 citationsarXiv
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora2505.23628v3 · Jiaxin Bai, Wei Fan, Qi Hu et al.2025 · 6 citationsarXiv
Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs2505.20948v3 · Yisen Gao, Jiaxin Bai, Tianshi Zheng et al.2025 · 0 citationsarXiv
INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling2505.16303v1 · Haochen Shi, Tianshi Zheng, Weiqi Wang et al.2025 · 0 citationsarXiv
Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents2505.14104v2 · Wei Fan, Tianshi Zheng, Yiran Hu et al.2025 · 0 citationsarXiv
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery2505.13259v3 · Tianshi Zheng, Zheye Deng, Hong Ting Tsang et al.2025 · 19 citationsarXiv
Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study2505.07313v2 · Baixuan Xu, Chunyang Li, Weiqi Wang et al.2025 · 0 citationsarXiv
The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning2504.05081v2 · Tianshi Zheng, Yixiang Chen, Chengxi Li et al.2025 · 1 citationarXiv
Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations2502.16169v2 · Chunyang Li, Weiqi Wang, Tianshi Zheng et al.2025 · 1 citationarXiv
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning2502.11176v4 · Tianshi Zheng, Jiayang Cheng, Chunyang Li et al.2025 · 1 citationarXiv
Top Ten Challenges Towards Agentic Neural Graph Databases2501.14224v1 · Jiaxin Bai, Zihao Wang, Yukun Zhou et al.2025 · 1 citationarXiv
Enhancing Transformers for Generalizable First-Order Logical Entailment2501.00759v3 · Tianshi Zheng, Jiazheng Wang, Zihao Wang et al.2025 · 1 citationarXiv
ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty2412.20251v2 · Qing Zong, Zhaowei Wang, Tianshi Zheng et al.2024 · 1 citationarXiv
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?2412.08985v4 · Tianshi Zheng, Weihan Li, Jiaxin Bai et al.2024 · 3 citationsarXiv
Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information2408.02559v1 · Yauwai Yim, Chunkit Chan, Tianyu Shi et al.2024 · 9 citationsarXiv
CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge2407.20564v1 · Tianshi Zheng, Jiaxin Bai, Yicheng Wang et al.2024 · 1 citationarXiv
Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction2404.14215v2 · Zheye Deng, Chunkit Chan, Weiqi Wang et al.2024 · 2 citationsarXiv
Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation2312.15643v3 · Jiaxin Bai, Yicheng Wang, Tianshi Zheng et al.2023 · 6 citationsarXiv
TILFA: A Unified Framework for Text, Image, and Layout Fusion in Argument Mining2310.05210v1 · Qing Zong, Zhaowei Wang, Baixuan Xu et al.2023 · 2 citationsarXiv
Sequential Query Encoding For Complex Query Answering on Knowledge Graphs2302.13114v3 · Jiaxin Bai, Tianshi Zheng, Yangqiu Song2023 · 6 citationsarXiv
Career total: 62 works. 47 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.