5 citations · 11 across the 39 of their papers we have counts for
47 papers
Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models
Weihan Li, Junhao Wu, Xinlei Chen +1
Language models can produce similar probabilistic predictions after observing outcomes, reading summaries, receiving instructions, or undergoing activation interventions. Whether t…
Toward Knowledge-Centric AI: Discovering, Internalizing, and Using Explicit Knowledge Across Agents and Generations
Yisen Gao, Haoyu Huang, Zhongwei Xie +7
Knowledge is how understanding accumulates across people and generations: durable records that outlive their producers and that others can check, combine, teach, and correct. AI ag…
SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition
Yuxuan Liu, Zhaochen Su, Hangyu Guo +11
Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluation is to expand task requir…
Before Bringing It Up: When and How AI Companions Should Use Memory
Zihan Guo, Roxy He, Junwei Quan
Memory can sustain AI companionship, yet even accurate recollection can be inappropriate to use. Two rounds of formative interviews with 14 users (n = 6 exploratory, n = 8 memory-f…
Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State
Weihan Li, Tianshi Zheng, Junhao Wu +1
What happens to information a pretrained model already encodes when post-training no longer rewards using it? The common language of representation compression conflates three fate…
ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe
Weihan Li, Tianshi Zheng, Yangqiu Song +2
Scientific discovery often begins when scattered clues call for a new way of describing the world. Such abductive exploration can require constructing the representation in which a…
Same Outcome, Different Readout: What Does a Steerable Valence Direction in LLMs Represent?
Weihan Li, Xinlei Chen, Yuhan Song +2
Claims about what an internal direction in an LLM represents need evidential constraints beyond an observer's prior beliefs about the system. Decodability and successful activation…
AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era
Yunxiang Mo, Tianshi Zheng, Yisen Gao +7
Scientific ideation is the capacity to formulate novel and testable hypotheses from scientific evidence, and autonomous AI scientists depend on it. Existing evaluations largely ass…
MultivationBench: A Benchmark for Multimodal Sequential Motivation Reasoning
Kawai Chung, Chunkit Chan, Yauwai Yim +12
Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning…
Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos
Baixuan Xu, Yinyui Xu, Tianshi Zheng +9
While LVLMs rapidly improve, long-video question answering still remains challenging: relevant evidence is sparse, and question-relevant context often fails to provide cues that di…
Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
Tian Zheng, Kai-Tai Hsu
Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics. This makes them more challenging to evaluate than single-turn LLM res…
Target-Aware Linear Regression Under Distribution Shift
Zhewen Hou, Tian Zheng
Distribution shift between training and deployment is a pervasive challenge for modern AI systems. In many cases, the target marginals of covariates and response are known or speci…
SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding
Yueming Wang, Tianshi Zheng, Jiaxin Bai +3
Scientific discovery increasingly relies on automated systems that generate hypotheses, inspect multimodal evidence, and validate claims at scale. Yet scientific claim verification…
SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents
Qiao Xiao, Haochen Shi, Yisen Gao +9
Large language model (LLM) agents increasingly rely on agent harnesses that manage context, tools, and multi-turn execution, making tools a central interface for acting in realisti…
One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs
Yisen Gao, Yixi Cai, Tianshi Zheng +2
Abductive reasoning over knowledge graphs (KGs) seeks a first-order logic hypothesis whose answer set explains a given set of observed entities. Since many hypotheses can explain t…
SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
Tianshi Zheng, Rui Wang, Xiyun Li +5
Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to…
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
Wei Fan, Yining Zhou, Mufan Zhang +8
While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must matc…
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
Xiyu Ren, Zhaowei Wang, Yiming Du +11
Memory is essential for large vision-language models (LVLMs) to handle long, multimodal interactions, with two method directions providing this capability: long-context LVLMs and m…
PatchWorld: Gradient-Free Optimization of Executable World Models for Agent Environments
Jiaxin Bai, Yue Guo, Yifei Dong +13
World models for interactive text agents must typically be learned from observation-action trajectories alone. Specifically, the environment returns text observations after each ac…
NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems
Jiayu Liu, Rui Wang, Qing Zong +9
Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is wid…
CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
Qing Zong, Jiayu Liu, Tianshi Zheng +7
Accurate confidence calibration in Large Language Models (LLMs) is critical for safe use in high-stakes domains, where clear verbalized confidence enhances user trust. Traditional…
DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
Yunxiang Mo, Tianshi Zheng, Qing Zong +6
Multimodal abductive reasoning--the generation and selection of explanatory hypotheses from partial observations--is a cornerstone of intelligence. Current evaluations of this abil…
The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
Baixuan Xu, Tianshi Zheng, Zhaowei Wang +4
Enabling LLMs to effectively operate long-horizon task which requires long-term planning and multiple interactions is essential for open-world autonomy. Conventional methods adopt…
LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game
Fangzhou Liang, Tianshi Zheng, Chunkit Chan +2
Effective multi-agent collaboration requires agents to infer the rationale behind others' actions, a capability rooted in Theory-of-Mind (ToM). While recent Large Language Models (…