2 citations · 7 across the 29 of their papers we have counts for
34 papers
AssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture Assembly
Zhiyuan Qi, Jierui Li, Yifan Shen +2
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains diffi…
LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures
Jiateng Liu, Rushi Wang, Cheng Qian +9
LLM-based agents are increasingly capable of generating complex 3D structures, with the potential to reshape how objects are designed and realized in the physical world. Yet, produ…
Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
Kunlun Zhu, Xuyan Ye, Yibo Li +3
An unsuccessful LLM agent rollout contains more information than its final reward: the observations available to the agent, the actions it chose, and the environment's responses. R…
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Cheng Qian, Kunlun Zhu, Beibin Li +2
Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-AI, asking how a Builder can learn to construct better execution…
Popular Knowledge Propagates More Errors in LLM Knowledge Updating
Yuji Zhang, Weibing Wang, Cheng Qian +5
Updating a language model's knowledge through fine-tuning is essential for keeping its outputs current, yet can also induce factual forgetting and new hallucinations. Prior work sh…
Evaluating the Hidden Costs of Personalization in Large Language Models
Yumeng Wang, Yuchen Wu, Cheng Qian +6
While Large language models (LLMs) incorporate user personalization signals to improve usability and helpfulness, they increasingly shift from providing balanced, informative respo…
Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design
Qing Zong, Jiayu Liu, Junhao Shen +9
Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks and feedb…
Long-Horizon Embodied Decision-Making via Multimodal Memory Compression
Bingxuan Li, Rui Yang, Cheng Qian +6
Agents are increasingly expected to act not only as task executors, but also as decision-makers on behalf of human users. This shift requires agents to accumulate evidence over lon…
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning
Shujin Wu, Cheng Qian, Xiusi Chen +1
Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains. We hypothesize that the success of…
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
Jiayu Liu, Cheng Qian, Zhenhailong Wang +10
Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclosed through…
Trimming the Long-Tail of Visual World Modeling Evaluation
Bingxuan Li, Yining Hong, Cheng Qian +6
Physical interactions follow a long-tailed distribution: a set of common and regular interactions dominates human experience and visual data, while a broad spectrum of rare and irr…
Rethinking Synthetic Rationale Supervision for Disease Prediction
Buxin Su, Bingxuan Li, Cheng Qian +3
Supervised fine-tuning with synthetic rationales is widely assumed to improve clinical prediction by teaching models not only what to predict but why. We test this assumption on fi…
Brick-Composer: Using MLLMs for Assembly with Diverse Bricks
Jiateng Liu, Bingxuan Li, Zhenhailong Wang +8
We dream of AI agents that can read arbitrary designs and construct real-world objects from reusable building blocks. As a first step toward this vision, we study whether multimoda…
UniCAD: A Unified Benchmark and Universal Model for Multi-Modal Multi-Task CAD
Jingyuan Chen, Sheng Jin, Haopeng Sun +2
Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in…
Advancing Creative Physical Intelligence in Large Multimodal Models
Cheng Qian, Hyeonjeong Ha, Jiayu Liu +10
Large multimodal models (LMMs) have rapidly advanced in perception and reasoning; however, it remains unclear whether these capabilities generalize to discovering visually grounded…
MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
Hyeonjeong Ha, Jeonghwan Kim, Cheng Qian +7
Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often co…
UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind
Cheng Qian, Jiayu Liu, Heng Ji
Understanding what a user believes and intends is central to building effective agent assistants. This ability is often evaluated through Theory-of-Mind (ToM) tasks, where success…
CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
Cheng Qian, Hyeonjeong Ha, Jiayu Liu +10
Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains under…
A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents
Tianxin Wei, Ting-Wei Li, Zhining Liu +26
Reasoning is a fundamental cognitive process underlying inference, problem-solving, and decision-making. While large language models (LLMs) demonstrate strong reasoning capabilitie…
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer…
PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning
Bingxuan Li, Jeonghwan Kim, Cheng Qian +4
Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this preference-driven decision process…
From Word to World: Can Large Language Models be Implicit Text-based World Models?
Yixia Li, Hongru Wang, Jiahao Qiu +7
Agentic reinforcement learning increasingly relies on experience-driven scaling, yet real-world environments remain non-adaptive, limited in coverage, and difficult to scale. World…
Self-Improving LLM Agents at Test-Time
Emre Can Acikgoz, Cheng Qian, Heng Ji +2
One paradigm of language model (LM) fine-tuning relies on creating large training datasets, under the assumption that high quantity and diversity will enable models to generalize t…
Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning
Qi He, Cheng Qian, Xiusi Chen +3
Claim verification with large language models (LLMs) has recently attracted growing attention, due to their strong reasoning capabilities and transparent verification processes com…