58 citations · 188 across the 90 of their papers we have counts for
94 papers
Self-Evolving Embodied Agents via Skill-Harness Evolution
Peidong Wang, Zhiming Ma, Ying Chang +7
Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills, context, action interfaces,…
Agent Lightning v1.0: Towards Harnessed Agentic RL
Zhiyuan He, Siwei Zhang, Zhiwen Zhou +7
Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a critical part of the agent system. Our original Agent Lightning intr…
Beyond Text Conditioning: A Systematic Study of MLLM-DiT Fusion for Video Generation
Yanbo Ding, Yijia Fan, Caihua Shan +8
Diffusion Transformers (DiTs) have become the dominant paradigm for high-fidelity video generation, yet their ability to perform high-level semantic planning remains limited. While…
From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization
Ying Chang, Jiahang Xu, Xuan Feng +3
The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to diagnose agent failures and i…
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Yuqing Yang, Qi Zhu, Zhen Han +5
While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understan…
What are Key Factors for Updates in RL for LLM Reasoning?
Peidong Wang, Demi Wang, Xufang Luo +5
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising framework for enhancing the reasoning ability of large language models. However, much of the existi…
Memory Retrieval for Changing Preferences
Yuehan Qin, Li Li, Linxin Song +4
Long-context dialogue systems must decide both when to access memory and which parts of the interaction history are relevant. Existing approaches typically rely on heuristic retrie…
Latent Spatial Memory for Video World Models
Weijie Wang, Haoyu Zhao, Yifan Yang +7
Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space. This design is both computat…
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Weijie Wang, Xiaoxuan He, Youping Gu +9
Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via…
SkillOpt: Executive Strategy for Self-Evolving Agent Skills
Yifan Yang, Ziyang Gong, Weiquan Huang +12
Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning optimizer for the skill, an…
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
Jeonghye Kim, Jiwon Jeon, Dongsheng Li +1
Self-distillation has emerged as a powerful framework for post-training LLMs, where a teacher conditioned on extra information guides a student without it, both from the same model…
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
Yan Li, Zezi Zeng, Yifan Yang +12
The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visualizations to be created on demand for webpage design, offering a flexi…
Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
Yuqing Yang, Tengxiao Liu, Wang Bill Zhu +3
As LLM-based assistants become persistent and personalized, they must extract and retain useful information from past conversations as memory. However, the types of information wor…
AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
Ziwei Zhou, Zeyuan Lai, Rui Wang +6
Text-to-Audio-Video (T2AV) generation is rapidly becoming a core interface for media creation, yet its evaluation remains fragmented. Existing benchmarks largely assess audio and v…
Beyond identifiability: Learning causal representations with few environments and finite samples
Inbeom Lee, Tongtong Jin, Bryon Aragam
We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide…
SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
Yiqi Zhang, Huiqiang Jiang, Xufang Luo +7
Scaling reinforcement learning (RL) has shown strong promise for enhancing the reasoning abilities of large language models (LLMs), particularly in tasks requiring long chain-of-th…
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
Zeyuan Liu, Jeonghye Kim, Xufang Luo +2
Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environme…
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Jeonghye Kim, Xufang Luo, Minbeom Kim +5
Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we…
Parallelizing Tool Execution and LLM Generation for Low-Latency Agent Serving
Yifan Sui, Han Zhao, Rui Ma +6
LLM-powered agents execute tasks through a sequential loop of model generation and tool execution. Today's serving systems serialize this loop, leaving tool latency exposed on the…
Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty
Jeonghye Kim, Xufang Luo, Minbeom Kim +3
LLMs often exhibit Aha moments such as self-correction after tokens like "Wait," yet the underlying mechanism remains unclear. Standard LLMs collapse mainly through silent divergen…
From Struggle to Success: Context-Aware Guidance for Screen Reader Users in Computer Use
Nan Chen, Jing Lu, Zilong Wang +3
Equal access to digital technologies is critical for education, employment, and social participation. However, mainstream interfaces are visually oriented, creating steep learning…
PosIR: Position-Aware Heterogeneous Information Retrieval Benchmark
Ziyang Zeng, Dun Zhang, Yu Yan +4
In real-world documents, the information relevant to a user query may reside anywhere from the beginning to the end. This makes position bias -- a systematic tendency of retrieval…
Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search
Ziyang Zeng, Heming Jing, Jindong Chen +11
Ranking relevance is a fundamental task in search engines, aiming to identify the items most relevant to a given user query. Traditional relevance models typically produce scalar s…
Optimize Replica Server Placement in a Satellite Network
Zhiyuan He, Yi Xu, Cheng Luo +2
Satellite communication offers Internet connectivity to remote locations, such as villages, deserts, mountains, and at sea. However, transmitting content over satellite networks is…