8 citations · 18 across the 26 of their papers we have counts for
27 papers
Scaling Automatic Research Agents via World Models
Xiyuan Yang, Sheikh Sarwar, Jingru Cheng +8
Automating empirical research is a long-standing direction of AI. Recent automatic research (AutoResearch) agents bring this goal within reach, as modern LLMs show the capability t…
Predict, Don't Iterate: Efficient Adaptive-Length Infilling for Diffusion Language Models
Haobo Xu, Sirui Chen, Yuanchen Bei +5
Diffusion language models (DLMs) have emerged as a promising alternative to the auto-regressive paradigm. With bidirectional attention and any-order generation, DLMs naturally fit…
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
Tianxin Wei, Zhan Shi, Minhua Lin +14
Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from accumulated traject…
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
Xuying Ning, Dongqi Fu, Tianxin Wei +17
Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, recover from failures, and reuse experience across extended interactions.…
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Yanjun Zhao, Ruizhong Qiu, Tianxin Wei +6
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs) in realistic applications. Although recent LLMs support incre…
Code as Agent Harness
Xuying Ning, Katherine Tieu, Dongqi Fu +39
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineerin…
EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
Ting-Wei Li, Sirui Chen, Jiaru Zou +4
Adapting large language models (LLMs) to a targeted task efficiently and effectively remains a fundamental challenge. Such adaptation often requires iteratively improving the model…
Recursive Multi-Agent Systems
Jiaru Zou, Rui Pan, Ruizhong Qiu +8
Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend…
Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR
Haobo Xu, Sirui Chen, Ruizhong Qiu +5
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, methods such as GRPO and DAPO…
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
Yuanchen Bei, Tianxin Wei, Xuying Ning +7
Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over…
CoFiRec: Coarse-to-Fine Tokenization for Generative Recommendation
Tianxin Wei, Xuying Ning, Xuxing Chen +6
In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific items. However, existing generative recomme…
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Tianxin Wei, Noveen Sachdeva, Benjamin Coleman +12
Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and ev…
Latent Collaboration in Multi-Agent Systems
Jiaru Zou, Ruizhong Qiu, Gaotang Li +10
Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on…
Geometric-disentangelment Unlearning
Duo Zhou, Yuji Zhang, Tianxin Wei +9
Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting u…
Harnessing Consistency for Robust Test-Time LLM Ensemble
Zhichen Zeng, Qi Yu, Xiao Lin +6
Different large language models (LLMs) exhibit diverse strengths and weaknesses, and LLM ensemble serves as a promising approach to integrate their complementary capabilities. Desp…
NIRVANA: Structured Pruning Reimagined for Large Language Model Compression
Mengting Ai, Tianxin Wei, Sirui Chen +1
While structured pruning presents a highly effective pathway for accelerating Large Language Model (LLM) inference, existing methods frequently suffer from significant performance…
PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis
Xinyu He, Chenhan Xiao, Haoran Li +5
Modern power systems are becoming increasingly dynamic, with changing topologies and time-varying loads driven by renewable energy variability, electric vehicle adoption, and activ…
Latte: Collaborative Test-Time Adaptation of Vision-Language Models in Federated Learning
Wenxuan Bao, Ruxi Deng, Ruizhong Qiu +3
Test-time adaptation with pre-trained vision-language models has gained increasing attention for addressing distribution shifts during testing. Among these approaches, memory-based…
Saffron-1: Safety Inference Scaling
Ruizhong Qiu, Gaotang Li, Tianxin Wei +2
Existing safety assurance research has primarily focused on training-phase alignment to instill safe behaviors into LLMs. However, recent studies have exposed these methods' suscep…
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
Zhining Liu, Ze Yang, Xiao Lin +6
Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark…
Tensor Convolutional Network for Higher-Order Interaction Prediction in Sparse Tensors
Jun-Gi Jang, Jingrui He, Andrew Margenot +1
Many real-world data, such as recommendation data and temporal graphs, can be represented as incomplete sparse tensors where most entries are unobserved. For such sparse tensors, i…
ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration
Mengting Ai, Tianxin Wei, Yifan Chen +7
Mixture-of-Experts (MoE) Transformer, the backbone architecture of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for eac…
Transforming the Hybrid Cloud for Emerging AI Workloads
Deming Chen, Alaa Youssef, Ruchi Pendse +42
This white paper, developed through close collaboration between IBM Research and UIUC researchers within the IIDAI Institute, envisions transforming hybrid cloud systems to meet th…
What Do LLMs Need to Understand Graphs: A Survey of Parametric Representation of Graphs
Dongqi Fu, Liri Fang, Zihao Li +3
Graphs, as a relational data structure, have been widely used for various application scenarios, like molecule design and recommender systems. Recently, large language models (LLMs…