2 citations · 4 across the 31 of their papers we have counts for
37 papers
Prospective Memory for Proactive LLM Agents
Yuanchen Bei, Zhining Liu, Tianxin Wei +6
Most memory systems for LLM agents are retrospective, preserving and retrieving past information to inform current decisions. Proactive agents, however, also require prospective me…
ProbePO: Sparse Probes, Redistributed Credit for Critic-Free LLM Reinforcement Learning
Diyi Hu, Ruizhong Qiu, Lin Qiu +2
Reinforcement learning from verifiable rewards assigns one terminal reward to an entire reasoning trajectory, obscuring how individual reasoning steps contributed to the outcome. G…
Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry
Qi Yu, Ruizhong Qiu, Zhichen Zeng +6
Reinforcement learning with verifiable rewards (RLVR) has been shown to improve the reasoning capability of large language models (LLMs) across diverse reasoning tasks. However, gr…
PolicyMem: Geometric Policy Memory for LLM Governance
Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao +3
Effective LLM governance extends beyond detecting unsafe responses to guiding their correction through closed-loop assessment, revision, and verification. Learning-based guards pro…
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…
One Model, Many Minds: Unlocking Multi-Agent Synergy in a Single Agent via Mixture of Roles
Zhichen Zeng, Huiyuan Chen, Jingru Cheng +7
Specializing Large Language Models (LLMs) toward distinct abilities underpins successes ranging from personalized assistants to multi-agent systems (MAS). Single-agent paradigms re…
Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attribution
Ting-Wei Li, Yuanchen Bei, Xiao Lin +1
Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outcomes. This motivates the task…
From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model
Qi Yu, Zhichen Zeng, Katherine Tieu +8
Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference. Although significant effo…
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…
TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning
Lingjie Chen, Yuanchen Bei, Haobo Xu +3
Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often hand…
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…
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM-based Multi-Agent Systems
Hezhe Qiao, Hanghang Tong, Ee-Peng Lim +2
Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliability. Automatic failure attri…
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9
Deep research agents plan, search, evaluate evidence, and synthesize long-form reports. Training these agents with reinforcement learning (RL) is challenging because they operate o…
PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs
Yanjun Zhao, Tianxin Wei, Jiaru Zou +7
Understanding scientific papers requires more than answering isolated questions or summarizing content. It involves an integrated reasoning process that grounds textual and visual…
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…
TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
Lingjie Chen, Ruizhong Qiu, Yuyu Fan +2
Diffusion language models (DLMs) offer a promising path toward low-latency generation through parallel decoding, but their practical efficiency depends heavily on the decoding traj…
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…
MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
Xuying Ning, Dongqi Fu, Tianxin Wei +7
With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve…
FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation
Xinrui He, Ting-Wei Li, Tianxin Wei +5
Federated cross-domain recommendation (Federated CDR) aims to collaboratively learn personalized recommendation models across heterogeneous domains while preserving data privacy. R…
Graph homophily booster: Reimagining the role of discrete features in heterophilic graph learning
Ruizhong Qiu, Ting-Wei Li, Gaotang Li +1
Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nod…
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Wei-Chieh Huang, Weizhi Zhang, Yueqing Liang +56
Research in artificial intelligence is shifting from model innovations and benchmark scores towards problem definition and rigorous real-world evaluation. As the field enters the "…
Do VLMs Have a Moral Backbone? A Study on the Fragile Morality of Vision-Language Models
Zhining Liu, Tianyi Wang, Xiao Lin +9
Despite substantial efforts toward improving the moral alignment of Vision-Language Models (VLMs), it remains unclear whether their ethical judgments are stable in realistic settin…