1 citations · 1 across the 21 of their papers we have counts for
26 papers
Continual Test-Time Learning with Evolution Strategies
Guangya Hao, Yiting Duan, Longyan Tan +5
Large language models increasingly operate in open-ended environments, where they are expected to continually adapt to evolving tasks and distributions, often without access to ext…
Scaling Multi-Agent Intelligence with Substrate-Centric Coordination
Zhenting Qi, Zhuokai Zhao, Rulin Shao +7
Existing large language model (LLM) based multi-agent systems have been shown to scale poorly, and we identify three problems: reading burden that grows with the group, useful info…
Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall
Jacqueline He, Howard Yen, Shuyue Stella Li +9
Logit-based knowledge distillation (KD) is used to train smaller language models (LMs) via supervision from stronger teachers, but whether its benefits are consistent across traini…
SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning
Mingyuan Wu, Jingcheng Yang, Shengyi Qian +11
We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning. For each query, the m…
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Yifan Wu, Lizhu Zhang, Yuhang Zhou +5
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task require…
SWE-Together: Evaluating Coding Agents in Interactive User Sessions
Yifan Wu, Zhuokai Zhao, Songlin Li +8
Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with us…
SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation
Yuhang Zhou, Lizhu Zhang, Yifan Wu +5
On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in ag…
OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification
Yuhang Zhou, Lizhu Zhang, Yifan Wu +5
On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy dist…
Self-Evolving Multi-Agent Systems via Decentralized Memory
Guangya Hao, Yunbo Long, Zhuokai Zhao
Self-evolving multi-agent systems (MAS) have emerged as a promising route to LLM agents that continually improve from experience, with persistent memory at their foundation. Howeve…
Self-Policy Distillation via Capability-Selective Subspace Projection
Guangya Hao, Yitong Shang, Yunbo Long +2
Self-distillation bootstraps large language models (LLMs) by training on their own generations. However, existing methods either rely on external signals to curate self-generated o…
Agentic Recommender System with Hierarchical Belief-State Memory
Xiang Shen, Yuhang Zhou, Yifan Wu +8
Memory-augmented LLM agents have advanced personalized recommendation, yet existing approaches universally adopt flat memory representations that conflate ephemeral signals with st…
Synthetic Sandbox for Training Machine Learning Engineering Agents
Yuhang Zhou, Lizhu Zhang, Yifan Wu +4
As large language model agents advance beyond software engineering (SWE) tasks toward machine learning engineering (MLE), verifying agent behavior becomes orders of magnitude more…
LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems
Yuhang Zhou, Zhuokai Zhao, Ke Li +14
Feature selection is a crucial step in large-scale industrial machine learning systems, directly affecting model accuracy, efficiency, and maintainability. Traditional feature sele…
TARo: Token-level Adaptive Routing for LLM Test-time Alignment
Arushi Rai, Qiang Zhang, Hanqing Zeng +5
Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer…
Token-Level LLM Collaboration via FusionRoute
Nuoya Xiong, Yuhang Zhou, Hanqing Zeng +5
Large language models (LLMs) exhibit strengths across diverse domains. However, achieving strong performance across these domains with a single general-purpose model typically requ…
Exploring System 1 and 2 communication for latent reasoning in LLMs
Julian Coda-Forno, Zhuokai Zhao, Qiang Zhang +6
Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base…
Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding
Yuhang Zhou, Mingrui Zhang, Ke Li +12
Understanding and reasoning over tables is a critical capability for many real-world applications. Large language models (LLMs) have shown promise on this task, but current approac…
Thought Communication in Multiagent Collaboration
Yujia Zheng, Zhuokai Zhao, Zijian Li +4
Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject t…
Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning
Chenghao Yang, Lin Gui, Chenxiao Yang +3
Reinforcement learning with verifiable rewards (RLVR) is a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs), yet its success hinges on eff…
LILO: Bayesian Optimization with Natural Language Feedback
Katarzyna Kobalczyk, Zhiyuan Jerry Lin, Benjamin Letham +3
Many real-world optimization problems are guided by complex, subjective preferences that are difficult to express as explicit closed-form objectives. In response, we introduce Lang…
RecoWorld: Building Simulated Environments for Agentic Recommender Systems
Fei Liu, Xinyu Lin, Hanchao Yu +12
We present RecoWorld, a blueprint for building simulated environments tailored to agentic recommender systems. Such environments give agents a proper training space where they can…
StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding
Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla +4
Multimodal large language models (MLLMs) have made significant progress in visual-language reasoning, but their ability to efficiently handle long videos remains limited. Despite r…
CircuitProbe: Tracing Visual Temporal Evidence Flow in Video Language Models
Yiming Zhang, Zhuokai Zhao, Chengzhang Yu +8
Autoregressive large vision--language models (LVLMs) interface video and language by projecting video features into the LLM's embedding space as continuous visual token embeddings.…
S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
Hanqing Zeng, Yinglong Xia, Zhuokai Zhao +7
Fine-tuning pre-trained large language models (LLMs) presents a dual challenge of balancing parameter efficiency and model capacity. Existing methods like low-rank adaptations (LoR…