14 papers
Know When to Escalate: Critic-Guided Adaptive Execution for Cloud-Local Embodied Agents
Wei Zhang, Lirong Xiang, Charles Fleming
Recent advances in foundation-model agents have enabled increasingly capable embodied systems for long-horizon planning and interaction. However, embodied agents require fast, clos…
Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge Recasting
Zijie Liu, Zhen Tan, Charles Fleming +1
Adapting language models to new domains during post-training risks degrading previously acquired capabilities, a phenomenon commonly known as catastrophic forgetting. Existing miti…
VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning
Meng Lu, Ligeng Zhu, Olivia Xiao +8
Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for post-training vision-language models (VLMs), but it typically assumes a static training envir…
MASkills: Continual Skills Optimization for Multi-Agent LLM Systems
Huaiyuan Yao, Xiaoou Liu, Charles Fleming +2
LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improvement from interaction experience remains challenging. Existing self-reflection me…
Scaling Multi-agent Systems: A Smart Middleware for Improving Agent Interactions
Charles Fleming, Guillaume De Saint Marc, Ramana Kompella +2
As Large Language Model (LLM) based Multi-Agent Systems (MAS) evolve from experimental pilots to complex, persistent ecosystems, the limitations of direct agent-to-agent communicat…
Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
Yuhui Wang, Tanqiu Jiang, Jiacheng Liang +2
As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user-agent-e…
Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory
Jiaqi Liu, Zipeng Ling, Shi Qiu +9
AI agents increasingly operate over extended time horizons, yet their ability to retain, organize, and recall multimodal experiences remains a critical bottleneck. Building effecti…
LangMARL: Natural Language Multi-Agent Reinforcement Learning
Huaiyuan Yao, Longchao Da, Xiaoou Liu +3
Large language model (LLM) agents struggle to autonomously evolve coordination strategies in dynamic environments, largely because coarse global outcomes obscure the causal signals…
TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT
Rana Muhammad Shahroz Khan, Zijie Liu, Zhen Tan +2
Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) are the two dominant paradigms for enhancing Large Language Model (LLM) performance on downstream tasks. While RL gener…
HiPER: Hierarchical Reinforcement Learning with Explicit Credit Assignment for Large Language Model Agents
Jiangweizhi Peng, Yuanxin Liu, Ruida Zhou +4
Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execut…
MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning
Meng Lu, Yuxing Lu, Yuchen Zhuang +6
Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning t…
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Meng Lu, Ran Xu, Yi Fang +14
While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, rem…
A Layered Protocol Architecture for the Internet of Agents
Charles Fleming, Luca Muscariello, Vijoy Pandey +1
Large Language Models (LLMs) have demonstrated remarkable performance improvements and the ability to learn domain-specific languages (DSLs), including APIs and tool interfaces. Th…
Command-V: Pasting LLM Behaviors via Activation Profiles
Barry Wang, Avi Schwarzschild, Alexander Robey +4
Retrofitting large language models (LLMs) with new behaviors typically requires full finetuning or distillation-costly steps that must be repeated for every architecture. In this w…