Related papers: Agent Workflow Memory
Function as a Service (FaaS) is poised to become the foundation of the next generation of cloud systems due to its inherent advantages in scalability, cost-efficiency, and ease of use. However, challenges such as the need for specialized…
LLM-powered agents face a persistent challenge: learning from their execution experiences to improve future performance. While agents can successfully complete many tasks, they often repeat inefficient patterns, fail to recover from similar…
Humans spend a remarkable fraction of waking life engaged in acts of "mental time travel". We dwell on our actions in the past and experience satisfaction or regret. More than merely autobiographical storytelling, we use these event…
LLM-based web agents show immense promise for information seeking, yet their effectiveness on long-horizon tasks is hindered by a fundamental trade-off in context management. Prevailing ReAct-based agents suffer from context saturation as…
Wearable AI systems aim to provide timely assistance in daily life, but existing approaches often rely on user initiation or predefined task knowledge, neglecting users' current mental states. We introduce ProMemAssist, a smart glasses…
With recent advancements in large language models, web agents have been greatly improved. However, dealing with complex and dynamic web environments requires more advanced planning and search abilities. Previous studies usually adopt a…
Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model…
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…
Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to…
Agentic AI shifts LLM serving from isolated prompt-generation requests to stateful, multi-turn executions that repeatedly invoke the model, call tools, and grow context over time. This paper characterizes ReAct-style agents from both the…
Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…
Language agents increasingly operate over streams of related tasks, yet existing memory systems struggle to convert accumulated experience into reusable knowledge. Retrieval-augmented and structured memory methods record per-session…
Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload within them. While human…
We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…
To succeed in common digital tasks such as web navigation, agents must carry out a variety of specialized tasks such as searching for products or planning a travel route. To tackle these tasks, agents can bootstrap themselves by learning…
What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from…
Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm,…
Autonomous agents driven by Large Language Models (LLMs) offer enormous potential for automation. Early proof of this technology can be found in various demonstrations of agents solving complex tasks, interacting with external systems to…
Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information. Existing memory systems typically follow a pipeline of…
Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to…