Related papers: Memory as Action: Autonomous Context Curation for …

Computer-use agents operate over long horizons under noisy perception, multi-window contexts, evolving environment states. Existing approaches, from RL-based planners to trajectory retrieval, often drift from user intent and repeatedly…

Despite recent advances, autonomous agents often struggle to solve complex tasks in enterprise domains that require coordinating multiple tools and processing diverse data sources. This struggle is driven by two main limitations. First,…

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…

Large Language Models (LLMs) often experience performance degradation during long-running interactions due to increasing context length, memory saturation, and computational overhead. This paper presents an adaptive context compression…

Foundation models rely on in-context learning for personalized decision making. The limited size of this context window necessitates memory compression and retrieval systems like RAG. These systems however often treat memory as large…

Capturing human learning behavior based on deep learning methods has become a major research focus in both psychology and intelligent systems. Recent approaches rely on controlled experiments or rule-based models to explore cognitive…

Decision Transformer-based decision-making agents have shown the ability to generalize across multiple tasks. However, their performance relies on massive data and computation. We argue that this inefficiency stems from the forgetting…

In this work, we consider the problem of computing optimal actions for Reinforcement Learning (RL) agents in a co-operative setting, where the objective is to optimize a common goal. However, in many real-life applications, in addition to…

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been…

Molecular editing and optimization are multi-step problems that require iteratively improving properties while keeping molecules chemically valid and structurally similar. We frame both tasks as sequential, tool-guided decisions and…

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with…

Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks the initial memory extraction stage. In this paper, we argue…

Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed to harness the collective intelligence of LLM agents.…

With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their failure to learn from the accumulated interaction history,…

The rise of multi-agent systems powered by large language models (LLMs) and specialized reasoning agents exposes fundamental limitations in today's data management architectures. Traditional databases and data fabrics were designed for…

Document-level context for neural machine translation (NMT) is crucial to improve the translation consistency and cohesion, the translation of ambiguous inputs, as well as several other linguistic phenomena. Many works have been published…

Large Language Model (LLM) agents, capable of performing a broad range of actions, such as invoking tools and controlling robots, show great potential in tackling real-world challenges. LLM agents are typically prompted to produce actions…

Reinforcement Learning (RL) agents typically learn memoryless policies---policies that only consider the last observation when selecting actions. Learning memoryless policies is efficient and optimal in fully observable environments.…

Large language model (LLM) agents increasingly rely on accumulated memory to solve long-horizon decision-making tasks. However, most existing approaches store memory in fixed representations and reuse it at a single or implicit level of…