Related papers: PREPING: Building Agent Memory without Tasks

In Reasoning about Action and Planning, one synthesizes the agent plan by taking advantage of the assumption on how the environment works (that is, one exploits the environment's effects, its fairness, its trajectory constraints). In this…

Much of model-based reinforcement learning involves learning a model of an agent's world, and training an agent to leverage this model to perform a task more efficiently. While these models are demonstrably useful for agents, every…

Collaborative problem-solving under time pressure is common but difficult, as teams must generate ideas quickly, coordinate actions, and track progress. Generative AI offers new opportunities to assist, but we know little about how…

In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…

In many, if not every realistic sequential decision-making task, the decision-making agent is not able to model the full complexity of the world. The environment is often much larger and more complex than the agent, a setting also known as…

Existing Graphical User Interface (GUI) agents operate through step-by-step calls to vision language models--taking a screenshot, reasoning about the next action, executing it, then repeating on the new page--resulting in high costs and…

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…

Programming-by-example is the task of synthesizing a program that is consistent with a set of user-provided input-output examples. As examples are often an under-specification of one's intent, a good synthesizer must choose the intended…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental challenge for tool-augmented agents, as API execution typically requires complete…

Computational agents support humans in many areas of life and are therefore found in heterogeneous contexts. This means they operate in rapidly changing environments and can be confronted with huge state and action spaces. In order to…

Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies…

We present a novel approach for generating plausible verbal interactions between virtual human-like agents and user avatars in shared virtual environments. Sense-Plan-Ask, or SPA, extends prior work in propositional planning and natural…

Graphical User Interface (GUI) agents can automate complex tasks across digital environments, but their development is hindered by the scarcity of high-quality trajectory data for training. Existing approaches rely on expensive human…

Addressing the disparity between forecasts and actual results can enable individuals to expand their thought processes and stimulate self-reflection, thus promoting accurate planning. In this research, we present **PreAct**, an agent…

We introduce \emph{Memento-Skills}, a generalist, continually-learnable LLM agent system that functions as an \emph{agent-designing agent}: it autonomously constructs, adapts, and improves task-specific agents through experience. The system…

A key challenge for reinforcement learning is solving long-horizon planning problems. Recent work has leveraged programs to guide reinforcement learning in these settings. However, these approaches impose a high manual burden on the user…

This paper tackles the problem of how to pre-train a model and make it generally reusable backbones for downstream task learning. In pre-training, we propose a method that builds an agent-environment interaction model by learning domain…

Humans can pursue a near-infinite variety of tasks, but typically can only pursue a small number at the same time. We hypothesize that humans leverage experience on one task to preemptively learn solutions to other tasks that were…

Effective long-term memory in conversational AI requires synthesizing information across multiple sessions. However, current systems place excessive reasoning burden on response generation, making performance significantly dependent on…