Related papers: PREPING: Building Agent Memory without Tasks

We study a repeated Principal Agent problem between a long lived Principal and Agent pair in a prior free setting. In our setting, the sequence of realized states of nature may be adversarially chosen, the Agent is non-myopic, and the…

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack…

Large language model agents are becoming increasingly capable at web-centric tasks such as information retrieval, complex reasoning. These emerging capabilities have given rise to surge research interests in developing LLM agent for…

Pretraining language models directly on web-scale corpora is the de facto paradigm. We study an alternative where the model is initially exposed to abstract structured data to ease the subsequent acquisition of rich semantic knowledge, much…

Recent advances in multimodal agents have improved computer-use interaction and tool-usage, yet most existing systems remain reactive, optimizing actions in isolation without reasoning about future states or long-term goals. This limits…

We seek to align agent behavior with a user's objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user…

Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely primarily on learning-based methods, whose policy…

Modern AI agents increasingly combine conversational interaction with autonomous task execution, such as coding and web research, raising a natural question: What happens when an agent engaged in long-horizon tasks is exposed to user…

Large language model (LLM) agents are constrained by limited context windows, necessitating external memory systems for long-term information understanding. Current memory-augmented agents typically depend on pre-defined instructions and…

The development of autonomous tool-use agents for complex, long-horizon tasks in collaboration with human users has become the frontier of agentic research. During multi-turn Human-AI interactions, the dynamic and uncertain nature of user…

Large Language Model agents are reshaping the industrial landscape. However, most practical agents remain human-designed because tasks differ widely, making them labor-intensive to build. This situation poses a central question: can we…

We introduce a new software toolbox for agent-based simulation. Facilitating rapid prototyping by offering a user-friendly Python API, its core rests on an efficient C++ implementation to support simulation of large-scale multi-agent…

Synthetic data is becoming increasingly important for accelerating the development of language models, both large and small. Despite several successful use cases, researchers also raised concerns around model collapse and drawbacks of…

Affordance prediction, which identifies interaction regions on objects based on language instructions, is critical for embodied AI. Prevailing end-to-end models couple high-level reasoning and low-level grounding into a single monolithic…

Existing memory systems for embodied agents typically inject retrieved memory as static context at episode start, a paradigm we term Ahead-of-time Monolithic Memory Injection (AMMI). However, this static design quickly becomes misaligned…

How an agent can act optimally in stochastic, partially observable domains is a challenge problem, the standard approach to address this issue is to learn the domain model firstly and then based on the learned model to find the (near)…

While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying on manually crafted agent roles and interaction prompts, which leads to…

Learning how to do things from trial and error in real time is a hallmark of biological intelligence, yet most LLM-based agents lack mechanisms to acquire procedural knowledge after deployment. We propose Procedural Recall for Agents with…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…