Related papers: PEARL: Plan Exploration and Adaptive Reinforcement…

Effective tool use is essential for large language models (LLMs) to interact with their environment. However, progress is limited by the lack of efficient reinforcement learning (RL) frameworks specifically designed for tool use, due to…

Representation learning is a key technique in modern machine learning that enables models to identify meaningful patterns in complex data. However, different methods tend to extract distinct aspects of the data, and relying on a single…

Meta-learning is a line of research that develops the ability to leverage past experiences to efficiently solve new learning problems. Meta-Reinforcement Learning (meta-RL) methods demonstrate a capability to learn behaviors that…

The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior work suggests using pretrained small models to improve…

Large language model (LLM)-based evolution is a promising approach for open-ended discovery, where progress requires sustained search and knowledge accumulation. Existing methods still rely heavily on fixed heuristics and hard-coded…

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of…

Human intelligence involves metacognitive abilities like self-regulation, recognizing limitations, and seeking assistance only when needed. While LLM Agents excel in many domains, they often lack this awareness. Overconfident agents risk…

Large language models (LLM) have achieved remarkable performance on various NLP tasks and are augmented by tools for broader applications. Yet, how to evaluate and analyze the tool-utilization capability of LLMs is still under-explored. In…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse domains. However, despite their impressive capabilities, MAS remain susceptible to…

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing…

A common challenge in reinforcement learning is how to convert the agent's interactions with an environment into fast and robust learning. For instance, earlier work makes use of domain knowledge to improve existing reinforcement learning…

Large language model (LLM)-based agents have emerged as powerful autonomous controllers for digital environments, including mobile interfaces, operating systems, and web browsers. Web navigation, for example, requires handling dynamic…

Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, existing approaches primarily focus on data…

This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations. Recently, prompting Large Language…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

The prevailing paradigm for improving large language models relies on offline training with human annotations or simulated environments, leaving the rich experience accumulated during real-world deployment entirely unexploited. We propose…

In preference-based Reinforcement Learning (RL), obtaining a large number of preference labels are both time-consuming and costly. Furthermore, the queried human preferences cannot be utilized for the new tasks. In this paper, we propose…

In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as…

Reinforcement learning (RL) in continuous action spaces encounters persistent challenges, such as inefficient exploration and convergence to suboptimal solutions. To address these limitations, we propose CAMEL, a novel framework integrating…