Related papers: One STEP at a time: Language Agents are Stepwise P…

Planning represents a fundamental capability of intelligent agents, requiring comprehensive environmental understanding, rigorous logical reasoning, and effective sequential decision-making. While Large Language Models (LLMs) have…

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document…

Software development is a complex, multi-phase process traditionally requiring collaboration among individuals with diverse expertise. We propose AgentMesh, a Python-based framework that uses multiple cooperating LLM-powered agents to…

The recent surge in research interest in applying large language models (LLMs) to decision-making tasks has flourished by leveraging the extensive world knowledge embedded in LLMs. While there is a growing demand to tailor LLMs for custom…

Despite remarkable advancements in emulating human-like behavior through Large Language Models (LLMs), current textual simulations do not adequately address the notion of time. To this end, we introduce TimeArena, a novel textual simulated…

The language generation and reasoning capabilities of large language models (LLMs) have enabled conversational systems with impressive performance in a variety of tasks, from code generation, to composing essays, to passing STEM and legal…

We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representations of classic Atari games into rich textual descriptions,…

Large language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans…

Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

Agentic frameworks powered by Large Language Models (LLMs) can be useful tools in scientific workflows by enabling human-AI co-creation. A key challenge is recommending the next steps during workflow creation without relying solely on LLMs,…

In this work, we introduce Speech-Copilot, a modular framework for instruction-oriented speech-processing tasks that minimizes human effort in toolset construction. Unlike end-to-end methods using large audio-language models, Speech-Copilot…

Comprehensive planning agents have been a long term goal in the field of artificial intelligence. Recent innovations in Natural Language Processing have yielded success through the advent of Large Language Models (LLMs). We seek to improve…

While large language models (LMs) have shown remarkable capabilities across numerous tasks, they often struggle with simple reasoning and planning in physical environments, such as understanding object permanence or planning household…

Intelligent agents working in real-world environments must be able to learn about the environment and its capabilities which enable them to take actions to change to the state of the world to complete a complex multi-step task in a…

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;…

Explaining how to get from A to B can be challenging. It requires mentally simulating what the listener will do based on what they are told. To capture this process, we propose a computational model that converts utterances into action…

Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite…

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,…

Humans engage in lifelong social interactions through interacting with different people under different scenarios for different social goals. This requires social intelligence to gather information through a long time span and use it to…