Related papers: Recon-Act: A Self-Evolving Multi-Agent Browser-Use…

Language agents have demonstrated autonomous decision-making abilities by reasoning with foundation models. Recently, efforts have been made to train language agents for performance improvement, with multi-step reasoning and action…

LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate…

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…

Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maintenance, and…

Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by…

Multiagent reinforcement learning, as a prominent intelligent paradigm, enables collaborative decision-making within complex systems. However, existing approaches often rely on explicit action exchange between agents to evaluate action…

Embodied social agents have recently advanced in generating synchronized speech and gestures. However, most interactive systems remain fundamentally reactive, responding only to current sensory inputs within a short temporal window.…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after explicit user prompts. This paradigm ignores a critical opportunity: the idle time between…

As agent systems powered by large language models (LLMs) advance, improving performance in context understanding, tool usage, and long-horizon execution has become critical. However, existing agent frameworks and benchmarks provide limited…

To achieve successful assistance with long-horizon web-based tasks, AI agents must be able to sequentially follow real-world user instructions over a long period. Unlike existing web-based agent benchmarks, sequential instruction following…

Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly,…

Recently, large language models (LLMs) have demonstrated remarkable problem-solving capabilities by autonomously integrating with external tools for collaborative reasoning. However, due to the inherently complex and diverse nature of…

To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement…

Current agentic frameworks underperform on long-horizon tasks. As reasoning depth increases, sequential orchestration becomes brittle, context windows impose hard limits that degrade performance, and opaque execution traces make failures…

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These…

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…

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically…

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single…