Related papers: AgentFold: Long-Horizon Web Agents with Proactive …
Large language model (LLM)-based agents that reason, plan, and act through tools, memory, and structured interaction are emerging as a promising paradigm for automating complex workflows. Recent systems such as OpenClaw and Claude Code…
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…
The era of the Internet of Agents (IoA) is taking shape: LLM agents are expected to fulfill user goals by orchestrating fast-growing populations of Model Context Protocol (MCP) servers, Agent-to-Agent (A2A) endpoints, reusable skills, and…
Long-context Large Language Models, despite their expanded capacity, require careful working memory management to mitigate attention dilution during long-horizon tasks. Yet existing approaches rely on external mechanisms that lack awareness…
Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders their ability to maintain long-term user's intents and…
The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles…
Language model (LM) agents have gained significant attention for their ability to autonomously complete tasks through interactions with environments, tools, and APIs. LM agents are primarily built with prompt engineering or supervised…
Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…
With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack…
Large Language Models (LLMs) suffer from significant performance degradation when processing long contexts due to proactive interference, where irrelevant information in earlier parts of the context disrupts reasoning and memory recall.…
Recent advancements in Large Language Model (LLM)-based frameworks have extended their capabilities to complex real-world applications, such as interactive web navigation. These systems, driven by user commands, navigate web browsers to…
Long-horizon code generation requires sustained context and adaptive expertise across domains. Current multi-agent systems use static workflows that cannot adapt when runtime analysis reveals unanticipated complexity. We propose AgentSpawn,…
LLM-based agent applications have shown increasingly remarkable capabilities in complex workflows but incur substantial costs and latency due to extensive planning and reasoning requirements. Existing LLM caching techniques (like context…
Large Language Models (LLMs) have become a popular interface for human-AI interaction, supporting information seeking and task assistance through natural, multi-turn dialogue. To respond to users within multi-turn dialogues, the…
AI applications increasingly depend on long-context inference, where LLMs consume substantial context to support stronger reasoning. Common examples include retrieval-augmented generation, agent memory layers, and multi-agent orchestration.…
Autonomous agent frameworks still struggle to reconcile long-term experiential learning with real-time, context-sensitive decision-making. In practice, this gap appears as static cognition, rigid workflow dependence, and inefficient context…
Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required. In this work, we propose an agent-based approach to enhance both the efficiency and…
Multimodal agentic pipelines are transforming human-computer interaction by enabling efficient and accessible automation of complex, real-world tasks. However, recent efforts have focused on short-horizon or general-purpose applications…
Large Language Model (LLM) agents have shown significant autonomous capabilities in dynamically searching and incorporating relevant tools or Model Context Protocol (MCP) servers for individual queries. However, fixed context windows limit…
Large language models (LLMs) excel at solving complex tasks by executing agentic workflows composed of detailed instructions and structured operations. Yet, building general-purpose agents by manually embedding foundation models into…