Related papers: WISE-Flow: Workflow-Induced Structured Experience …
The rapid proliferation of scientific knowledge presents a grand challenge: transforming this vast repository of information into an active engine for discovery, especially in high-stakes domains like healthcare. Current AI agents, however,…
Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks. Existing LLM agents suffer from a critical…
Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…
The advancement of Large Language Models (LLMs) has led to significant improvements in various service domains, including search, recommendation, and chatbot applications. However, applying state-of-the-art (SOTA) research to industrial…
Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. We identify this structural gap as \emph{Agent-Environment…
The transition from static Large Language Models (LLMs) to self-improving agents is hindered by the lack of structured reasoning in traditional evolutionary approaches. Existing methods often struggle with premature convergence and…
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…
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent…
We propose a novel model- and feature-based approach to development of vehicle software systems, where the end architecture is not explicitly defined. Instead, it emerges from an iterative process of search and optimization given certain…
Recent advances in large language models (LLMs) have sparked growing interest in agentic workflows, which are structured sequences of LLM invocations intended to solve complex tasks. However, existing approaches often rely on static…
Recently, large language models (LLMs) have demonstrated remarkable potential as an intelligent agent. However, existing researches mainly focus on enhancing the agent's reasoning or decision-making abilities through well-designed prompt…
Autonomous agents driven by Large Language Models (LLMs) offer enormous potential for automation. Early proof of this technology can be found in various demonstrations of agents solving complex tasks, interacting with external systems to…
This paper presents a Large Language Model (LLM) based conversational agent system designed to enhance human-machine collaboration in Machine Learning Operations (MLOps). We introduce the Swarm Agent, an extensible architecture that…
Recent advances in large language models (LLMs) have enabled new applications in e-commerce customer service. However, their capabilities remain constrained in complex, multimodal scenarios. We present MindFlow, the first open-source…
Large language models (LLMs) have advanced virtual educators and learners, bridging NLP with AI4Education. Existing work often lacks scalability and fails to leverage diverse, large-scale course content, with limited frameworks for…
The paper investigates using a Large Language Model (LLM) to automatically perform web software tasks using click, scroll, and text input operations. Previous approaches, such as reinforcement learning (RL) or imitation learning, are…
Large Language Models (LLMs) have achieved considerable performance across various agentic planning tasks. However, traditional agent planning approaches adopt a "flood irrigation" methodology that indiscriminately injects gold…
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…
Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…
Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…