Related papers: Toward Systems Foundations for Agentic Exploration

Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM…

The introduction of large language models ignited great retooling and rethinking of the software development models. The ensuing response of software engineering research yielded a massive body of tools and approaches. In this paper, we…

The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice. Rather than encoding all procedural knowledge within model weights, agent…

Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…

AI agentic programming is an emerging paradigm where large language model (LLM)-based coding agents autonomously plan, execute, and interact with tools such as compilers, debuggers, and version control systems. Unlike conventional code…

We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

The recent surge in AI agents that autonomously communicate, collaborate with humans and use diverse tools has unlocked promising opportunities in various real-world settings. However, a vital aspect remains underexplored: how agents handle…

AI agent frameworks operate in isolation, forcing agents to rediscover solutions and repeat mistakes across different systems. Despite valuable problem-solving experiences accumulated by frameworks like smolagents, OpenHands, and OWL, this…

Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However, existing agentic frameworks take a relatively narrow view of agents, apply a centralized model, and…

Designing high-performance system heuristics is a creative, iterative process requiring experts to form hypotheses and execute multi-step conceptual shifts. While Large Language Models (LLMs) show promise in automating this loop, they…

Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…

Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured…

Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models…

As the reasoning capabilities of Large Language Models (LLMs) continue to advance, LLM-based agent systems offer advantages in flexibility and interpretability over traditional systems, garnering increasing attention. However, despite the…

Large Language Model (LLM)-based agents are widely used in real-world applications such as customer service, web navigation, and software engineering. As these systems become more autonomous and are deployed at scale, understanding why an…

Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture…

LLM-based agents are rapidly being adopted for scientific data analysis, automating tasks once limited by human time and expertise. This capability is often framed as an acceleration of discovery, but it also accelerates a familiar failure…

AI Agents have rapidly gained prominence in both research and industry as systems that extend large language models with planning, tool use, memory, and goal-directed action. Despite this progress, the development and maintenance of Agent…

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…