Related papers: Software Self-Extension with SelfEvolve: an Agenti…
Recent advances in agentic systems increasingly treat code as an executable operational substrate rather than as a disposable output artifact. Prior work such as \emph{Code as Agent Harness} frames validated agent-generated artifacts as…
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…
Agentic AI denotes an architectural transition from stateless, prompt-driven generative models toward goal-directed systems capable of autonomous perception, planning, action, and adaptation through iterative control loops. This paper…
Computer-use agents that combine GUI interaction with structured API calls via the Model Context Protocol (MCP) show promise for automating software tasks. However, existing approaches lack a principled understanding of how agents should…
Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have…
Having a model and being able to implement open-ended evolutionary systems is important for advancing our understanding of open-endedness. Complex systems science and newest generation high-level programming languages provide intriguing…
Agentic LLM frameworks promise autonomous behavior via task decomposition, tool use, and iterative planning, but most deployed systems remain brittle. They lack runtime introspection, cannot diagnose their own failure modes, and do not…
Several recent advances in AI systems solve problems by providing a "scaffolding" program that structures multiple calls to language models (LMs) to generate better outputs. A scaffolding program is written in a programming language such as…
As LLM-based multi-agent systems (MAS) become more autonomous, their free-form interactions increasingly dominate system behavior. However, scaling the number of agents often amplifies context pressure, coordination errors, and system…
Self-evolution methods enhance code generation through iterative "generate-verify-refine" cycles, yet existing approaches suffer from low exploration efficiency, failing to discover solutions with superior complexity within limited budgets.…
Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiting their reusability, reliability, and long-term improvement.…
For agentic systems to use external tools to solve complex, long-horizon tasks, we need a large set of diverse and controllable tool-use environments. We introduce SynthTools, a fully LLM-based pipeline spanning the entire lifecycle:…
We present an agentic flow consisting of multiple agents that combine specialized LLMs and hardware simulation tools to collaboratively complete the complex task of Register Transfer Level (RTL) generation without human intervention. A key…
Software engineers resolving repository-level issues do not treat existing tests as immutable correctness oracles. Instead, they iteratively refine both code and the tests used to characterize intended behavior, as new modifications expose…
Large Language Models (LLMs) have improved programming efficiency, but their performance degrades significantly as requirements scale; when faced with multi-modal documents containing hundreds of scenarios, LLMs often produce incorrect…
In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of…
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better…
Computer use agents represent an emerging area in artificial intelligence, aiming to operate computers autonomously to fulfill user tasks, attracting significant attention from both industry and academia. However, the performance of…
We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the task prompt plus optional parent archives that initialize a fresh workspace. The outer loop searches over these reusable starting…
Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing…