Related papers: FlashEvolve: Accelerating Agent Self-Evolution wit…

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in…

LLM-based agents are increasingly used for cybersecurity tasks, but most existing systems rely on fixed, human-designed scaffolds that struggle to adapt across diverse targets and failure modes. We introduce \textsc{CyberEvolver}, a…

Although agentic workflows have demonstrated strong potential for solving complex tasks, existing automated generation methods remain inefficient and underperform, as they rely on predefined operator libraries and homogeneous LLM-only…

The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that…

We introduce ShinkaEvolve: a new open-source framework leveraging large language models (LLMs) to advance scientific discovery with state-of-the-art performance and unprecedented efficiency. Recent advances in scaling inference time compute…

Test-time Scaling (TTS) has been demonstrated to significantly enhance the reasoning capabilities of Large Language Models (LLMs) during the inference phase without altering model parameters. However, existing TTS methods are largely…

The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operators within evolutionary loops. While effective, these systems…

Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…

Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems…

Many applications seek to optimize LLM outputs at test time by iteratively proposing, scoring, and refining candidates over a discrete output space. Existing methods use a calibrated scalar evaluator for the target objective to guide…

We present CodeEvolve, an evolutionary framework for improving program performance and code quality with Large Language Models (LLMs). CodeEvolve extends OpenEvolve with runtime-guided target selection, Monte Carlo Tree Search (MCTS),…

Traditional self-adaptive systems automatically reconfigure existing components in response to changing requirements, but provide limited support for the generation of novel functionalities. The software generation capabilities of large…

We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…

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…

In dynamic manufacturing environments, disruptions such as machine breakdowns and new order arrivals continuously shift the optimal dispatching strategy, making adaptive rule selection essential. Existing LLM-powered Automatic Heuristic…

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a…

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are…

In recent years, a variety of powerful LLM-based agentic systems have been applied to automate complex tasks through task orchestration. However, existing orchestration methods still face key challenges, including strategy collapse under…

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often…

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…