Related papers: Collaborative Evolving Strategy for Automatic Data…

Generative AI is increasingly important in software engineering, including safety engineering, where its use ensures that software does not cause harm to people. This also leads to high quality requirements for generative AI. Therefore, the…

The ability to autonomously explore and resolve tasks with minimal human guidance is crucial for the self-development of embodied intelligence. Although reinforcement learning methods can largely ease human effort, it's challenging to…

In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces…

As Large Language Models (LLMs) are increasingly deployed as autonomous agents, they face a critical scalability bottleneck known as the "Generalization-Specialization Dilemma." Monolithic agents equipped with extensive toolkits suffer from…

Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug these AI agent teams? In formative interviews with five AI…

Reinforcement Learning (RL) has demonstrated significant potential in enhancing the reasoning capabilities of large language models (LLMs). However, the success of RL for LLMs heavily relies on human-curated datasets and verifiable rewards,…

Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolution techniques. However, in large-scale industrial settings…

Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with adversarial multimodal inputs. To improve the safety of…

The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches…

Geospatial modeling provides critical solutions for pressing global challenges such as sustainability and climate change. Existing large language model (LLM)-based algorithm discovery frameworks, such as AlphaEvolve, excel at evolving…

Large Language Models (LLMs) exhibit remarkable capabilities across various tasks, yet guiding them to follow desired behaviours during inference remains a significant challenge. Activation steering offers a promising method to control the…

While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on human-specified workflows. This dependence on manually designed workflows suffers from human biases…

Large Language Model (LLM) agents have shown great potential in addressing real-world data science problems. LLM-driven data science agents promise to automate the entire machine learning pipeline, yet their real-world effectiveness remains…

Automating the adaptation of software engineering (SE) research artifacts across datasets is essential for scalability and reproducibility, yet it remains largely unstudied. Recent advances in large language model (LLM)-based multi-agent…

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…

Scientific progress in Earth science depends on integrating data across the planet's interconnected spheres. However, the accelerating volume and fragmentation of multi-sphere knowledge and data have surpassed human analytical capacity.…

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…

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.…

Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current…

LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automation for whom? Researchers operate under different resource configurations, hold different…