Related papers: EvoGraph: Hybrid Directed Graph Evolution toward S…

Scaling vision-language models into Visual Multiagent Systems (VMAS) is hindered by two coupled issues. First, communication topologies are fixed before inference, leaving them blind to visual content and query context; second, agent…

Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experience accumulation and the lack of cross-vulnerability…

Modern enterprises manage vast knowledge distributed across heterogeneous systems such as Jira, Git repositories, Confluence, and wikis. Conventional retrieval methods based on keyword search or static embeddings often fail to answer…

Every document format in existence was designed for a human reader moving linearly through text. Autonomous LLM agents do not read - they retrieve. This fundamental mismatch forces agents to inject entire documents into their context…

We introduce EvoLib, a test-time learning framework that enables large language models to accumulate, reuse, and evolve knowledge across problem instances without parameter updates or external supervision. Instead of adapting model…

Large language models (LLMs) have already revolutionized code generation, after being pretrained on publicly available code data. However, while various methods have been proposed to augment LLMs with retrieved knowledge and enhance the…

Neural networks for structured data like graphs have been studied extensively in recent years. To date, the bulk of research activity has focused mainly on static graphs. However, most real-world networks are dynamic since their topology…

Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-source LLMs with high inference latency, or fine-tune smaller…

Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e.g., for calculating gradients via…

We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs using large language models (LLMs) and evolutionary algorithms. Each robot design is represented by a structured grammar, and we use LLMs to…

In the past years, a number of static application security testing tools have been proposed which make use of so-called code property graphs, a graph model which keeps rich information about the source code while enabling its user to write…

Recognizing speaker intent in long audio dialogues among speakers has a wide range of applications, but is a non-trivial AI task due to complex inter-dependencies in speaker utterances and scarce annotated data. To address these challenges,…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…

Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval,…

The paradigm of programmable diagram generation is evolving rapidly, playing a crucial role in structured visualization. However, most existing studies are confined to a narrow range of task formulations and language support, constraining…

We introduce EVIL (\textbf{EV}olving \textbf{I}nterpretable algorithms with \textbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover simple, interpretable algorithms for dynamical systems inference. Rather than…

Large language models are increasingly used to produce runnable software. In practice, security is often addressed through a Detect--Repair--Verify (DRV) loop that detects issues, applies fixes, and verifies the result. This work studies…

Machine Learning (ML) for software engineering (SE) has gained prominence due to its ability to significantly enhance the performance of various SE applications. This progress is largely attributed to the development of generalizable source…

Traditionally, digital hardware designs are written in the Verilog hardware description language (HDL) and debugged manually by engineers. This can be time-consuming and error-prone for complex designs. Large Language Models (LLMs) are…

While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to…