Related papers: SERA: Soft-Verified Efficient Repository Agents

Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable…

Functional verification remains a dominant cost in modern IC development, and SystemVerilog Assertions (SVAs) are critical for simulation-based monitoring and formal property checking. However, writing SVAs by hand is time-consuming and…

Federated learning (FL) enables collaborative model training by aggregating local updates without requiring raw data sharing. However, prior studies have shown that servers can exploit gradient inversion to compromise user privacy or…

Sora is a text-to-video generative AI model, released by OpenAI in February 2024. The model is trained to generate videos of realistic or imaginative scenes from text instructions and show potential in simulating the physical world. Based…

Programmable Logic Controllers are operated by proprietary code dialects; this makes it challenging to train coding assistants. Current LLMs are trained on large code datasets and are capable of writing IEC 61131-3 compatible code out of…

The rapid advancement of autonomous driving technology is accompanied by substantial challenges, particularly the reliance on remote task execution without ensuring a reliable and accurate returned results. This reliance on external compute…

Ensuring correctness is crucial for code generation. Formal verification offers a definitive assurance of correctness, but demands substantial human effort in proof construction and hence raises a pressing need for automation. The primary…

Training software engineering (SWE) LLMs is bottlenecked by expensive infrastructure, inefficient evaluation pipelines, scarce training data, and costly quality control. We present RepoForge, an autonomous, end-to-end pipeline that…

Code embeddings are essential for semantic code search; however, current approaches often struggle to capture the precise syntactic and contextual nuances inherent in code. Open-source models such as CodeBERT and UniXcoder exhibit…

Vector processing is highly effective in boosting processor performance and efficiency for data-parallel workloads. In this paper, we present Ara2, the first fully open-source vector processor to support the RISC-V V 1.0 frozen ISA. We…

Reinforcement learning (RL) has become a key paradigm for training software engineering (SWE) agents, but existing pipelines typically rely on per-task containers for isolation. At scale, pre-built container images incur substantial storage…

Prior works on training software engineering agents have explored utilizing existing resources such as issues on GitHub repositories to construct software engineering tasks and corresponding test suites. These approaches face two key…

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…

The development of Multimodal Virtual Agents has made significant progress through the integration of Multimodal Large Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective…

SAFE is a clean-slate design for a highly secure computer system, with pervasive mechanisms for tracking and limiting information flows. At the lowest level, the SAFE hardware supports fine-grained programmable tags, with efficient and…

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large…

The increasing design complexity of System-on-Chips (SoCs) has led to significant verification challenges, particularly in meeting coverage targets within a timely manner. At present, coverage closure is heavily dependent on constrained…

Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are…

Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial…

Large language models (LLMs) have demonstrated strong capabilities in code generation, yet they remain prone to producing security vulnerabilities. Existing approaches commonly suffer from two key limitations: the scarcity of high-quality…