Related papers: daVinci-Env: Open SWE Environment Synthesis at Sca…
Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing high-performance software. We develop an automated pipeline…
Software engineers operating in complex and dynamic environments must continuously adapt to evolving requirements, learn iteratively from experience, and reconsider their approaches based on new insights. However, current large language…
Auto-regressive LLM-based software engineering (SWE) agents, henceforth SWE agents, have made tremendous progress (>60% on SWE-Bench Verified) on real-world coding challenges including GitHub issue resolution. SWE agents use a combination…
AI-driven software development has rapidly advanced with the emergence of software development agents that leverage large language models (LLMs) to tackle complex, repository-level software engineering tasks. These agents go beyond just…
Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments.…
Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…
Large language models (LLMs) are expected to be trained to act as agents in various real-world environments, but this process relies on rich and varied tool-interaction sandboxes. However, access to real systems is often restricted;…
In recent years, open-source efforts like Senorita-2M have propelled video editing toward natural language instruction. However, current publicly available datasets predominantly focus on local editing or style transfer, which largely…
Repository-level code editing requires models to understand complex dependencies and execute precise multi-file modifications across a large codebase. While recent gains on SWE-bench rely heavily on complex agent scaffolding, it remains…
LLM agents have demonstrated remarkable capabilities in software development, but their performance is hampered by long interaction contexts, which incur high API costs and latency. While various context compression approaches such as…
Training agentic models for terminal-based tasks critically depends on high-quality terminal trajectories that capture realistic long-horizon interactions across diverse domains. However, constructing such data at scale remains challenging…
Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting human annotations for this application is prohibitively…
Existing datasets for coding agents evaluate performance on isolated, single pull request (PR) tasks in a stateless manner, failing to capture the reality of real-world software development where code changes accumulate, technical debt…
Large-scale modelling of three-dimensional controlled-source electromagnetic (CSEM) surveys used to be feasible only for large companies and research consortia. This has changed over the last few years, and today there exists a selection of…
At present each neutron scattering facility has its own set of data treatment software, normally based on a proprietary data format. The travelling scientist is either forced to continually learn new software or to write conversion routines…
Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification design: transforming initial proposals into carefully considered…
Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale…
This work explores learning agent-agnostic synthetic environments (SEs) for Reinforcement Learning. SEs act as a proxy for target environments and allow agents to be trained more efficiently than when directly trained on the target…
Adapting pre-trained deep learning segmentation models to new clinical domains is a persistent challenge in medical image analysis, particularly when annotated data at the target site are scarce. Parameter-efficient fine-tuning strategies…
We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…