SWE-QA
PulseAugur coverage of SWE-QA — every cluster mentioning SWE-QA across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Semantic Search outperforms Deep Agentic Search in code QA, study finds
A new study published on arXiv investigates two primary methods for code question answering within large repositories: Semantic Search and Deep Agentic Search. Researchers found that Semantic Search outperformed Deep Ag…
-
Microsoft releases FastContext to boost LLM coding agent efficiency
Microsoft has released FastContext, an open-source repository-exploration subagent designed to enhance the performance of LLM coding agents. This tool separates the roles of repository exploration and task solving, allo…
-
New LaMR framework prunes code context for LLM agents
Researchers have developed a new framework called LaMR (Latent Multi-Rubric) to improve the efficiency of LLM-powered coding agents. Current agents often waste token budgets on irrelevant code snippets, but LaMR address…
-
SWE-QA benchmark tests LLMs on repository-level code questions
Researchers have introduced SWE-QA, a new benchmark designed to evaluate language models' ability to answer questions about entire software repositories. This benchmark addresses limitations of previous datasets by focu…