SWE-Agent
PulseAugur coverage of SWE-Agent — every cluster mentioning SWE-Agent across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New benchmark TestEvo-Bench evaluates AI agents on code and test co-evolution
Researchers have introduced TestEvo-Bench, a new benchmark designed to evaluate AI agents on their ability to co-evolve tests with code changes. The benchmark includes tasks for generating new tests and updating existin…
-
Paper defines 'agent harness' for AI coding assistants
A new paper published on arXiv proposes a formal definition for "agent harness," a term used in software engineering for systems that wrap language models to create coding agents. The authors trace the term's origins an…
-
DeepSeek Researcher Co-Authors Paper With AI Agent, Proposing Autonomy Levels
DeepSeek researcher Chen Deli has co-authored a research paper with an AI agent, where the AI generated 99% of the content. The paper, titled "A Taxonomy of Autonomous Research Agents L1-L5," proposes a five-level class…
-
Alibaba's Qwen3-Coder-Next achieves 70.6 on SWE-Bench with sparse MoE
Alibaba's Qwen3-Coder-Next, an 80 billion parameter model with 3 billion active parameters, has achieved a 70.6 score on the SWE-Bench Verified benchmark. This performance is notable as it rivals top closed-source model…
-
Code Researcher agent boosts Linux kernel crash resolution by 48%
A new deep research agent called Code Researcher has been developed to tackle complex systems code by analyzing large codebases and their commit histories. This agent significantly outperforms existing methods on benchm…