Claw-SWE-Bench: New Benchmark for Evaluating AI Coding Agents Across Multiple Languages
Researchers have introduced Claw-SWE-Bench, a multilingual benchmark and adapter protocol designed to fairly compare heterogeneous AI agent harnesses on software engineering coding tasks. The benchmark addresses a gap in existing SWE-bench evaluations, where general-purpose agents like OpenClaw cannot be directly scored due to incompatible workspace and output requirements. The work highlights that adapter design and harness choice are as consequential as model selection for coding agent performance.
A team of researchers has released Claw-SWE-Bench, a benchmark containing 350 GitHub issue-resolution instances spanning 8 programming languages and 43 repositories, derived from SWE-bench-Multilingual and SWE-bench-Verified-Mini after filtering for future-commit contamination. The benchmark introduces a standardized adapter protocol — called a 'claw' — that enforces a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator, enabling fair comparison across different agent harnesses. Experiments demonstrate the critical importance of adapter design: OpenClaw using a minimal direct-diff adapter achieves only 19.1% Pass@1, while a full adapter with the same GLM 5.1 backbone reaches 73.4%. Sweeps across nine models and five harnesses show that model choice shifts Pass@1 by up to 29.4 percentage points, while harness choice accounts for up to 27.4 percentage points under fixed models. The researchers also release Claw-SWE-Bench Lite, an 80-instance subset selected via a cost-aware, rank-aware procedure, intended for faster and cheaper validation runs. The benchmark explicitly treats harness design and API cost accounting as first-class evaluation dimensions alongside raw accuracy.
What's missing
It is unclear how the cost-aware selection procedure for Claw-SWE-Bench Lite affects the representativeness of the subset relative to the full benchmark distribution.
What different sources said
- arXiv cs.LGCenter
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.