Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
Devloop addresses the self-review bias of single-model-family coding agents by routing implementation and review to different model families, automating the iterate-until-accepted loop so humans only intervene at the spec and PR sign-off stages.
As benchmark scores saturate, ProcGrep provides a concrete mechanism for distinguishing agents by how they solve problems — enabling procedural auditing, task-aware routing, and cost analysis that success-rate metrics alone cannot support.
The pattern replaces fragile prose-based guardrails with tool-scoped enforcement and parallel clean contexts, directly addressing the context dilution and incorrect cross-repo edits that occur when a single agent session spans multiple repositories.
mcp-gen removes the need to manually write MCP schemas by deriving them directly from TypeScript type definitions.
The tutorial provides a concrete, reproducible starting point for the agentic post-training workflow — SFT from agent traces — before the more complex GRPO and environment RL stages that follow in the series.
The skill packages a repeatable, severity-scored security audit directly into the Claude Code workflow, addressing the gap where AI-generated apps ship without any security review.
The survey provides the first structured taxonomy of Multimodal Code Intelligence, connecting mature code-generation benchmarks to emerging agentic settings and identifying verification gaps that current text-to-code evaluations do not address.
Systematic reward hackability at this scale means frontier models trained or evaluated on SWE-bench Verified and R2E-Gym may be earning inflated Pass@1 scores on a measurable fraction of tasks, undermining the reliability of these benchmarks as signals of true coding ability.
Open-SWE-Traces provides a large-scale, permissively licensed, multilingual trajectory dataset that enables fine-tuning of open-source LLMs for autonomous software engineering — directly addressing the data scarcity the paper identifies as the primary bottleneck on this path.
The pipeline replaces prohibitively expensive manual architectural labeling with a scalable agentic approach, enabling fine-tuned models to achieve dramatically higher SWE-bench Verified resolved rates than either the base model or unfiltered fine-tuning.