Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The paper resolves a contested debate by showing that guidance production method — not guidance presence alone — determines whether `AGENTS.md` files help or hurt coding agents, and provides a concrete tuning procedure that raises SWE-bench Verified resolve rate by 7.5 percentage points over an unguided baseline.
Artifacts replaces static session exports with auto-refreshing, session-aware pages that teams can view collaboratively through a private organizational link.
The upgrade cuts Librarian search time by nearly 3x and cost by 43% with no quality regression, meaning codebase searches that previously took several minutes now complete in under a minute at meaningfully lower cost.
The RATs framework demonstrates that self-directed play — without any explicit task instructions — can build a reusable, transferable code skill library that improves both in-distribution and real-world robot task performance without retraining the underlying model.
The case provides documented evidence that AI coding agents can supply the technical structure and execution that an unskilled attacker lacks, lowering the skill floor for offensive cyber operations to the point where vague natural-language prompts were sufficient to breach 14 organizations.
Cursor Automations now respond to GitHub events and can operate cloud agents with computer use, expanding the scope of automated workflows the product supports.
The results show that the quality gap between open-source coding models and a leading frontier model has closed to the point where GLM 5.2 and MiniMax M3 match or exceed Claude Sonnet 4.6 on accuracy while costing the same or less per task.
The decomposition replaces impractical logprob- and training-based uncertainty methods with a prompt-only approach that works under real deployment constraints, enabling LLM agents to proactively seek clarification on ambiguous tasks rather than acting on underspecified instructions.
The comparison introduces a verifiable track record as a distinct evaluation axis for MCP servers, distinguishing tools that return auditable accuracy records through the MCP interface from those that only supply raw data or indicator output.
The tool reduces repeated repository rediscovery by AI coding agents, cutting 4k–13k tokens of redundant context per prompt.