Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
Agent Canvas moving to production readiness marks a shift from experimental to officially supported tooling for running parallel AI agents and automations within the OpenHands ecosystem.
Z Code gives developers a free, high-capacity alternative to Codex — 5 million tokens per day — backed by GLM-5.2, currently the top-ranked open-weights model on the Artificial Analysis Intelligence Index, under a permissive MIT license.
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.
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 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 results show that CLI-based mobile agents, without any mobile-specific training, already surpass GUI-based agents on established benchmarks while completing tasks in nearly half the steps, establishing CLI as a viable and more efficient paradigm for mobile automation research.
NRT-Bench reveals that frontier LLM agents are vulnerable to adaptive multi-turn attacks even in safety-critical supervisory roles, and that model-specific, nearly non-overlapping failure modes mean aggregate robustness metrics can mask significant individual weaknesses.
The paper provides a measurable, formal account of how evaluation bias spreads in multi-agent LLM pipelines and identifies a concrete structural intervention — expanding evaluator committee size — that reduces that spread by 72.4%.