Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The study establishes that explicit delegation contracts improve the reviewability of AI coding agent work — not its correctness — reframing the contract as a mechanism for human oversight rather than a driver of agent task performance.
The framework demonstrates that automated prompt optimization alone — without any fine-tuning — can turn a completely failing LLM agent (0% on PutNext) into one that succeeds nearly three-quarters of the time, showing prompt engineering can be systematically automated rather than done by hand.
AWF provides infrastructure-layer isolation and lifecycle management for parallel AI coding agents, replacing ad-hoc coordination with a governed worktree-per-task model that handles the full contribution pipeline from checkout to merge.
The paper demonstrates that source attribution is an independent axis of factuality verification — meaning standard source-blind metrics can pass answers that contain incorrect attributions, a gap ProvenanceGuard is designed to close in MCP-based agents.
The benchmark exposes concrete, measurable gaps in LLM agents' ability to infer hidden world models through interaction, providing a rigorous testbed with classical algorithm baselines that quantifies how far current agents fall short of robust interactive discovery.
The `/import` command creates a direct migration path from Claude Code into Codex, while the new Bedrock authentication and encrypted credential storage extend Codex's reach to AWS-managed deployments.
CoreMCP provides a ready-made bridge for connecting legacy on-premises SQL databases — including SQL Server 2000+ — to MCP-compatible AI agents without requiring custom integration work.
The project surfaces a concrete technique for onboarding coding agents to new or unfamiliar APIs — using a dynamically generated OpenAPI spec to drive prompt generation — addressing a gap in established practice for agent-driven API integration.
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.