Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
The paper demonstrates that targeted Human-on-the-Loop escalation — rather than full attorney review — can cut the legal risk of autonomous LLM-driven privilege review by up to 61%, offering a concrete architecture for deploying agentic AI in high-stakes legal workflows without requiring human oversight of every document.
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 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 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.
ChatGPT's health and wellness responses are now shaped by physician-informed evaluations, marking a more structured approach to medical accuracy in the model's outputs.
Kimi K2.7 Code delivers substantial benchmark improvements over its predecessor while cutting reasoning token usage by 30%, making a capable open-weights coding model more efficient and freely accessible.
DSG demonstrates that externalizing search grounding into a shared, MCP-compatible layer can reduce production search costs by over 98% while preserving accuracy, replacing a fixed, opaque model feature with a tunable, provider-agnostic interface.
As frontier models saturate existing benchmarks, the work of designing harder, more meaningful evaluations becomes the primary mechanism by which the field can track — and anticipate — the pace of AI capability growth.
The paper establishes that PLT performance saturates at exactly two loops and provides a gain–cost diagnostic framework explaining why, giving practitioners a principled basis for loop-count selection rather than relying on monotonic scaling assumptions.
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.