Daily AI News — 2026-08-19
Generated at 2026-08-19T06:08:27.532846-07:00 by a GitHub Actions GitOps pipeline.
Top stories
- Write, Execute, Refine: From Skill Followers to Skill Optimizers via Reinforcement Learning from Execution Feedback — arXiv cs.CL, 2026-08-19 04:00 UTC. Score 10.1 — arXiv:2608.17587v1 Announce Type: new Abstract: Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8-11 points worse than using no skill. This gap suggests that following procedural guidance and improving it from execution evidence are distinct capabilities. Inference time loops can repair skills but do not improve the model that writes the next one. We study how to organize execution experience from intermediate skills into training states for an optimizer. We introduce WER (Write, Execute, and Refine), a multi-phase framework that trains a Skill Optimizer outside a frozen executor. The o…
- Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models — arXiv cs.AI, 2026-08-19 04:00 UTC. Score 10.0 — arXiv:2608.17183v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal risks. However, existing AI safety\slash security\slash compliance benchmarks are designed for large language models that may not transfer reliably to SLMs. We therefore ask: Can these benchmarks effectively and reliably evaluate SLMs? To answer this question, we conduct a large-scale assessment of the effectiveness and robustness of these automated pipelines by evaluating five widely used benchmark suites across 26 open-sourc…
- StartupBench: Benchmarking General-Purpose Agents on Market-Validated End-to-End Workflows — arXiv cs.AI, 2026-08-19 04:00 UTC. Score 10.0 — arXiv:2608.17800v1 Announce Type: new Abstract: Recent advances in Large Language Models(LLMs) and agents have substantially improved the ability of AI systems to execute complex tasks. Yet existing benchmarks largely rely on researcher-selected tasks, leaving uncertain whether such progress extends to the work that real-world users actually demand from AI systems. We introduce \textbf{StartupBench}, an E2E agent benchmark grounded in market-validated AI startup products. Rather than defining tasks from pre-defined assumptions about useful agent capabilities, we systematically study AI products with demonstrated adoption, together with their…
- OpenAI institutes new safeguards after Hugging Face breach — TechCrunch AI, 2026-08-18 18:00 UTC. Score 8.6 — The new safeguards include more detailed monitoring of models during the development process, as well as greater emphasis on alignment and security during the post-training process.
- KernelArc: A Multi-Agent Framework for GPU Kernel Optimization — arXiv cs.AI, 2026-08-19 04:00 UTC. Score 8.4 — arXiv:2608.17071v1 Announce Type: new Abstract: We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in parallel and coordinate through conclusions-only shared memory, a deterministic benchmark guard, and read-only cross-agent state with plateau-triggered drafting. We evaluate \kernelarc{} on NVIDIA H100 and B200 GPUs using category-representative SOL-ExecBench workloads. The resulting implementations span custom BF16 GEMM, static cuBLASLt Expert-API configuration tables, fused mixture-of-experts backward, shape-gated decoder-layer fusion, native…
- PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs — arXiv cs.AI, 2026-08-19 04:00 UTC. Score 8.4 — arXiv:2608.17289v1 Announce Type: new Abstract: Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants fail to distinguish advantages among successful trajectories even when these trajectories differ substantially in their interaction efficiency. For instance, circuitous successes are often assigned the identical outcome reward, causing advantage collapse and severe performance bottlenecks. To this end, we propose Group Planning-aware Policy Optimization (PlanPO), a simple yet effective RL method for learning generaliz…
- AISA: AI Safety Assistant Framework for Continuous Improvement of Highway Construction — arXiv cs.CL, 2026-08-19 04:00 UTC. Score 8.4 — arXiv:2608.17184v1 Announce Type: new Abstract: Job Safety Analysis (JSA) and pre-task planning can benefit from prior incident records, yet historical accident data is often stored as unstructured narratives that are difficult to consult at the point of planning. A novel framework centered on large language models (LLMs) for highway construction safety reporting and planning is proposed as a foundation for future agentic applications, prioritizing deterministic, local inferencing. The first aim is to enable classification and quality scoring of incident narratives for existing and future reporting purposes. The second is to evaluate retriev…
- Temporal Leakage in Financial News NLP: A Multi-Architecture Audit with a Regime-Specific M&A Signal — arXiv cs.CL, 2026-08-19 04:00 UTC. Score 8.4 — arXiv:2608.17223v1 Announce Type: new Abstract: Financial-news direction prediction has become a popular NLP benchmark, yet reported gains depend critically on whether the train-test split is chronological or random, i.e., on temporal leakage. We audit this dependence on a 49,799-article corpus across 16 feature-model combinations spanning TF-IDF, MiniLM, FinBERT, and fine-tuned RoBERTa-large / DeBERTa-v3-large, plus separate zero/few-shot and LoRA probes of Llama-3 and Qwen2.5 LLMs: random splits inflate MCC by $1.1\times$ to $6.5\times$, tracking model capacity and feature richness, and end-to-end FinBERT fine-tuning re-amplifies rather th…
- PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX — arXiv cs.CL, 2026-08-19 04:00 UTC. Score 8.4 — arXiv:2608.17379v1 Announce Type: new Abstract: We introduce PTXBench, a benchmark for evaluating and adapting large language models (LLMs) to use architecture-specific PTX for GPU kernel optimization. PTXBench measures functional correctness, whether selected target instructions execute at runtime, and speedup over frontier libraries across GEMM and attention workloads on H100 and B200 GPUs. Our evaluation shows that architecture-specific PTX capability remains uneven: success rates fall substantially on complex attention backward workloads, and executing the target instructions does not necessarily translate into competitive performance. N…
- Inverse Problems for Partial Differential Equations with Jump Discontinuities in Coefficients via Two-Stage Physics-Informed Deep Learning and Statistical Mixture Models — arXiv stat.ML, 2026-08-19 04:00 UTC. Score 8.4 — arXiv:2510.14656v3 Announce Type: replace Abstract: This work proposes a two-stage physics-informed deep learning framework that combines neural-network-based sampling with statistical inference and constrained parameter refinement. In the first stage, a dual-network physics-informed architecture is used, where a main network approximates the PDE solution and an auxiliary coefficient sub network provides a relaxed continuous surrogate of the true discontinuous coefficient field. A gradient-adaptive weighting strategy is incorporated into the physics residual to improve residual training and enhance sampling reliability near possible disconti…
Signals to watch
- Most represented sources: arXiv cs.CL (4), arXiv cs.AI (4), arXiv stat.ML (4), TechCrunch AI (2).
- Recurring themes: model (13), agent (7), security (6), training (5), benchmark (5), openai (5), inference (3), ai safety (2).
- Review the raw JSON output in
data/items/ if you want to audit scoring or feed coverage.
All links
- Selected items: 18
- AI summarization: deterministic fallback
- Source data:
data/items/ in this repository