Daily AI News — 2026-08-29
Generated at 2026-08-29T09:43:22.531817-07:00 by a GitHub Actions GitOps pipeline.
Top stories
- Leveraging Large Language Models for Systematic Literature Review of Disease Spread Models — arXiv cs.AI, 2026-08-29 04:00 UTC. Score 8.4 — arXiv:2608.26150v1 Announce Type: new Abstract: Recent advancements in Large Language Models (LLMs) have created new opportunities to streamline and potentially automate many research processes, including systematic literature reviews (SLRs). This study reports an LLM pipeline development for extracting model-relevant information from 536 peer-reviewed agent-based modeling papers. We compare the results with those of a human-conducted SLR. Our results show paper-level accuracies of approximately 77.95% for GPT-4.1 and 81.67% for GPT-5.0. Field-level accuracy ranges from 32.40% to 100.00%, with more complex or subjective fields performing les…
- Same Model, Different Harness: Different Coding-Agent Results — arXiv cs.AI, 2026-08-29 04:00 UTC. Score 7.6 — arXiv:2608.26218v1 Announce Type: new Abstract: A coding agent combines a model with a harness, which decides what the model sees, which tools it can use, and how the work continues. We ask whether changing the harness changes the result when the model and task stay fixed. We compare two configurations of the same harness on three coding benchmarks. The control supplies the full conversation in time order, while the treatment keeps the same record but mechanically shortens older tool results as the context fills and responds to repeated or stalled work. Under tight context, the treatment raises mean per-task fail-to-pass fraction (F2PF) in a…
- AI Control Scientist: LLM-driven Agentic System for Automated Control Design — arXiv cs.AI, 2026-08-29 04:00 UTC. Score 7.6 — arXiv:2608.26780v1 Announce Type: new Abstract: Control system design is critical for modern industry, such as chemical process temperature regulation and aero-engine control. However,traditional control design workflows rely heavily on expert knowledge and extensive manual parameter tuning, resulting in limited efficiency and scalability. To this end, this paper proposes AI Control Scientist (AICS), the first large language model (LLM)-driven agent capable of automatically generating optimized controller from language design requirements. Specifically, a Task Modeling Agent interprets user requirements to engineering constraints; a Controll…
- Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds — arXiv cs.AI, 2026-08-29 04:00 UTC. Score 7.5 — arXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes requested knowledge while preserving model utility, offering a practical alternative to full retraining, but existing methods treat the explicitly identified forget examples as the complete deletion scope. This is insufficient when target knowledge remains recoverable through paraphrases, aliases, or neighboring training examples. We propose GRAPHSU, a graph-guided controller that expands the deletion scope beyond forget se…
- Our decision on Cursor following its acquisition by SpaceX — OpenAI Blog, 2026-08-28 06:00 UTC. Score 6.1 — Our decision to wind down our contract providing OpenAI models to Cursor following its acquisition by SpaceX.
- Nvidia’s AI advantage is moving beyond the GPU — TechCrunch AI, 2026-08-29 13:00 UTC. Score 5.2 — The new generation of data center systems is increasing efficiency with smarter traffic control instead of just more processor cycles.
- Open-weight AI companies are the Valley’s hottest acquisition targets — TechCrunch AI, 2026-08-28 18:19 UTC. Score 4.4 — There's a lot of capital pouring into the business of giving models away.
- How Decathlon runs demand forecasting at scale with Chronos-2 — AWS Machine Learning Blog, 2026-08-28 16:22 UTC. Score 4.4 — Decathlon, one of the world's largest sporting goods retailers, forecasts weekly demand for tens of thousands of products across multiple continents. Learn how they deployed Chronos-2 on AWS to improve forecast accuracy by 11-15 points while cutting operational complexity and running weekly inference for about $0.03 on CPU-only instances.
- Anthropic gets its first court win over the Pentagon’s supply-chain risk label — TechCrunch AI, 2026-08-28 12:46 UTC. Score 4.4 — A federal judge ruled the Trump administration illegally labeled Anthropic a supply-chain risk, handing the AI company a victory as its second Pentagon lawsuit continues in Washington.
- Meta executive leaves for OpenAI as the social media giant faces growing scrutiny in India — TechCrunch AI, 2026-08-28 12:21 UTC. Score 4.4 — Sandhya Devanathan will oversee some OpenAI operations across Southeast Asia and Australia in her new role.
Signals to watch
- Most represented sources: arXiv cs.AI (4), TechCrunch AI (4), AWS Machine Learning Blog (2), The Verge AI (2).
- Recurring themes: model (6), agent (3), openai (2), gpt (1), research (1), benchmark (1), regulation (1), training (1).
- Review the raw JSON output in
data/items/ if you want to audit scoring or feed coverage.
All links
- Selected items: 13
- AI summarization: deterministic fallback
- Source data:
data/items/ in this repository