arXiv:2608.26788v1 Announce Type: new Abstract: Recent work shows that pre-trained, instruction-tuned vision-language models (VLMs) perform well at…
Accelerating Scientific Research with Gemini in the Real-World
arXiv:2608.26701v1 Announce Type: new Abstract: We present an extension and comprehensive real-world validation of Co-Scientist, a Gemini-based…
Style as a Confound: False Positives in AI Detection of Non-Native Academic Writing
arXiv:2608.26710v1 Announce Type: new Abstract: AI text detectors are increasingly employed in academic settings, but it remains unclear whether their…
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
arXiv:2608.26730v1 Announce Type: new Abstract: Large language models offer broad capabilities, but adapting them to evolving domains, tools, and…
Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds
arXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy,…
Anthropic continues compute-gobbling streak in $45B deal with Nscale
The new deal with the infrastructure provider is the latest example of Anthropic’s white-hot compute-gobbling streak.
AgentFold: Closed-Loop Agentic Search for Protein Folding Model Design
arXiv:2608.26747v1 Announce Type: new Abstract: Scientific LLM agents have shown promise in literature reasoning, tool use, and experiment planning, but…
AI News Brief Hourly Summary 2026-08-28 11h : 13 posts
13 posts published in the last hour 08:33SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation 08:33Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation 08:33Five Primitives for Governing Autonomous AI Agents at Runtime 08:33DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows…
SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation
arXiv:2608.26683v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning (MARL) faces significant challenges in maintaining robust…
Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation
arXiv:2608.26694v1 Announce Type: new Abstract: Detecting AI-generated text (AIGT) remains challenging because existing approaches rely on token-level…
Five Primitives for Governing Autonomous AI Agents at Runtime
arXiv:2608.26696v1 Announce Type: new Abstract: Enterprise deployments of autonomous AI agents inherit a control model built for human users and…
DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows
arXiv:2608.26546v1 Announce Type: new Abstract: Autonomous agents are increasingly adopted to complete complex, multi-tool workflows in real-world…
Always-on and self-starting AI agents might be OpenAI’s next big play
OpenAI is building a “Persistent Mode” for its AI agent Codex that stays active indefinitely and generates its own follow-up tasks. WIRED found the…
AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling
arXiv:2608.26623v1 Announce Type: new Abstract: LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured,…
ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving
arXiv:2608.26334v1 Announce Type: new Abstract: Automated theorem proving offers a natural foundation for recursive self-improvement in scientific…
Don’t Overthink, Don’t Underthink: Toward Adaptive Reasoning in Agentic AI
arXiv:2608.26442v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have shown that increased inference-time reasoning can…
Fine-Tuning of Transformer models with Frames
arXiv:2608.26430v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) strategies such as Low-Rank Adaptation (LoRA) are effective…
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents
arXiv:2608.26530v1 Announce Type: new Abstract: Long-horizon agent runs generate experience that can improve both the current run and future work. Most…