about
Stories from October 13, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. AI models can provably hide arbitrary capabilities (arxiv.org)
282 points by sbulaev 36 days ago | hide | past | pdf | 145 comments
2. Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents (arxiv.org)
5 points by matt_d 36 days ago | hide | past | pdf | discuss
3. LLM Agents Can Easily Tamper with Their Own Traces (arxiv.org)
4 points by Kaedon 35 days ago | hide | past | pdf | discuss
4. A Universal Wi-Fi CSI Encoder for Ubiquitous Human Sensing (arxiv.org)
4 points by d3ron 36 days ago | hide | past | pdf | discuss
5. Qwen3.8-Omni: Towards Native Omni-Modal Agents (arxiv.org)
3 points by teleforce 35 days ago | hide | past | pdf | discuss
6. Stateless Language Agents: Scaling Long-Horizon Automated Research (arxiv.org)
3 points by matt_d 36 days ago | hide | past | pdf | discuss
7. Tools make LLMs less likely to refuse requests (arxiv.org)
2 points by jameslk 35 days ago | hide | past | pdf | discuss
8. Agentic RAG: Taxonomy, Architectures, Evaluation and Research Directions (arxiv.org)
2 points by teleforce 35 days ago | hide | past | pdf | discuss
9. Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name (arxiv.org)
1 point by mrugge 35 days ago | hide | past | pdf | discuss
10. Agentic Large Language Models (arxiv.org)
1 point by Anon84 35 days ago | hide | past | pdf | discuss
11. Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG (arxiv.org)
1 point by teleforce 35 days ago | hide | past | pdf | discuss
12. Same Query, Different Answer: Run-to-Run Variance in Semantic Query Processing (arxiv.org)
1 point by sbulaev 35 days ago | hide | past | pdf | discuss