Timeline lokal

Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs.
Source: arXiv
https://arxiv.org/abs/2610.10611
#MachineLearning

Plan-and-Patch introduces a diffusion language model framework for agentic planning and repair. Diffusion achieved a higher plan repair success rate than autoregressive models.
Source: arXiv
https://arxiv.org/abs/2610.10786
#MachineLearning

BeliefScope is a controlled black-box framework for separating evidence-driven revision and directional user pressure in language models.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.11305
#MachineLearning

New research tests a sociolinguistic approach to measuring user-persona fidelity in simulations, using authorship-verification stylometry and lexicon-based analysis.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.10988
#MachineLearning

South Korea and Japan are strengthening cyber defenses following a wave of attacks. Experts say AI may be lowering the bar for cybercriminals. Authorities are investigating how AI was used.
Source: BusinessWorld
https://bworldonline.com/world/2026/10/09/785880/south-korea-japan-buffeted-by-hacks-as-ai-lowers-bar-for-cybercriminals/
#AI

We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productively.
Source: arXiv
https://arxiv.org/abs/2610.10833
#MachineLearning

Anthropic is clarifying how its AI assistant can be used.
Source: Business Today
https://www.businesstoday.in/technology/news/story/anthropic-tightens-claude-ai-rules-on-model-abuse-elections-weapons-and-surveillance-560587-2026-10-09?utm_source=rssfeed
#TechPolicy #Anthropic #Claude

OpenAI has banned accounts from Russia and Iran after discovering covert influence operations that used ChatGPT to generate misleading content.
Source: Business Today
https://www.businesstoday.in/technology/news/story/openai-bans-russian-and-iranian-accounts-over-ai-powered-fake-news-campaigns-targeting-global-audiences-560608-2026-10-09?utm_source=rssfeed
#TechPolicy #OpenAI #ChatGPT

Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish admission and presentation decisions.
Source: arXiv
https://arxiv.org/abs/2610.11188
#MachineLearning

TSMC and GF inked a $2B manufacturing agreement for GF to manufacture silicon interposers at its Malta, New York fab.
Source: Semiconductor Engineering
https://semiengineering.com/chip-industry-week-in-review-159/
#Semiconductors #TSMC

Researchers studied agent-controlled forgetting, where agents select observed tool results and replace them with short notes while keeping originals recoverable.
Source: arXiv
https://arxiv.org/abs/2610.10590
#MachineLearning

Fine-grained MoE upcycling collapses when experts are derived from a single source model, causing accuracy to drop to near-random levels.
Source: arXiv
https://arxiv.org/abs/2610.11317
#MachineLearning

EvoSim is introduced as a self-evolving AI scientist for physical modeling. It uses experimental discrepancies to drive mechanism and equation revisions. Evaluation on industrial battery modeling tasks shows it surpasses reported human expert accuracy.
Source: arXiv
https://arxiv.org/abs/2610.11344
#MachineLearning

A verified reference solution provides a correct trajectory for training a reasoning model. Experiments on Qwen3-4B and Qwen3-8B show Adaptive Reference Guidance achieves the highest aggregate pass@12.
Source: arXiv
https://arxiv.org/abs/2610.11128
#MachineLearning

Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper.
Source: arXiv
https://arxiv.org/abs/2610.11005
#MachineLearning

Heuristic search can store exponentially many states. Learning search control avoids this limitation.
Source: arXiv
https://arxiv.org/abs/2610.10954
#MachineLearning

Hackers earned $560,000 for Google Pixel 10 exploits at Pwn2Own.
Source: SecurityWeek
https://www.securityweek.com/google-pixel-10-exploits-earned-hackers-560000-at-pwn2own/
#Tech #Google

OpenAI said it fired three researchers after an investigation found they violated policies on handling sensitive information.
Source: BusinessWorld
https://bworldonline.com/technology/2026/10/09/785871/openai-says-it-has-fired-three-researchers-for-violating-sensitive-information-policy/
#AI #OpenAI

ByteDance's TRAE merged TraeWork and TraeCode into one platform. TraeWork shuts down on October 23.
Source: Pandaily
https://pandaily.com/bytedance-trae-merges-traework-traecode-agent-ide-modes-traework-shutdown-oct-23
#Tech #ByteDance

Odyssey 3 is a world model that simulates physics in real time.
Source: Product Hunt
https://www.producthunt.com/products/odyssey-3
#Tech