General Science
AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks
arXiv:2610.20675v1 Announce Type: new Abstract: Agents pair reasoning models with harnesses that organize model calls, execute tools, load skill…
Putting Earth AI to work: Geospatial agents for our planet’s biggest challenges
Earth AI
The World Won’t Wait: Evaluating and Teaching Agents Under a Live Clock
arXiv:2610.20665v1 Announce Type: new Abstract: Large language model (LLM) agents can solve complex interactive tasks, yet reasoning and tool calls take…
AI News Brief Hourly Summary 2026-10-16 06h : 17 posts
17 posts published in the last hour 03:32How Third Moment Research runs 10,000 agents for 36+ hours 03:32When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing 03:32Floqer’s AI agents research sales prospects so teams don’t…
How Third Moment Research runs 10,000 agents for 36+ hours
With GPT-6 Astra and GPT-6.1 Sol, Codex, and Daybreak for cybersecurity, this AI lab builds agents that focus for days and improve with use.
When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing
arXiv:2610.17118v1 Announce Type: new Abstract: Future AI-native networks are being designed to apply autonomous agents built on large language models…
Floqer’s AI agents research sales prospects so teams don’t have to
The problem Floqer is trying to solve is familiar to anyone who has worked in sales or revenue operations.
EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research
arXiv:2610.17130v2 Announce Type: new Abstract: Automated alpha factor discovery is critical for modern quantitative research. While large language models…
Meta Releases Muse Spark Open: 816B Open-Weight MoE With 1M Context
Meta released Muse Spark Open, an 816B-parameter open-weight MoE model with 42B active parameters and a 1M-token context. It leads open models on…
SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
arXiv:2610.17093v1 Announce Type: new Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained…
Zenzap raises $44M for its AI chat app that aims to replace WhatsApp in the workplace
Zenzap is used by organizations including Starbucks and Taco Bell.
PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
arXiv:2610.17059v1 Announce Type: new Abstract: Clinical decisions depend on anticipating how a patient’s condition will evolve as treatment is adjusted…
Save 50% on your TechCrunch Disrupt 2026 ticket and join the last 2 days in San Francisco’s Moscone West
Get a 50% discount on the last two days of TechCrunch Disrupt 2026, October 14-15, in San Francisco. Register now and join the rest of the startup…
The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express
arXiv:2610.17158v1 Announce Type: new Abstract: When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1–5 rating, 0–100…
VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval
arXiv:2610.17057v1 Announce Type: new Abstract: Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize…
Neos: Learning to Interleave Search and Visual Reasoning
arXiv:2610.17043v1 Announce Type: new Abstract: Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still…
Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents
arXiv:2610.16998v1 Announce Type: new Abstract: Deep search enables language agents to solve complex information-seeking tasks through iterative web…