Meta announced the Muse Spark Open AI model today, claiming that it’s the “most capable US open-weight model to date.” But the company also says that it’s…
TRACER: Trajectory-Aware Tool Retrieval for LLM Agents
arXiv:2610.21267v1 Announce Type: cross Abstract: Modern agents select tools from registries, but exposing entire registries incurs high token costs and…
Last chance to save up to $200 on your TechCrunch Founder Summit pass: Early booking ends October 16
Savings of up to $200 end October 16 for TechCrunch Founder Summit. These savings for Founder and Investor Passes vanish after Friday. Join 1,000 founders…
Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG
arXiv:2610.21318v1 Announce Type: cross Abstract: Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its…
AI News Brief Hourly Summary 2026-10-17 02h : 16 posts
16 posts published in the last hour 23:32What do AI chatbots do after users decline therapeutic redirection for suicide thoughts? 23:32Behavioral Compositionality of Sparse Autoencoder Representations 23:32Meta’s Muse Spark Open now available in Amazon SageMaker JumpStart 23:31Fractional Power-of-Two Quantization for…
What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?
arXiv:2610.21253v1 Announce Type: cross Abstract: Safety evaluations of artificial intelligence (AI) chatbots focus on therapeutic redirection, statements…
Behavioral Compositionality of Sparse Autoencoder Representations
arXiv:2610.21261v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) represent model activations with sparse, linearly decoded features, but the…
Meta’s Muse Spark Open now available in Amazon SageMaker JumpStart
Muse Spark Open, Meta’s coding-optimized open-weight model, is now available in Amazon SageMaker JumpStart. Deploy it to a SageMaker AI endpoint in your…
Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference
arXiv:2610.21257v1 Announce Type: cross Abstract: Large Language Models (LLMs) demand efficient inference, where the multiply-accumulate (MAC) operations…
How Itaú is building generative AI for its entire customer base
With ia.i, a conversational interface, and the IARA governance platform, Itaú is applying its AI First strategy to customers and employees — in one of…
A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems
arXiv:2610.21243v1 Announce Type: cross Abstract: Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in…
Replit CEO Masad Says Company No Longer Works With Anthropic
Replit CEO Amjad Masad said during an onstage interview at TechCrunch Disrupt 2026 that the company is no longer working with Anthropic, framing the…
System1-Arena: Which Decisions Can Be Left to System 1?
arXiv:2610.21244v1 Announce Type: cross Abstract: Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a…
Judging the Judges: Confidence and Disagreement in Rubrics as Rewards
arXiv:2610.21179v1 Announce Type: cross Abstract: Rubrics as Rewards (RaR) extends reinforcement learning to non-verifiable domains by using an LLM judge…
FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence
arXiv:2610.21194v1 Announce Type: cross Abstract: Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve…
RecSoup: Efficient Model Merging Approach for Controllable Multi-Objective Recommendation
arXiv:2610.21220v1 Announce Type: cross Abstract: Recommender systems often need to balance multiple conflicting objectives. Controllable Multi-Objective…
IBM ties intelligent operations to agent safety and business value
Intelligent operations begin with a business question: What should artificial intelligence help an enterprise accomplish? As agents take on more work,…
Representation Redistribution in Sparse Autoencoders
arXiv:2610.21240v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) decompose language model activations into sparse features, but prompt…