arXiv:2611.02839v1 Announce Type: new Abstract: Recursive self-improvement (RSI) in production agents involves transforming accumulated experience into…
SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
arXiv:2611.02846v1 Announce Type: new Abstract: Speculative decoding (SD) accelerates large language model inference by reducing the sequential cost of…
Value-Conditioned Proposal Acquisition for Test-Time Reasoning
arXiv:2611.02852v1 Announce Type: new Abstract: Sampling and selection spend test-time compute inside a candidate pool, but they cannot recover a correct…
TLAPS-Bench: Formally Proving Correctness of Real-World System Specifications with TLA+ Proof System
arXiv:2611.02849v1 Announce Type: new Abstract: TLAPS-Bench is a benchmark and execution harness for constructing machine-checked proofs for real-world…
Goldman Sachs pulls AI coding tools from traders and bankers
Goldman Sachs is pulling AI coding tools like Claude Code and GitHub Copilot from traders and bankers, limiting access to engineers only. As recently as…
Think with Skills: Pseudocode Planning Before Execution for Advanced Reasoners
arXiv:2611.02830v1 Announce Type: new Abstract: Language model agents often struggle with complex tasks even when equipped with expert-written skills.…
AI News Brief Hourly Summary 2026-11-04 04h : 14 posts
14 posts published in the last hour 02:33Creating Hybrid Interactive Narrative Systems with LLM: From Formal Description to Evaluation 02:33Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment 02:33Predictive Safety Guardrails Do Not Always Make LLM Agents…
Creating Hybrid Interactive Narrative Systems with LLM: From Formal Description to Evaluation
arXiv:2611.02807v1 Announce Type: new Abstract: Interactive narratives let users shape a story while an Experience Manager (EM) keeps it coherent,…
Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment
arXiv:2611.02809v1 Announce Type: new Abstract: This paper introduces a reinforcement learning-based approximate dynamic programming approach to optimize…
Predictive Safety Guardrails Do Not Always Make LLM Agents Safer
arXiv:2611.02815v1 Announce Type: new Abstract: Large language model agents increasingly take consequential actions in digital and physical environments,…
RxnMiner: A Multimodal Agent for Structured Reaction Data Extraction from Chemistry Figures
arXiv:2611.02826v1 Announce Type: new Abstract: Reaction data underpin machine learning for reaction prediction, condition recommendation, and…
Raising the quality of insights in agentic analytics
In just a few years, generative AI has changed the face of enterprise analytics, notably by making analytics accessible to users across the organization.…
Analysing the Narrative Paradox through Formal Models and Properties in Interactive Narrative
arXiv:2611.02801v1 Announce Type: new Abstract: Interactive narratives aim to let players influence the unfolding of a story while preserving a coherent…
Stage-aware Multimodal Brain Graph Contrastive Learning for Neurodegenerative Disorder Diagnosis
arXiv:2611.02771v1 Announce Type: new Abstract: Neurodegenerative disorders are characterized by their progressive nature, with distinct stages that…
Is your LLM an Agressive Narcissist with Depression? Analyzing Psychological Portraits of Large Language Models
arXiv:2611.02757v1 Announce Type: new Abstract: Nowadays, interaction with AI requires caution not only regarding the factual reliability of generated…
New York Times and other outlets sue web browser Brave over alleged content scraping
The New York Times is suing privacy-focused web browser company Brave for allegedly scraping the outlet’s copyrighted content and unlawfully distributing…
DrawOffer: Evidence-Grounded Longitudinal User-State Modeling for Career Support
arXiv:2611.02793v1 Announce Type: new Abstract: Career-support assistants must distinguish user claims from evidence of current ability and withhold…
Coming in 2027: Apple’s $1,000 home robot for FaceTime and switching on lights
Apple robot backed by CEO John Ternus may have hefty price tag and limited uses.