arXiv:2610.38551v1 Announce Type: new Abstract: Multi-source millimeter-wave (mmWave) observations offer an opportunity to learn human representations…
Co-Evolving Policy and Rubric via Capability Awareness for Open-Ended Generation
arXiv:2610.38566v1 Announce Type: new Abstract: Rubric-based reinforcement learning (RL) offers interpretable, fine-grained supervision for aligning large…
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
arXiv:2610.38568v1 Announce Type: new Abstract: Recursive self-improvement requires models not only to acquire useful training experience, but also to…
An Alignment Benchmark for Enterprise Agents on Era by Eon
arXiv:2610.38544v1 Announce Type: new Abstract: AI agents are widely used in enterprises to access business systems and act on them in pursuit of a goal.…
OpenAI raises just $11 billion of its $30 billion target as big investors lose their AI appetite
OpenAI raised only about $11 billion in its latest funding round, less than half of the $30 billion it was targeting. At $1.25 trillion, the valuation…
CALM: Conflict-Aware Lifecycle Memory Governance for Long-Horizon Language Agents
arXiv:2610.38573v1 Announce Type: new Abstract: A memory can be outdated for present-day reasoning yet indispensable for reconstructing the past.…
Accelerating Nonlinear MPC by Behavior Cloning with Separated Timescales: Application to Nuclear Reactor Load-Following
arXiv:2610.38496v1 Announce Type: new Abstract: Behavior Cloning (BC) of expert controllers for multiscale dynamical systems is challenging: state…
Value Probes: Learned Value Functions for Beam-Search Red Teaming
arXiv:2610.38526v1 Announce Type: new Abstract: Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors.…
From Leniency to Suspicion: How an Open Post-Training Recipe Changes Whom LLM Fact-Checkers Believe
arXiv:2610.38532v1 Announce Type: new Abstract: LLMs increasingly fact-check online content with the poster’s identity in view. However, it remains…
DES-JEPA: Learning a Shared Vocabulary for High-Dimensional Discrete Event Sequences
arXiv:2610.38445v1 Announce Type: new Abstract: Temporal foundation models such as Chronos and TimesFM generalize across domains through a shared…
Predict the Reward, Not the World: World Reward Models for ML Agents
arXiv:2610.38439v1 Announce Type: new Abstract: Search-based machine-learning (ML) agents improve a solution by writing candidate programs, executing…
AI News Brief Hourly Summary 2026-10-31 10h : 11 posts
11 posts published in the last hour 08:34Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web 08:34Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI 08:34Compute Has Shape: Self-Morphing the Internal Computation of…
Agent Transfer Protocol: Server-Mediated Agent-to-Agent Communication Architecture for the Agentic Web
arXiv:2610.38398v1 Announce Type: new Abstract: The Agentic Web needs to support continuous collaboration among agents from different organizations. These…
Governance-Aware Federated Learning for Multi-Agent AI Systems: A Policy-Driven Framework for Trustworthy Collaborative AI
arXiv:2610.38411v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without exchanging raw data, but conventional…
Compute Has Shape: Self-Morphing the Internal Computation of Frozen LLMs
arXiv:2610.38382v1 Announce Type: new Abstract: Test-time scaling improves large language models through additional computation, but how to adapt the…
Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents
arXiv:2610.38392v1 Announce Type: new Abstract: Self-improving LLM agents edit their own harness, the prompts and rules around a fixed model, and keep an…
SCOPE: Selective Critical-Step On-Policy Self-Distillation for Agentic Reinforcement Learning
arXiv:2610.38391v1 Announce Type: new Abstract: Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed…
Encode Once, Answer Many: Internalizing Context via Parametric Flow
arXiv:2610.38356v1 Announce Type: new Abstract: Large language models are typically adapted to a task either by placing knowledge in the input context,…