arXiv:2608.17684v1 Announce Type: new Abstract: Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution…
Category: AI
GraphWake: Group Polarization via Memory-Mediated Polarization Cascade in LLM-Agent Communities
arXiv:2608.17665v1 Announce Type: new Abstract: LLM-driven agents can autonomously exchange opinions on online platforms and form communities. Such…
Beyond the Trace: Coupling an Interpretable Reasoning-State Readout to Native MoE Routing
arXiv:2608.17638v1 Announce Type: new Abstract: What a reasoning model writes is only a partial record of the process that produces it. We introduce a…
Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
arXiv:2608.17634v1 Announce Type: new Abstract: The $\operatorname{do}$-operator is described graphically by deleting arrows into its targets and…
LLM-Derived Preference Judgments Are Not Self-Consistent
arXiv:2608.17644v1 Announce Type: new Abstract: Agents increasingly interpret a person’s natural-language preferences by querying an LLM for numerical…
MiniMax Releases MiniMax-Music3: An Open-Weights Music Model Generating Complete Five-Minute Songs From Lyrics and a Structured Caption
MiniMax released MiniMax-Music3, an open-weights text-to-music model. Given lyrics with section tags and a structured caption, it generates a complete…
Validated Adaptation for Aerial Crowd Monitoring at Mass Gathering Scale: A Deployment Protocol, a Severity Law, and a Diagnostic for Label-Free Drone Crowd Counting, Toward the FIFA World Cup 2034 (Saudi Arabia)
arXiv:2608.17625v1 Announce Type: new Abstract: Saudi Arabia will host the 2034 FIFA World Cup and already operates crowd management at Hajj scale.…
Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making
arXiv:2608.17574v1 Announce Type: new Abstract: How cautious should an agent be while it is still learning its environment? We propose RATTL…
When to Review: Spaced Repetition for Continual Pre-Training of Language Models
arXiv:2608.17530v1 Announce Type: new Abstract: Continual pre-training of large language models must acquire new information without erasing old…
MoNe: Modular Neural Memory for Efficient Long Context Inference
arXiv:2608.17616v1 Announce Type: new Abstract: We present MoNe, a lightweight modular neural memory that attaches to any frozen pretrained Transformer to…