arXiv:2608.08253v1 Announce Type: new Abstract: AI agents are becoming shared infrastructure, yet durable memory is commonly assembled from separate…
Tag: AI
Metanormative Theory for RL-Based Moral Agents
arXiv:2608.08220v1 Announce Type: new Abstract: The overlapping disciplines of machine ethics and value alignment are concerned with designing artificial…
Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue
arXiv:2608.08210v1 Announce Type: new Abstract: Collaborative dialogue can end with apparent agreement while participants still differ on goals,…
LatticeMind: A Conflict-Aware Memory Primitive for Multi-Agent Systems
arXiv:2608.08236v1 Announce Type: new Abstract: Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent…
Anthropic says it will watermark text generated by its AI models
Anthropic will extend support for watermarking AI generations for older models as well.
A Fair Objective for Human-Empowerment-Preserving AI: Desiderata, Design, and Likely Behavioral Consequences
arXiv:2608.08240v1 Announce Type: new Abstract: This paper explores the idea of promoting well-being and safety in human-AI interactions by forcing AI…
AI’s Memory Problem: Why Efficient Long Context Changes Everything, and What It Takes to Get It Right
A colleague who forgot every prior conversation the moment it ended would not last long in most jobs. Yet a lot of business AI works exactly that way. The…
Harmful Content Is Not Enough: Continuation Framing Moderates In-Context Emergent Misalignment
arXiv:2608.08212v1 Announce Type: new Abstract: In-context learning (ICL) can induce emergent misalignment (EM), where narrow misaligned examples alter…
A Minimal $\kappa$–$\tau$ Logic for Risk-Sensitive Abduction
arXiv:2608.08192v1 Announce Type: new Abstract: Standard approaches to abductive reasoning can retain multiple candidate explanations, but they do not…
Janus: An Algorithm-Evaluator Co-Evolution Framework for LLM-Driven Discovery under Expensive Evaluation Budgets
arXiv:2608.08189v1 Announce Type: new Abstract: LLM-driven program discovery relies on rapid evaluator feedback, but many scientific and engineering tasks…