arXiv:2608.21364v1 Announce Type: cross Abstract: Both human and AI systems that process narrative or long-form content operate incrementally: input is…
Tag: AI
Correcting a learned physical invariant improves world-model rollouts
arXiv:2608.23526v1 Announce Type: new Abstract: World models can predict video without learning dynamics that they reliably preserve. We test whether a…
EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards
arXiv:2608.23525v1 Announce Type: new Abstract: Earth-system analysis reconstructs changing physical processes from observations that differ in source,…
ReWorld: An Interactive World Model with Long-Horizon Memory
arXiv:2608.23565v1 Announce Type: new Abstract: An interactive world model must follow the user’s actions, remember the places it has shown, and stream in…
How AI Assistance Affects Human Skill Development: A Study of Learning with Logic Puzzles
arXiv:2608.23543v1 Announce Type: new Abstract: While AI assistance can improve human task performance in the short term, it may also undermine the…
Prime Agent: A Self-Improving RLM Harness
arXiv:2608.23552v1 Announce Type: new Abstract: Language models are sequential processors, but long-horizon agency requires external information and…
Multi-Modal Semantic Expansion with Constrained LLM Reranking for Conversational Music Recommendation
arXiv:2608.23484v1 Announce Type: new Abstract: We present Team Semiintelligencn’s solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing…
SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning
arXiv:2608.23493v1 Announce Type: new Abstract: Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome…
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
arXiv:2608.23497v1 Announce Type: new Abstract: Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content,…
Perplexity Ships Portable Computer on NVIDIA DGX Spark: Local Harness, OS-Enforced Sandbox, and Zero Per-Token Cost for Local Steps
Perplexity releases Portable Computer, packaging local models, harness, sandbox, and connectors into one system running on NVIDIA DGX Spark.