arXiv:2608.13667v1 Announce Type: new Abstract: LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate…
Learning to Assemble Novel Structures with Unfamiliar Parts under Semantic Constraints
arXiv:2608.13684v1 Announce Type: new Abstract: This paper describes a neurosymbolic architecture for learning to assemble novel structures using evidence…
AI News Brief Hourly Summary 2026-08-17 08h : 10 posts
10 posts published in the last hour 05:32Algorithm Design and Physician Liability 05:32Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning 05:32Reward Machines for Signal Temporal Logic 05:32ARC: Fair Relative Advantage Comparison in…
Algorithm Design and Physician Liability
arXiv:2608.13618v1 Announce Type: new Abstract: A single clinical algorithm can deliver unequal accuracy across patient groups, and concern about such…
Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning
arXiv:2608.13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations,…
Reward Machines for Signal Temporal Logic
arXiv:2608.13625v1 Announce Type: new Abstract: Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued…
ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction
arXiv:2608.13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for…
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
arXiv:2608.13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We…
Evaluating Agentic Learning Harness Capabilities Without Labels via the Scaling Hypothesis
arXiv:2608.13608v1 Announce Type: new Abstract: Agentic “Continual Learning Harnesses”, systems that pair an LLM with retrieval or memory to improve from…
SemPlan: Benchmarking Structured Semantic Planning for LLM-Based Queries over Enterprise Data
arXiv:2608.13612v1 Announce Type: new Abstract: Natural-language interfaces to enterprise data must translate underspecified requests into governed,…
MobileMem: Learning from a Year of Mobile Experiences
arXiv:2608.13606v1 Announce Type: new Abstract: The next generation of AI agents is increasingly moving beyond systems that answer isolated questions…
No Universal Signal Predicts Sample-Level LLM Regression under Version Updates
arXiv:2608.13607v1 Announce Type: new Abstract: Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate. But…
How Compliant is Sepsis Treatment? An Expert-Guided Neuro-symbolic Pipeline for Generating Clinical Compliance Insights
arXiv:2608.13617v1 Announce Type: new Abstract: Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet…
AI News Brief Hourly Summary 2026-08-17 07h : 10 posts
10 posts published in the last hour 04:32Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents 04:32AI Evaluation Should Work With Humans 04:32Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors…
Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI Agents
arXiv:2608.13604v1 Announce Type: new Abstract: Detection of misunderstanding is an urgent problem to solve because communication has moved away from…
AI Evaluation Should Work With Humans
arXiv:2608.13577v1 Announce Type: new Abstract: This position paper argues that the dominant paradigm of AI evaluation (which focuses on superhuman…
Stable Miscalibration in Large Language Models: A Practical View of High-Confidence Errors
arXiv:2608.13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal…
Active Perception for Embodied Disambiguation
arXiv:2608.13605v1 Announce Type: new Abstract: Natural language provides robots with a flexible task interface, but target ambiguity in embodied…