arXiv:2609.18736v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs), performing logically consistent deductive…
CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents
arXiv:2609.18779v1 Announce Type: new Abstract: Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate…
Version- and Scope-Aware Question Answering over Normative Documents: A Deployed System and an End-to-End Evaluation at Production Scale
arXiv:2609.18769v1 Announce Type: new Abstract: Correctly answering a question grounded in normative documents often depends on information outside any…
OpenRouter’s staggering token chart is the AI bubble debate in a single image
On OpenRouter, weekly token consumption has surged more than 25,000 percent since January 2025, from 0.5 to 126.2 trillion tokens. The number looks…
Beyond Truncation: Rethinking LLM Decoding as Ensemble Pruning
arXiv:2609.18723v1 Announce Type: new Abstract: We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large Language Model (LLM) decoding…
Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making
arXiv:2609.18591v1 Announce Type: new Abstract: In-context learning (ICL) enables large language model (LLM) agents to improve decisions using interaction…
The Uneven Impact of Generative AI on Student Learning: Examining the Roles of Reliance, Evaluation Literacy, and Course Policy in AI-related Courses
arXiv:2609.18676v1 Announce Type: new Abstract: Generative artificial intelligence (GenAI) is changing how students learn, yet the roles of course…
Lidl deploys driverless truck for store deliveries in Germany
Lidl has started using a cab-less autonomous electric truck for regular store deliveries in Germany, assigning it a daily replenishment route between its…
Reasoning through Evolution: Automatic Meta-path Discovery for LLM-based Fake News Detection
arXiv:2609.18597v1 Announce Type: new Abstract: Propagation structures provide crucial evidence for fake news detection, yet existing approaches primarily…
OpenAI’s GPT-6 Astra decrypts a Nazi radio message in ten hours that went unsolved for 83 years
A Bloomberg developer claims to have cracked an 83-year-old Enigma message from the Wehrmacht using OpenAI’s GPT-6 Astra. The 82-character radio message…
TRIPROBE: Probing Task Separability Beyond Classification for XAI
arXiv:2609.18525v1 Announce Type: new Abstract: Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of…
Z.ai Details GLM-5.3-Flash Inference Build on 100,000 Chinese Chips
Z.ai on September 17, 2026 published a technical account describing how it built a complete production-grade inference service for its GLM-5.3-Flash model…
AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution
arXiv:2609.18520v1 Announce Type: new Abstract: Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared…
AI News Brief Hourly Summary 2026-09-17 12h : 12 posts
12 posts published in the last hour 09:32Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning 09:32Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs 09:32First Token Matters: Understanding Safety Collapse in Large Reasoning Models 09:32Beyond Routine Compliance: Cunning Data…
Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning
arXiv:2609.18461v1 Announce Type: new Abstract: Personalized agents are required to reason over long-term history interactions to infer both explicit…
Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs
arXiv:2609.18481v1 Announce Type: new Abstract: Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among…
First Token Matters: Understanding Safety Collapse in Large Reasoning Models
arXiv:2609.18471v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) exhibit strong problem-solving abilities, yet their safety alignment often…
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
arXiv:2609.18515v1 Announce Type: new Abstract: Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky…