13 posts were published in the last hour 0:31 : From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization 0:31 : ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization 0:31 : CoRCi: Cross-Reconstruction of Coherent Interests Modeling in…
From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization
arXiv:2608.09595v1 Announce Type: new Abstract: Compressing large language models to two bits or fewer is increasingly feasible through block-wise…
ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization
arXiv:2608.09577v1 Announce Type: new Abstract: Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging…
CoRCi: Cross-Reconstruction of Coherent Interests Modeling in Cross-Domain Sequential Recommendation
arXiv:2608.09580v1 Announce Type: new Abstract: Cross-Domain Sequential Recommendation (CDSR) aims to alleviate data sparsity by transferring dynamic user…
ICM Out! Better Tournament Strategy from Computed Continuations, vs. Solvers and LLMs
arXiv:2608.09586v1 Announce Type: new Abstract: The Independent Chip Model (ICM) converts tournament chips into reference prize equity, and policies are…
Adaptive Sequential Test Planning for Multi-Mechanism Reliability Qualification via Bayesian Monte Carlo Tree Search
arXiv:2608.09622v1 Announce Type: new Abstract: Reliability qualification of advanced semiconductor devices requires sequential stress decisions that…
One Adapter Pair per Model: A Universal Activation Interface for Language Models
arXiv:2608.09521v1 Announce Type: new Abstract: Activation-based tools are usually tied to one model’s native hidden space, requiring probes, sparse…
Renormalising Generative Models for Active Inference: Foundations, Derivations, and Verification
arXiv:2608.09512v1 Announce Type: new Abstract: Active inference offers a unified framework for perception, learning, and action, but scaling discrete…
verdi: retrieval is not transfer for continual world model optimization
arXiv:2608.09537v1 Announce Type: new Abstract: Foundation world models have made remarkable progress in planning, simulation, and embodied intelligence.…
Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
This post has no text preview — click the link below to read the original article. This article has been indexed from Hugging Face – Blog Read the original article: Meta is back with Muse Glimmer: local, agentic, multimodal, and…
Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents
arXiv:2608.09555v1 Announce Type: new Abstract: External natural-language skills provide large language model (LLM) agents with reusable and editable…
Meta Muse Glimmer brings local AI agents to consumer GPUs
Meta is releasing Muse Glimmer under an Apache 2.0 licence for local AI agents that can run on a consumer GPU. The company’s Superintelligence Labs has…
The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games
arXiv:2608.09574v1 Announce Type: new Abstract: LLMs are rapidly embedding themselves into daily life: drafting our emails, managing our schedules, and…
AI News Brief Hourly Summary 2026-08-12 02h : 13 posts
13 posts were published in the last hour 23:31 : Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents 23:31 : Coupled Graph–Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity 23:31 : Listen, See…
Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM Agents
arXiv:2608.09485v1 Announce Type: new Abstract: Cooperative capabilities in language models are dual-use. The same social reasoning that supports civic…
Coupled Graph–Policy Distillation for Personalized Medication Safety in Older Adults with Multimorbidity
arXiv:2608.09443v1 Announce Type: new Abstract: Large language model (LLM) agents can support medication review between clinical visits, but safe choices…
Listen, See and Track: Spatio-Temporal Audio-Visual Sound Event Reasoning for Omni-Modal Language Models
arXiv:2608.09435v1 Announce Type: new Abstract: Understanding dynamic sound sources requires jointly determining what produces a sound, where the source…
KVDiagnosis: A Diagnostic Benchmark for KV-Cache Compression in Long-Context Language Models
arXiv:2608.09412v1 Announce Type: new Abstract: KV-cache compression reduces long-context memory, but aggregate task scores reveal neither which correct…