Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…SpeechEditBench provides a rigorous diagnostic framework to identify bottlenecks in Speech LLMs, thereby facilitating the development of next-generation Speech LLMs with more robust and precise instruction-guided editing capabilities. Data and…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Can Large Language Models (LLMs) understand and reason about quantum operators ? Despite their remarkable capabilities in mathematics and symbolic reasoning, LLMs remain inherently blind…
…Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines Published on Jun 17 Submitted by Paul Kassianik on Jun 19 Cisco Foundation AI Authors: Paul Kassianik , , , , , , Abstract FAPO optimizes LLM pipelines by…
…Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents Published on May 13 Submitted by Mikhail Menschikov on May 14 Skoltech Authors: Mikhail Menschikov , , , , , , , , , , Abstract PersonalAI 2.0 enhances…
…Deployment-Time Layer Profiling for Memory-Constrained LLM Inference (2026) The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures (2026) Blink: CPU-Free LLM Inference…
…Internal-Signal Detection of Skill Poisoning in LLM Agents (2026) ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection (2026) Please give a thumbs up to this comment if you found it…
Papers arxiv:2607.01793 Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification Published on Jul 4 Submitted by YunHao-Feng on Jul 7 Ant Group Authors: , , , , , , , , , , , , , , Abstract…
…Sparse Decoupled Attention for Efficient Long-Context LLM Inference Published on Jun 3 Submitted by Yaosheng Fu on Jun 11 NVIDIA Authors: Yaosheng Fu , , , , Abstract SparDA is a decoupled sparse attention architecture…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Large language models (LLMs) are increasingly used to take actions in the real world and support human decision-making, yet most agents rely on…
…Steering LLM Logical Reasoning via Alignment of Natural-Language and Symbolic Views (2026) Where Reasoning Breaks: Logic-Aware Path Selection by Controlling Logical Connectives in LLMs Reasoning Chains (2026) When Chain-of…