Skip to content
LMC Feed-Models, Papers, Benchmarks. Zero Fluff.Live

LMC Feed

LLM & AI News·RSS·Archive
|
1.I Tried to Run Qwen3.8–27B on a 16GB Mac Mini with AirLLM. Here’s Exactly Where It Breaks
39 pts·Towards AI··infra
2.Pew study confirms sharp rise of AI-written text on the web since ChatGPT's launch
44 pts·The Decoder··research
3.llm-anthropic 0.27
39 pts·Simon Willison··tools
4.Terminal Agents: A Survey of AI Agents in Command-Line Environments
58 pts·arXiv cs.AI··research
5.Knowing but Not Saying: Preventing Factual Access Failures in LLM SFT via Recall-Anchored Distillation
69 pts·arXiv cs.AI··research
6.UpgradeBench: A Decision-Centric Benchmark for Upgrading Fine-Tuned LLM Specialists
87 pts·arXiv cs.AI··research
7.Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
74 pts·arXiv cs.AI··research
8.RouteScan: A Non-Intrusive Approach to Auditing MoE LLMs Safety via Expert Routing Telemetry
89 pts·arXiv cs.CL··research
9.How to Orchestrate 100+ Agents With Claude Code
46 pts·Towards AI··tools
10.Weighted Memory Tree: Remembering What Matters for Long-Horizon LLM Agents
79 pts·arXiv cs.AI··research
11.When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
38 pts·arXiv cs.AI··research
12.Peer-Voted LLM-Agent Stress Tests Find Feed-Induced Lexical Convergence but No Reliable Matched-Exposure Advantage for Distributed Sources
40 pts·arXiv cs.AI··research
13.AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale
71 pts·arXiv cs.AI··research
14.SCOPE: A Generative Approach for LLM Prompt Compression
76 pts·arXiv cs.AI··research
15.AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems
38 pts·arXiv cs.AI··research
16.RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs
48 pts·arXiv cs.AI··research
17.The Metanym Game: An LLM Benchmark Without Ground Truth That Rises With the Models It Measures
42 pts·arXiv cs.AI··research
18.Fine-tuning LLMs for Tourist Trajectory Prediction using Field Experiment Data
76 pts·arXiv cs.LG··research
19.Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs
68 pts·arXiv cs.LG··release
20.Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements
51 pts·arXiv cs.LG··research
21.NeuroStrata: An Electroencephalographic Connectivity-Aware Deep Representation Learning Framework for Dynamic Brain Network Analysis of Mental Stress
71 pts·arXiv cs.AI··research
22.Recognizing Artificial Minds: A Philosophical Defense of AI Cognition
78 pts·arXiv cs.AI··research
23.TH-GNN: Heterogeneous Temporal Graph Neural Networks for LLM-Agent Shilling Attack Detection
69 pts·arXiv cs.CL··research
24.Nexus: Depth-Adaptive KV-Cache Splicing and Retrieval-Decoupled Tool Routing for Agentic LLMs on Unified Memory
69 pts·arXiv cs.AI··research
25.Certified Multi-Turn Robustness for LLM Safety via Compositional Bounds and Safety Persistence
85 pts·arXiv cs.AI··research
26.FL-MAESTRO: Multi-Agent LLM Orchestration for Resource-Constrained Federated Learning
30 pts·arXiv cs.AI··research
27.Auditable by Construction: An Ontology-Driven Framework for Trustworthy LLM Analytics in Enterprise Finance
54 pts·arXiv cs.AI··research
28.Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol
89 pts·arXiv cs.AI··research
29.Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
34 pts·arXiv cs.AI··research
30.Personalized Privacy Control in LLMs via Attention Head Intervention
44 pts·arXiv cs.AI··research
30 of 500
LMC Feed - LLM & AI News (August 2026) | LM Market Cap