ML Newsnew | past | best | rss | submit about
Stories from August 26, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. Agentic Context Management: Memory and Cost as Architecture Problems (arxiv.org)
79 points by gdad 39 days ago | hide | past | pdf | 28 comments
2. A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation (arxiv.org)
20 points by matt_d 38 days ago | hide | past | pdf | discuss
3. Training LLMs to write tools generalized beyond self use (arxiv.org)
6 points by blackcat201 39 days ago | hide | past | pdf | discuss
4. Dependencies in the LLM API Reseller Ecosystem (arxiv.org)
4 points by sbulaev 39 days ago | hide | past | pdf | discuss
5. Maia 200: A Software Defined Dataflow System for Large-Scale AI Acceleration (arxiv.org)
3 points by matt_d 38 days ago | hide | past | pdf | discuss
6. Credentials Are Leaked by LLM Agent Skills: An Empirical Study (arxiv.org)
3 points by geox 38 days ago | hide | past | pdf | discuss
7. Show HN: I built a tool showing how AI providers (should) throttle their models (arxiv.org)
3 points by eliotho 38 days ago | hide | past | pdf | discuss
8. DumpsterCluster: From Dumpster Diving to Serving Llama-70B on $60 GPUs (arxiv.org)
3 points by montalbano 39 days ago | hide | past | pdf | discuss
9. RL Contributes to Illegible Reasoning Traces in Hard Problems (arxiv.org)
3 points by make3 39 days ago | hide | past | pdf | discuss
10. Agent Harness Evolution Shapes Coding Agent Quality (arxiv.org)
2 points by wek 38 days ago | hide | past | pdf | 1 comment
11. From LLM Inference to Agentic Workloads: Characterization and Implications (arxiv.org)
2 points by matt_d 38 days ago | hide | past | pdf | discuss
12. Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce (arxiv.org)
2 points by lukaspetersson 38 days ago | hide | past | pdf | discuss
13. Generating Interpretable Networks Using Hypernetworks (arxiv.org)
1 point by E-Reverance 38 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv