about
691. Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems (arxiv.org)
1 point by yubblegum 94 days ago | hide | past | pdf | discuss
692. Reap: Automatic Curation of Coding Agent Benchmarks (arxiv.org)
2 points by dipankarsarkar 94 days ago | hide | past | pdf | discuss
693. VeriCache: Turning Lossy KV Cache into Lossless LLM Inference (arxiv.org)
1 point by matt_d 94 days ago | hide | past | pdf | discuss
694. OpenAI Gym (2016) (arxiv.org)
1 point by gregsadetsky 95 days ago | hide | past | pdf | discuss
695. Explaining Attention with Program Synthesis (arxiv.org)
1 point by bilsbie 95 days ago | hide | past | pdf | discuss
696. Predictable GRPO (arxiv.org)
1 point by rghosh8 95 days ago | hide | past | pdf | discuss
697. Why averaging LLM benchmark scores is fundamentally broken (arxiv.org)
1 point by testofschool 95 days ago | hide | past | pdf | discuss
698. Reinforcement Learning with Metacognitive Feedback (arxiv.org)
1 point by guard0g 95 days ago | hide | past | pdf | 1 comment
699. Discretizing Reward Models (arxiv.org)
2 points by gmays 95 days ago | hide | past | pdf | discuss
700. Scalable GANs with Transformers (arxiv.org)
3 points by MediaSquirrel 95 days ago | hide | past | pdf | discuss
701. Agentic Hardware Design as Repository-Level Code Evolution (arxiv.org)
2 points by matt_d 96 days ago | hide | past | pdf | discuss
702. Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora (arxiv.org)
4 points by jflynt76 96 days ago | hide | past | pdf | discuss
703. Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems (arxiv.org)
3 points by Brajeshwar 96 days ago | hide | past | pdf | discuss
704. Compiling Agentic Workflows into LLM Weights (arxiv.org)
2 points by dipankarsarkar 96 days ago | hide | past | pdf | discuss
705. Towards Automating Scientific Review with Google's Paper Assistant Tool (arxiv.org)
2 points by Anon84 96 days ago | hide | past | pdf | discuss
706. Memory in the Age of AI Agents (Survey Paper) (arxiv.org)
3 points by thoughtpeddler 96 days ago | hide | past | pdf | discuss
707. Simplified Sparse Attention via Gist Tokens (arxiv.org)
4 points by E-Reverance 96 days ago | hide | past | pdf | discuss
708. Are We Ready for an Agent-Native Memory System? (arxiv.org)
2 points by matt_d 97 days ago | hide | past | pdf | discuss
709. Radiology's Last Exam (RadLE) (arxiv.org)
2 points by AFF87 97 days ago | hide | past | pdf | discuss
710. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems (arxiv.org)
3 points by tamnd 97 days ago | hide | past | pdf | discuss
711. Towards Automating Scientific Review with Google's Paper Assistant Tool (arxiv.org)
2 points by ilreb 97 days ago | hide | past | pdf | discuss
712. LLM Medical Triage: Same Symptoms, Gender-Dependent Urgency (arxiv.org)
1 point by p4bl0 97 days ago | hide | past | pdf | discuss
713. Category-Theoretic Comparative Framework for Artificial General Intelligence (arxiv.org)
2 points by measurablefunc 97 days ago | hide | past | pdf | discuss
714. PCB-QA: Evaluating LLMs over the First PCB Design Question-Answer Dataset (arxiv.org)
2 points by teleforce 97 days ago | hide | past | pdf | discuss
715. Breaking the Tokenizer Barrier: On-Policy Distillation Across Model Families (arxiv.org)
2 points by Jimmc414 97 days ago | hide | past | pdf | discuss
716. Knowledge Distillation of Black-Box Large Language Models (2024) (arxiv.org)
123 points by babelfish 97 days ago | hide | past | pdf | 23 comments
717. Autoregressive Boltzmann Generators (arxiv.org)
4 points by root-parent 98 days ago | hide | past | pdf | 1 comment
718. The Scaling of PEFT: Towards Million Personal Models of Trillion Parameters (arxiv.org)
2 points by Anon84 98 days ago | hide | past | pdf | discuss
719. Improved LLM as a Judge Techniques (arxiv.org)
2 points by haritha1313 98 days ago | hide | past | pdf | discuss
720. Apple Neural Engine: Architecture, Programming, and Performance (arxiv.org)
234 points by Jimmc414 98 days ago | hide | past | pdf | 29 comments