Differences

This shows you the differences between two versions of the page.

--- nlp:autonomous_language_agents [2026/07/22 05:41] – [Papers] jmflanig
+++ nlp:autonomous_language_agents [2026/08/09 21:21] (current) – jmflanig
@@ Line 43: / Line 43: @@
   * [[https://arxiv.org/pdf/2505.21963|Yano et al 2025 - LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agents]]
   * [[https://arxiv.org/pdf/2505.22571|Pham et al 2025 - Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems]]
+  * [[https://arxiv.org/pdf/2601.09393|Wang et al 2026 - AI-NativeBench: An Open-Source White-Box Agentic Benchmark Suite for AI-Native Systems]]
   * **Tool Use and Agent Skills**
     * "Agent Skills are instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently" (from [[https://agentskills.io/home|here]])
@@ Line 64: / Line 65: @@
     * [[https://arxiv.org/pdf/2402.07456|Wu et al 2024 - OS-Copilot: Towards Generalist Computer Agents with Self-Improvement]]
     * [[https://arxiv.org/pdf/2404.07972|Xie et al 2024 - OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ]]
-  * **AI and ML**
+  * **AI, ML, CS**
+    * [[https://arxiv.org/pdf/2311.09835|Tang et al 2023 - ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code]]
+    * [[https://arxiv.org/pdf/2410.07095|Chan et al 2024 - MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering]] (this is the highly cited one, see for example the [[https://deploymentsafety.openai.com/gpt-5-6-preview/gpt-5-6-preview.pdf|GPT-5.6 Preview System Card]])
     * [[https://arxiv.org/pdf/2409.11363|Siegel et al 2024 - CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark]]