Differences

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

--- nlp:autonomous_language_agents [2025/10/08 09:17] – [Papers] jmflanig
+++ nlp:autonomous_language_agents [2026/03/05 00:02] (current) – [Papers] jmflanig
@@ Line 39: / Line 39: @@
   * [[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]]
+  * **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]])
+    * [[https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview|Claude - Agent Skills]] (I believe "agent skills" was introduced in Claude)
+    * [[https://agentskills.io/home|Agent Skills (website)]]
+    * [[https://arxiv.org/pdf/2602.12670|Li et al 2026 - SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks]]
   * **Software Engineering (SWE) Agents**
     * See also [[Software Engineering]]
@@ Line 54: / Line 59: @@
   * **OS Agents**
     * [[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 ]]
+    * [[https://arxiv.org/pdf/2404.07972|Xie et al 2024 - OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments ]]
 ===== Multi-Agents =====
@@ Line 64: / Line 69: @@
 ===== Related Pages =====
+  * [[ml:Computer Use Agents]]
   * [[Dialog]]
   * [[Language Model]]
   * [[Prompting]]