…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from…
…Reasoning (2026) Think Anywhere in Code Generation (2026) HintMR: Eliciting Stronger Mathematical Reasoning in Small Language Models (2026) Efficient Reasoning on the Edge (2026) Post Reasoning: Improving the Performance of Non-Thinking…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Reinforcement learning (RL) can be used to improve the policy ( denoiser ) of diffusion large language models (dLLMs), while being hindered by the intractability of…
…Massimo Rondelli , Francesco Pivi , Abstract BlenderRAG enhances natural language to Blender code generation by leveraging a retrieval-augmented approach with a curated multimodal dataset, improving both compilation success and semantic alignment without…
…improving AI system for embodied agents autonomously refines its own prompts, skills, and memory through continuous learning without environment resets, achieving human-level performance in complex video games. AI-generated summary Coding…
…However, code-switching ASR (CS-ASR) remains particularly challenging due to the severe scarcity of multilingual CS speech resources across diverse language pairs. Existing approaches primarily improve CS-ASR performance through synthetic…
…Tong Ye , , , , , , , , Abstract DOMINO enables domain-specific data synthesis through an inductive approach that learns domain representations from reference examples, improving code benchmark performance without requiring explicit domain descriptions. Generated by Qwen…
…MLS-Bench contains 140 tasks across 12 domains, each requiring an agent to improve one targeted component of an ML system or algorithm and demonstrate that the improvement generalizes across controlled settings…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Language agents increasingly rely on reusable skills to improve multi-step web automation across related tasks. A growing line of work studies online skill…
Papers arxiv:2605.08083 LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Published on May 8 Submitted by Chengsong Huang on May 11 #3 Paper of the day Google Authors: Tong…