…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…
…Across SWE-bench Multilingual , SWE-bench Pro , and SWE-QA , integrating FastContext into Mini-SWE-Agent improves end-to-end resolution rates up to 5.5\% while reducing coding-agent token consumption…
…input token consumption decreases by up to 26% while issue-resolution accuracy is maintained or improved. Visualization is most useful during fault localization and when the agent autonomously controls exploration depth . These…
…Chung-En Sun , , Abstract Tool-calling language model agents exhibit improved safety after initial interactions, with a systematic benchmark demonstrating enhanced security through prior task completion. Generated by Qwen/Qwen2.5-Coder…
…We propose Knowledge-Oriented Behavior Exploration (UI-KOBE), a framework that improves lightweight mobile GUI agents with reusable app-specific graph knowledge. UI-KOBE first autonomously explores a mobile application and constructs…
…Haoqin Tu , , , , , , , , , , , , , , , , Abstract VisualClaw is a self-evolving multimodal agent that reduces deployment costs through hybrid encoding and skill evolution while improving video-QA accuracy across multiple benchmarks. Generated by Qwen/Qwen2…
…View arXiv page View PDF GitHub 5 Add to collection Community SkillGrad views agent skills as optimizable parameters and improves them through iterative trajectory analysis, textual momentum, and skill patching. It significantly…
…Self-Organizing Agent Teams for Long-Running Scientific Experimentation (2026) PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents (2026) AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration (2026) Auto Research…
…it improves ALFWorld success by 21.4 and 13.4 points on the seen and unseen splits with 64.1% fewer prefill tokens, and improves Search-QA exact match by 3.0…
…Across 8 multimodal deep search benchmarks, ODE improves the Qwen3-VL-8B agent from 24.9% to 39.0% on average, surpassing Gemini-2.5 Pro in standard agent-workflow setting (37…