Tracked topic
Framework is a company that produces modular laptops designed so users can replace components like the motherboard, display, and keyboard.
…Yi Wang , , , , , , , , , , , , , Siyuan Feng , , Jianlan Luo Abstract Learning While Deploying framework enables continuous improvement of Vision-Language-Action policies through fleet-scale offline-to-online reinforcement learning with distributed robot experience and…
…Shuzheng Si , , , , Dingwei Chen , , , , , , , , Abstract A self-evolving framework autonomously discovers and refines context-specific skills for language models through a multi-agent self-play loop with Challenger, Reasoner, and Judge components…
…The framework shifts manual harness engineering into automated harness engineering, and takes one step further—automating the design of the automation itself. Our framework enables rapid harness convergence on any new task…
…Taicheng Guo , , , Abstract An agentic framework called AutoLLMResearch automates high-cost large language model experiment configurations by learning from multi-fidelity experimental environments and enabling efficient configuration identification through cross-fidelity extrapolation…
…Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution Published on May 11 Submitted by dj on May 14 Authors: , , , , Abstract HAGE introduces a weighted multi-relational memory framework that enables query…
…Zihao Li , , , , , , , , Jingrui He Abstract Eywa is a heterogeneous agentic framework that extends language-centric systems to scientific foundation models by integrating domain-specific models with language-based reasoning interfaces for improved…
…A Framework for Evaluating Coding Agents on Sequential Software Evolution (2026) An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc (2026) Vision2Web: A Hierarchical Benchmark for Visual Website Development with…
…Self-Evolving Reinforcement Learning for Instruction Following Published on May 8 Submitted by rain on May 12 Fudan University Authors: , , , , , , , , , Abstract A self-evolving reinforcement learning framework enhances large language model instruction…
…We introduce Web2BigTable, a multi-agent framework for web-to-table search that supports both regimes. Web2BigTable adopts a bi-level architecture in which an upper-level orchestrator decomposes the task into…
…A Scalable Framework for Building Effective Claw Agents (2026) Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents (2026) Experiential Reflective Learning for Self-Improving LLM…