15 citations · 17 across the 9 of their papers we have counts for
7 papers · 1 filter
MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
Shangheng Du, Jinxin Shi, Shuaiyu Zhang +7
Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4AI) as a…
Beyond Correctness: Compute-Responsive Data Selection for Reasoning Model Post-Training
Liang He, Xiangyu Li, Yuxin Wang +4
Reasoning language models increasingly rely on test-time compute scaling, yet most existing work studies how to allocate inference computation while treating the model itself as fi…
From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents
Liang He, Jingbo Wen, Hongyu Gu +5
Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural knowledge. Although recent work has substantially improved skill retrieval du…
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
Lei Bai, Zongsheng Cao, Yang Chen +50
We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling…
Learning While Acting: A Skill-Enhanced Test-Time Co-Evolution Framework for Online Lifelong Learning Agents
Bo Mao, Jie Zhou, Yutao Yang +5
Lifelong learning is essential for Large Language Model (LLM) agents operating in dynamic, interactive environments. However, existing lifelong learning agents for long-horizon tas…
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Shangheng Du, Xiangchao Yan, Jinxin Shi +13
Large language model (LLM) agents are increasingly applied to long-horizon tasks such as scientific discovery and machine learning engineering (MLE), where sustained self-evolution…
Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation
Jingbo Wen, Liang He, Haoyu Wang +4
Test-time compute has emerged as an effective paradigm for improving large language model capability at inference time. Existing allocation strategies primarily prioritize tasks ac…