13 papers
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…
Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark
Yigeng Jiang, Tengchao Yang, Taoyong Cui +25
Deep research agents are Large Language Model (LLM)-based systems designed for autonomous, multi-step scientific reasoning, and they hold immense potential for accelerating researc…
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…
MTRouter: Cost-Aware Multi-Turn LLM Routing with History-Model Joint Embeddings
Yiqun Zhang, Hao Li, Zihan Wang +6
Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model invocations, accumulating substan…
Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning
Zhiyin Yu, Bo Zhang, Qibin Hou +3
Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, the…
A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions
Zhiyin Yu, Yuchen Mou, Juncheng Yan +17
Reinforcement learning (RL) has emerged as a powerful post-training paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, reinforcement learni…
Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
Wenzhen Yuan, Wutao Xiong, Fanchen Yu +7
Multi-agent systems (MAS) demonstrate clear advantages in tackling complex problems by coordinating diverse agents and external tools. However, most existing orchestration methods…
Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale
Shengji Tang, Weihao Lin, Peng Ye +9
Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to mon…
DualResearch: Entropy-Gated Dual-Graph Retrieval for Answer Reconstruction
Jinxin Shi, Zongsheng Cao, Runmin Ma +6
The deep-research framework orchestrates external tools to perform complex, multi-step scientific reasoning that exceeds the native limits of a single large language model. However…
AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents
Shangheng Du, Xiangchao Yan, Dengyang Jiang +6
Large language models (LLMs) have shown impressive performance in general programming tasks. However, in Machine Learning Engineering (MLE) scenarios such as AutoML and Kaggle comp…
FlowSearch: Advancing deep research with dynamic structured knowledge flow
Yusong Hu, Runmin Ma, Yue Fan +11
Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-s…
Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback
Wenzhen Yuan, Shengji Tang, Weihao Lin +8
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex rewar…
ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineering
Zexi Liu, Jingyi Chai, Xinyu Zhu +5
The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering. However, the dominant prompt-ba…