NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
Scaling executable agent training data for LLM post-training is bottlenecked by substrate-bound methods that tie task generation to predefined tools, repositories, or skill graphs: expanding coverage requires manual substrate engineering, each new domain demands a bespoke pipeline, and the resulting task distributions often reflect substrate biases rather than real-world demand. We introduce NexForge, a requirement-driven framework that takes high-level capability requirements as input and synthesizes diverse, executable agent tasks and expert trajectories for SFT. NexForge first investigates real-world demand to construct scenarios and task profiles, then performs distribution-aware compilation to generate task directives. For each directive, NexForge automatically retrieves or constructs the required files, dependencies, and runtime configurations, and finally collects expert rollouts to produce training trajectories. Without domain-specific infrastructure, NexForge produces 3.6K terminal and 2K office tasks, improving Qwen3.5-35B-A3B Base from 22.5\% to 52.0\% on Terminal-Bench 2.0 and from 813 to 1338 Elo on GDPval; scaling further to 43.2K terminal tasks yields 58.4\%, on par with Claude Opus 4.6 equipped with Claude Code. Scaled further, NexForge-synthesized data contributes to the training of Nex-N2, a family of publicly available agent models that lift Qwen3.5-397B-A17B to 75.3\% on Terminal-Bench 2.1 and to 1585 Elo on GDPval---achieving state-of-the-art open-source performance and surpassing several frontier proprietary systems. Nex-N2 models are available at https://nex.sii.edu.cn/.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Observational Scaling Laws and the Predictability of Language Model Performance
Understanding how language model performance varies with scale is critical to benchmark and algorithm development. Scaling laws are one approach to building this understanding, but the requirement of training models acro…
Language ModelingLanguage ModellingEfficient Agents: Building Effective Agents While Reducing Cost
The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work…
DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
Large Language Models (LLMs) equipped with web search capabilities have demonstrated impressive potential for deep research tasks. However, current approaches predominantly rely on either manually engineered prompts (pro…
NavigatePrompt EngineeringRAGReinforcement Learning (RL)+1Learning to Orchestrate Agents in Natural Language with the Conductor
Powerful large language models (LLMs) from different providers have been expensively trained and finetuned to specialize across varying domains. In this work, we introduce a new kind of Conductor model trained with reinf…
Reinforcement LearningSLA Management in Reconfigurable Multi-Agent RAG: A Systems Approach to Question Answering
Retrieval Augmented Generation (RAG) enables Large Language Models (LLMs) to generalize to new information by decoupling reasoning capabilities from static knowledge bases. Traditional RAG enhancements have explored vert…
ManagementQuestion AnsweringRAGRetrieval-augmented Generation