Tag
CodeSpecWeave is a framework for synthesizing long-horizon coding tasks with rich, interdependent specifications, yielding 4,670 training tasks and a 100-task benchmark; RL training on these tasks significantly boosts DeepSWE-v1.1 performance over baselines.
DataPraxis 提出一种基于验证式工作区演化的分析任务合成框架,并据此构建 DataPraxis-5K 数据集(5000 条已验证轨迹),训练出 DataPraxis-27B 与 DataPraxis-35B-A3B 模型,在 DABStep 与 JobBench 上达到或超过 GLM-5.2 等前沿模型水平。
Navalia is a framework for Cowork Agents combining verifiable task synthesis from corporate financial reports with long-horizon post-training (SFT + RL), achieving consistent gains over its Qwen3.6-35B-A3B base model across five agent benchmarks.
Interlock 将长时程任务合成为类型化完成图,通过 agent-as-judge 验证与自训练提升复杂环境下 LLM 智能体的任务完成率,在 AutomationBench、JobBench 和 Harvey LAB 上带来 3–7 个百分点的提升。
ClawLoop 提出一个无需外部教师模型的自改进训练框架,通过任务合成、训练与诊断反馈三个阶段形成自我维持循环,持续提升基于 harness 环境的 LLM 智能体能力,并在多个基准上验证了效果。
FACET is a framework for synthesizing high-quality terminal tasks for AI agent training by preserving source intent and ensuring cross-artifact consistency, leading to improved performance on Terminal-Bench 2.1.
CalibForge is an autonomous terminal-task synthesis system that uses adversarial solver calibration to create learnable tasks for training terminal agents. It constructs 5,431 calibrated tasks and improves agent performance on Terminal-Bench2.0, SWE-bench Pro, and Doc2Repo.
CLI-Universe is a synthesis engine that generates verifiable terminal-agent tasks via multi-dimensional capability taxonomy and evidence-guided research, producing a distilled dataset of 6,000 trajectories. Fine-tuning Qwen3-32B on this dataset achieves 33.4% on Terminal-Bench 2.0, setting a new state-of-the-art for open-source models at or below 32B parameters.
TASTE is an automated method for generating challenging agent benchmarks with broader tool-use coverage by evolving tool sequences through adaptive contrastive n-gram modeling and iterative difficulty refinement. The resulting τ^c-Bench reveals that models nearly saturating existing benchmarks suffer severe performance drops, indicating saturation rather than robust skill.