跳到正文
Jones Ray

ScholarPulse 日报 2026-07-12

2026-07-12 学术简报:2 篇。LongStraw在固定GPU预算下实现了超过200万token的长上下文强化学习后训练。

今日速览

序号标题来源日期主题推荐等级
1LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU BudgetarXiv2026-07-16AI-Agent高
2StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering WorkflowsarXiv2026-07-16RAG高

重点论文与技术动态

1. LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

一句话结论

LongStraw在固定GPU预算下实现了超过200万token的长上下文强化学习后训练。

一段话。
该方法通过架构感知执行栈,解决了推理系统(百万token上下文)与RL后训练(通常256K token以下)之间的关键差距,特别适用于AI代理处理累积的长轨迹数据(如观察、工具输出和文档)。

核心内容

方法与数据

价值判断

摘要 A growing gap separates inference context lengths from RL post-training: inference systems are approaching million-token contexts, while post-training workloads often remain at 256K tokens or below and rely on length generalization at deployment. The gap is especially important for AI agents, whose observations, tool outputs, documents, and prior decisions accumulate over long trajectories. LongStraw is an architecture-aware execution stack for million-token RL post-training under a fixed GPU budget, instantiated with Group Relative Policy Optimization (GRPO). It evaluates the shared prompt without autograd, retains only model-specific state needed by later tokens, and replays short response branches one at a time, reducing the live training graph at the cost of additional replay time. We implement it for the hybrid recurrent and full-attention Qwen3.6-27B and the compressed-attention mixture-of-experts GLM-5.2. On eight H20 GPUs, LongStraw completes grouped Qwen scoring and response backward at 2.1M positions for groups of 2 and 8; increasing the group size adds only 0.21 GB of peak allocated memory, while a separate stress test reaches 4.46M positions. On 32 H20 GPUs, we validate the end-to-end LongStraw execution path for a 2.1M-token prompt across all 78 layers of GLM-5.2. These experiments establish execution capacity rather than complete training correctness because the captured prompt state is detached and some distributed forward and gradient composition paths remain incomplete.

2. StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows

一句话结论

结构工程中,基于工件的评估能暴露工作流级故障,提供更严格的评估基础,避免奖励流畅但工作流不完整或非可执行的输出。

核心内容

方法与数据

价值判断

摘要 Addressing a structural-engineering request requires more than a single answer; it requires a chain of interdependent artifacts: interpreted requirements, a computable model, validation records, solver outputs, code-check records, and a final report. Evaluations centered on question answering or script generation rarely verify this complete evidence chain and may therefore reward fluent outputs even when the underlying engineering workflow is incomplete, internally inconsistent, or non-executable. To address this limitation, we present StructureClaw, an artifact-centered workbench in which LLM agents operate through governed engineering skills, typed tools, shared artifact state, and local analysis backends. We also introduce StructureClaw-Bench, an executable benchmark of 150 controlled scenarios spanning standard workflow execution, interactive robustness, and multimodal structural-model reconstruction. A scenario succeeds only when all required artifact- and execution-level assertions pass in a single run. Across ten agent-model configurations, each evaluated on the same 50 standard cases, the average Success Rate rises from 56.8% with the generic-skill baseline to 88.6% with the full automatic workflow. The interactive and multimodal evaluations identify two prominent remaining challenges: safe handling of invalid numerical inputs and fixture-consistent reconstruction of structural models. These findings show that artifact-centered evaluation can expose workflow-level failures that are difficult to identify from final responses alone, providing a more rigorous basis for evaluating and improving structural-engineering agents. The code and benchmark are available at https://github.com/structureclaw/structureclaw.