AGORA: 基于适配器接地观察-动作保留的LLM智能体无推理提示压缩
AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents
AI总结：
针对LLM智能体，提出AGORA无推理步骤级压缩器，通过结构提示解析器、格式关键内容保留和125M参数相关性评分器，在9个测试单元中8个保持≥75%的无压缩性能。
摘要：
广泛用于通用LM上下文的token级抽取式压缩器在结构上不适合LLM智能体：在跨越两个独立token级方法家族的17个（环境、骨干、方法）单元中，尽管实现了1.3-13.3倍的压缩，每个单元的均值奖励≤0.05。我们将这种失败模式命名为动作语法破坏——携带动作语义的token（标识符、括号、动作动词）正是那些自信息排名最低的token，因此通用压缩器可靠地移除它们，环境拒绝剩余部分。诊断指向步骤粒度压缩。我们引入AGORA，一种无推理的步骤级压缩器，结合结构提示解析器、格式和时效关键内容的始终保留底线，以及一个在反事实下一步动作变化标签上训练的125M参数相关性评分器（约2ms/步，零每步LLM开销）。在比较的无推理和基于LLM的方法中，AGORA是唯一在9个单元中的8个中保持≥75%无压缩性能的方法（唯一的例外为73%）；四路组件消融将结构底线隔离为主要的性能杠杆，而学习到的评分器是单一固定保留比率下实现1.0-11.5倍自适应端到端压缩的来源。
英文摘要：
The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, method) cells spanning two independent token-level method families, every cell collapses to mean reward <= 0.05 despite 1.3-13.3x realized compression. We name and characterize this failure mode as action-grammar destruction -- the tokens carrying action semantics (identifiers, brackets, action verbs) are exactly those self-information ranks lowest, so a general-purpose compressor reliably removes them and the environment rejects the residual. The diagnosis points to step-granularity compression. We introduce AGORA, an inference-free step-level compressor combining a structural prompt parser, an always-keep floor for format- and recency-critical content, and a 125M-parameter relevance scorer trained on counterfactual next-action-change labels (~2ms/step, zero per-step LLM toll). Across the compared inference-free and LLM-based methods, AGORA is the only one retaining >= 75% uncompressed performance in 8 of 9 cells (with the lone exception at 73%); a four-way component ablation isolates the structural floor as the dominant quality lever and the learned scorer as the source of 1.0-11.5x adaptive end-to-end compression from a single fixed keep ratio.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
