压缩通信协议可能让双方总成本上升，且谁付钱取决于厂商和缓存状态。
Protocol Compression Changes Which Party Pays: Bilateral Cost in Cross-Organization LLM Agent Communication
- 在跨组织对话中，压缩消息会因解析失败导致额外调用，增加总token数
- 压缩使跨厂商成本差异扩大1.078倍，部分情况下接收方反而更贵
- 协议协商虽能达成共识，但实际任务完成率低，适合关注成本分配的研究者
跨组织大模型代理通信中，长消息按token计费。压缩表示法看似无成本节省，实则可能增加总消耗。当解析失败引发额外调用时，压缩比JSON基线多出8%至11%的token。在双端各自使用独立分词器、价格与缓存状态的场景下，我们对六家厂商的198个内容匹配项（共2,376个原生使用单元）进行了预注册的粒度级测量。进一步在采购谈判中对比英文基线、运行时模式协商后压缩及注入式压缩，覆盖1,053次完整对话（来自1,215格网格）及405次重跑。压缩使跨厂商成本离散度提升1.078倍（95%置信区间[1.066, 1.091]），两组厂商中出现支付方反转。运行时协商虽能达成121/135次模式一致，但仅9次成功完成任务，106次陷入僵局；平均对话轮次从17.6降至10.8，成本仅为英文基线的52%，源于会话提前结束而非握手开销回收。盈亏平衡点为20至70轮，最低值仅在条件性会计下成立，均高于所有观察到的英文会话。一组合同中双方各承担约一半成本，另一组在高缓存命中率下接收方负担更重。
原文摘要 · Abstract (English)
Agents that talk across organizations exchange long messages billed by the token. A shorter notation therefore looks like a saving that costs nothing but an agreement to use it. Recent work reports the saving is conditional. Compressed notation can instead raise total tokens by 8% to 11% over a JSON baseline, when parsing failures force extra model calls. That is measured for one payer. Between two organizations neither side can install a decoder at the other end, and each pays under its own tokenizer, price, and cache state. We measure both sides. A preregistered token-level study covered 198 content-matched item pairs across six vendors, for 2,376 native-usage cells. We then overlay an English baseline, runtime schema negotiation followed by compression, and injected-schema compression on a two-party procurement bargain with an exactly enumerated feasible set. The overlay covers 1,053 completed dialogues of a 1,215-cell grid across 3 model pairs, plus a 405-dialogue rerun of the negotiated condition. Compression amplifies cross-vendor cost dispersion by a factor of 1.078, with a 95% CI of [1.066, 1.091], and two vendor pairs reverse which endpoint is cheaper. Runtime negotiation succeeds as a protocol and fails as a bargain. The parties agree a schema in 121 of 135 headline dialogues, none of them the schema we would have supplied. They settle the task in only 9 of those dialogues, and they reach impasse in 106 of them. The negotiated sessions average 10.8 turns against 17.6, and cost 52% of the English total because sessions end sooner, not because the handshake is repaid. Break-even horizons run from 20 to 70 turns, the low end only under the conditional accounting, and all of them lie above every observed English session. On one cross-vendor pair both parties keep about half their cost. On the other the receiving party pays more at a high cache-hit rate.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。