不同格式的消息在多跳传递中表现差异大，弱代理时结构化格式反而更可靠。
Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent
- 设计多跳传递实验，对比五种消息格式在六跳中的信息保真度
- 强代理下格式影响小，弱代理下结构化格式召回率提升8.7倍
- 结构化格式能锁定错误不扩散，适合链路中最弱的环节
当大型语言模型代理在多跳传递中交接信息时，消息格式是否重要？现有研究分歧：优化格式者认为结构化消息降低成本且不影响准确率；限制格式者则认为强制结构会降低生成质量。但两者均未考察信息经多跳传递后的情况，而此时信息保真度而非单次生成才是关键。本文构建受控中继测试平台：12个程序生成的原子事实，以五种格式（自由文本、精准指令文本、JSON、三元组、键值对）经六跳传递，由固定强评分器基于程序真实答案评分，涵盖两种代理能力层级、认知负荷条件及成对分支错误注入。结果发现：（i）在忠实传递指令下，强代理几乎无信息损失，认知负荷使生成成本上升24-53%但格式间保真度仅差±1.8分；（ii）弱代理（1.5B参数）下，六跳召回率在各格式间差距扩大8.7倍（从2.3到20.5分），源于刚性格式的编码代价与固定键名JSON的抗漂移特性，导致格式排名反转；（iii）在成对分支注入实验中，错误值在83-100%的路径中持续传递至终点，其留存率与真实值一致，无邻近事实受损。结构化格式提供的是忠实且错误局部化的信道，而非纠错机制，格式选择应遵循链条中最弱的代理。
原文摘要 · Abstract (English)
When LLM agents hand off information to one another, does the message format matter? Two literatures disagree: format-optimization work reports that structured messages cut cost without hurting accuracy, while format-restriction work finds that imposing structure degrades generation -- and neither measures what happens when a message traverses multiple hops, where copy fidelity, not one-shot generation, dominates. We introduce a controlled relay testbed: briefs of twelve programmatically generated atomic facts are re-encoded hop-by-hop in five formats (free NL, precision-instructed NL, JSON, triples, key-value) over six hops, scored by a fixed strong grader against programmatic ground truth, across two relay-capability tiers, a cognitive-load condition, and a paired-fork error injection. We find that message-format effects are tier-dependent. (i) Under faithful-relay instructions a strong relay is nearly lossless -- the documented "telephone-game" collapse does not occur -- and adding per-hop cognitive load leaves format-level fidelity unchanged (within +/-1.8 points) while raising generation cost by 24-53%. (ii) Under a weak (1.5B) relay the across-format spread of six-hop recall grows by a factor of 8.7 (from 2.3 to 20.5 points), driven by two opposing mechanisms -- an encoding toll paid by the rigid formats and drift resistance specific to the fixed-key JSON schema -- that flip the format ranking in transit. (iii) In a paired-fork injection, an injected wrong value, once present, persists to the final hop in 83-100% of chains in every format, closely matching each format's retention of the true value, with no detectable collateral damage to neighboring facts. Structure buys a faithful, error-localizing channel -- not an error-correcting code -- and format choice should follow the weakest relay in the pipeline.
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。