跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2607.22610 · v2

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

首次提交 2026-06-15 01:14
版本更新 2026-11-20 00:06
雷达观测 2026-11-20 14:52
arXiv ↗PDF ↗

摘要

When a model answers after several turns of dialogue and tool use, an overseer needs to know which earlier turns and intermediate steps it rests on. Attribution is the natural primitive for answering this, but existing context attribution methods process the full transcript in a single pass: they recover surface-level dependencies while missing the layered structure of multi-turn traces, in which an assistant turn is itself a derived artifact that condenses or transforms earlier context. We introduce multi-turn context attribution (MTCA): given a target span in a model response, the task of tracing attribution backward across turns to identify not only which prior turns were directly relevant, but also how those turns themselves depended on earlier context. We propose Tokengeist, an attribution-method-agnostic and scalable framework that recovers full dependency paths by casting attribution as a recursive traversal of a directed acyclic graph over conversation turns. We will release MTCABench, a benchmark of 3,970 target spans across 685 multi-turn conversations, annotated with gold provenance graphs reaching depths of up to 17, across four dependency types. Across four open-weight models, flat attribution methods fail to recover multi-hop dependencies, with source recall improving from 11-38% under flat attribution to 82-94% under Tokengeist. Our results reveal a systematic failure mode of single-pass attribution, which we term provenance collapse, where attribution terminates at the nearest assistant restatement instead of the originating event.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-20 00:06 · 最新观测版本

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

When a model answers after several turns of dialogue and tool use, an overseer needs to know which earlier turns and intermediate steps it rests on. Attribution is the natural primitive for answering this, but existing context attribution methods process the full transcript in a single pass: they recover surface-level dependencies while missing the layered structure of multi-turn traces, in which an assistant turn is itself a derived artifact that condenses or transforms earlier context. We introduce multi-turn context attribution (MTCA): given a target span in a model response, the task of tracing attribution backward across turns to identify not only which prior turns were directly relevant, but also how those turns themselves depended on earlier context. We propose Tokengeist, an attribution-method-agnostic and scalable framework that recovers full dependency paths by casting attribution as a recursive traversal of a directed acyclic graph over conversation turns. We will release MTCABench, a benchmark of 3,970 target spans across 685 multi-turn conversations, annotated with gold provenance graphs reaching depths of up to 17, across four dependency types. Across four open-weight models, flat attribution methods fail to recover multi-hop dependencies, with source recall improving from 11-38% under flat attribution to 82-94% under Tokengeist. Our results reveal a systematic failure mode of single-pass attribution, which we term provenance collapse, where attribution terminates at the nearest assistant restatement instead of the originating event.

查看此版本解读 →查看此版本原文 ↗