SyncAI.news, a Varaisys broadcasting
Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations
JT

Jessica Tang, Shraddha Barke, Sharad Agarwal

· 1 min read

ResearcharXiv cs.CL

Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations

arXiv:2607.22610v2 Announce Type: replace-cross Abstract: 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.

Original source

This story was published by arXiv cs.CL and written by Jessica Tang, Shraddha Barke, Sharad Agarwal. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News