VeriTrace: Evolving Mental Models for Deep Research Agents

arXiv:2605.26081 · cs.AI · Submitted 2026-05-25 · Read on arXiv

cs.AI

Submitted: 2026-05-25

Updated: 2026-08-31

Comments: Accepted to Findings of EMNLP 2026

Code: https://github.com/youdotcom-oss/ydc-deep-research-evals

License: http://creativecommons.org/licenses/by/4.0/

The gist: Deep research agents face vast, interdependent, and pervasively uncertain information.

Terminology

Abstract

Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representations should look like, but leave their evolution to the LLM's implicit reasoning. Without explicit regulation, the intermediate layer is easily contaminated by mixed-quality information, and errors propagate along its dependencies, so model scale often ends up substituting for absent regulation. We argue that an agent's mental model should instead evolve through explicit feedback that continuously aligns task understanding with reality, and identify three regulatory loops: interpretive update, deviation feedback, and schema revision. We realise this in VeriTrace, a cognitive-graph framework that explicitly implements the three loops. Using matched Qwen3.5-27B backbones, VeriTrace improves over the strongest matched baseline by an average of 4.82 pp on DeepResearch Bench (DRB) Insight (1.83 pp Overall) and by 5.9 pp Overall win rate on DeepConsult. With Config-DeepSeek, it achieves the strongest reproducible open-source result on DRB.

Sources

Related papers