cs.AINov 2, 2026

DrawOffer: Evidence-Grounded Longitudinal User-State Modeling for Career Support

Authors: Lele Xu, Yuning Bian, Yifan Yuan

Organizations: Anhui University of Technology

Abstract

Career-support assistants must distinguish user claims from evidence of current ability and withhold judgments when evidence is insufficient. DrawOffer separates language-model observation extraction from deterministic inference over source-linked records to maintain uncertain ability estimates, experience assessments, and revisable issues. We evaluate 102 fictional personas with 580 scored checkpoints, a historical full-context and Mem0 comparison, and three auxiliary knowledge-tracing datasets. On 37 test personas, DrawOffer passes 169/210 checkpoints; checkpoint-defined issue precision and recall are 0.875 and 0.636. Across three development simulations, 87.0% of checkpoint verdicts agree, including persistent failures. A cache-only development ablation replacing answer-evidence requirements with confidence-only settlement reduces majority-vote passes from 306 to 293 of 370 and issue precision from 0.927 to 0.725. Equalizing positive source weights improves predictive metrics without changing total passes; removing decay gives mixed results. These findings support an exploratory systems contribution centered on evidence sufficiency. Developer-authored scenarios, unmatched baseline models, historical test exposure, and incomplete public artifacts limit generalization and independent reproduction.

Figures & tables

Explore similar work

CardsList
  1. OptionWorld: A Benchmark for Diagnosing Failures of LLMs as Long-Term Personal Assistants

    Oct 20, 2026Ruoyu Zhang, Zhaocen Liu, Weiyi Tian +2LLM Agent EvaluationLLM Agents

  2. Signals, Evidence, and Context: User Scrutiny in Real-World LLM Conversations

    Nov 5, 2026Ahana Biswas, Yu-Ru LinLLM Answer VerificationLLM Reliability

  3. Ask Before You Answer: A Question-Driven Evidence Reasoning Architecture (QERA) for In-Context Learning

    Oct 26, 2026Jinhu Qi, Minda Hu, Wentao Zhang +2Evidence-Grounded QAImplicit Reasoning in Language Models