Skip to content

Author

Yiqun Duan

9 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

When Does Execution Provenance Help Agent Memory Retrieval?

Overall, source-aligned candidates address the dominant granularity trade-off, while graph-conditioned propagation adds a smaller, targeted benefit for distributed evidence.

Yi-Qi Wang, Jin-Qian Ju, Jia-Qi Zhang et al. · 1 citation
#natural language process... Preprint Oct 2026

Learning What to Ask for Tomorrow: Active Preference Acquisition for Long-Term Personalized Web Agents

Web agents increasingly serve the same user across repeated online tasks such as booking travel, shopping, and scheduling, so their long-term usefulness depends on how well they know the user's preferences. Passive memory and personalization methods cannot obtain preferences the user never reveals, and clarification me...

Yi-Qi Wang, Zi-Zhi Zeng, Jia-Qi Zhang et al. · 0 citations
#machine learning Preprint Oct 2026

PACMI: Provenance-Aware Cascading Memory Invalidation for Long-Term LLM Agents

LLM agents rely on long-term memory to retain and reuse information when performing tasks over long horizons. Existing methods provide limited support for handling memories that become outdated as new observations or domain evidence arrive. Such outdated memories may remain semantically relevant, continue to affect dep...

Yi-Qi Wang, Jia-Qi Liu, Jia-Qi Zhang et al. · 1 citation
Preprint Sep 2026

When Does Execution Provenance Help Agent Memory Retrieval?

A language agent's execution history can exceed its context window, requiring its memory system to retrieve complete supporting evidence under a hard token budget. Evidence may span multiple execution events, yet conventional retrievers use fixed token windows and fixed-k metrics that reward individual fragments withou...

Yi-Qi Wang, Jin-Qian Ju, Jia-Qi Zhang et al. · 0 citations
#machine learning Preprint Sep 2026

Self-Confirming Superposition Traps in Reinforcement Learning

It is shown that this loop can sustain a lower-return policy even when representation fitting is globally optimal on data selected by the agent, which then uses the resulting returns to guide its next choices.

Dai Shi, Andi Han, Feng Chen et al. · 0 citations

A Benchmark and Diagnostic Study of Epistemic Admission in Shared Agent Memory

The Correlated Promotion Benchmark (CPB), which evaluates whether candidate claims should be admitted to shared memory, shows that policies which deduplicate sources reject many true claims alongside false ones, whereas policies preserving answer coverage admit nearly as many false claims as unrestricted sharing.

Xiao-Yang Li, Yi-Qi Wang, Chen-Cheng Zhu et al. · 2 citations
#artificial intelligence Preprint Sep 2026

IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models

IndustrialVLA-Bench is presented, an evidence-aware evaluation of six released VLA and WAM systems under a unified reporting schema that evaluates clean capability on LIBERO, non-language robustness on LIBERO-Plus, instruction sensitivity on LIBERO-Para, and observed execution cost.

Yi-Qi Wang, Zhi-Feng Rao, Jia-Qi Zhang et al. · 2 citations · ⚡1
#artificial intelligence Review Jun 2026

From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents

This survey examines evidence tracing and execution provenance as foundations for process-level accountability in trustworthy LLM agents and introduces a taxonomy covering trace sources, evidence and execution units, provenance relations, tracing granularity and timing, representation forms, and trust functions.

Yi-Qi Wang, Jia-Qi Zhang, Zhang-Kai Wu et al. · 37 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.