Skip to content

Author

Mingyang Liu

We have 5 of 12 papers

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.

#artificial intelligence Preprint Nov 2026

RegimeCouncil: Paired-Evidence Routing For Memory Conflict Governance In LLM Agents

RegimeCouncil is proposed, a lightweight paired-evidence router that retains both scopes as advisors and arbitrates between them online without retraining the LLM, and outperforms the better fixed-scope policy across LongMemEval update streams and real-world historical drift.

Qing-Can Kang, Ming-Yang Liu, Shi-Xiong Kai et al. · 0 citations
#artificial intelligence Preprint Nov 2026

EvoDisco: Strategy Discovery for Evolving Agent Memory

EvoDisco is proposed, which formulates agent memory evolution as evolutionary strategy discovery: the agent must discover which operator to apply, when to apply it, and how to instantiate it, rather than rewriting memory under a static operator schedule.

Ming-Yang Liu, Qing-Can Kang, Shi-Xiong Kai et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Verify--Backtrack Loop: Structured Precondition Recovery for Long-Horizon Language Agents

Language agents increasingly tackle long-horizon tasks in interactive environments, where actions often depend on latent preconditions. The core difficulty is not trajectory length but recovery: when a prerequisite is missing or an earlier decomposition fails, trying another plausible action rarely helps. ReAct and lat...

Ming-Yang Liu, Qing-Can Kang, Shi-Xiong Kai et al. · 0 citations
Jul 2026

Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory

This work decomposes each operator's utility into a coverage effect on evidence omitted by retention and a signed replacement effect on raw evidence that already fits, which explains why the preferred action changes with relative budget pressure.

Qingcan Kang, Mingyang Liu, Shixiong Kai et al. · 1 citation
Jun 2026

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

Automating optimization modeling from natural language with large language models (LLMs) faces two key challenges. First, training corpora lack structural diversity. Second, data generation pipelines remain static and decoupled from model learning. To address these challenges, we propose EvoOptiGraph, a novel framework...

Qingcan Kang, Mingyang Liu, Xiaojin Fu et al. · 0 citations

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