01Act
Agent systems
Agents that plan, use tools, and improve through interaction instead of staying fixed after deployment.
Research at SJTU-MARL · Shanghai
Agents that remember,
adapt, and improve
at runtime.
I am Shengtao Zhang. I study self-evolving agents at the intersection of reinforcement learning and memory—systems that turn experience into better decisions without retraining the underlying model.
SJTU-MARLAgent · RL · Memory
Current focus
How can an agent learn from every interaction while keeping its reasoning stable?
Research thesis
From storage to experience.
My work connects three layers of adaptive intelligence: acting in an environment, learning from feedback, and preserving useful experience.
02Adapt
Runtime reinforcement learning
Feedback-driven learning loops that turn execution outcomes into better choices at inference time.
03Remember
Memory
Episodic and value-aware memory that retrieves experience for utility, provenance, and continual refinement.
Featured work
Learning at inference time.
MemRL
A non-parametric route to runtime self-improvement: keep the reasoner stable, let episodic memory learn utility from feedback.
MemRL first recalls similar episodes, then selects them by learned Q-values. The frozen LLM acts with the retrieved context, while environmental rewards update each memory item's utility.
MemQ
Credit assignment for agent memory, propagated through the provenance chains that make later memories possible.
Each interaction retrieves memories, creates a new episode, and records its provenance. TD feedback then travels backward through the DAG to update the memories that enabled success.
EvoKernel
Value-guided experience reuse turns sparse NPU feedback into a continual drafting-and-refinement loop.
Cold-start drafting retrieves transferable experience for an initial kernel. Verification rewards update the shared memory, which later reuses successful traces for continual latency refinement.
Selected publications
Research index.
Work on self-evolving agents, reinforcement learning, and memory, alongside graph learning, language, and multimodal reasoning.
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
A non-parametric route to runtime self-improvement: keep the reasoner stable, let episodic memory learn utility from feedback.
MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
Credit assignment for agent memory, propagated through the provenance chains that make later memories possible.
Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
Value-guided experience reuse turns sparse NPU feedback into a continual drafting-and-refinement loop.
A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories
A reasoning-rich breast ultrasound resource that connects images, pathology coverage, and clinically grounded chains of thought.
PTCL: Pseudo-Label Temporal Curriculum Learning for Label-Limited Dynamic Graph
Temporal curriculum learning makes final-timestamp labels useful across the full evolution of a dynamic graph.
Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection
Genre structure and user history expose spoiler patterns that text-only classifiers tend to miss.
Recent notes
News.
MemQ releasedCredit assignment for self-evolving memory agents over provenance DAGs.↗EvoKernel accepted at ICML 2026Value-driven memory for cold-start NPU kernel synthesis and continual refinement.↗MemRL releasedRuntime reinforcement learning on episodic memory for self-evolving agents.↗Unveiling the Hidden at ECML PKDDGenre- and user-aware modeling for spoiler detection.↗
About
Building learning loops for agents that operate in the real world.
I work on agent learning and memory with SJTU-MARL. I am especially interested in non-parametric adaptation: how agents can use outcomes, provenance, and episodic experience to improve continuously while the base model stays stable.
Previously, I studied Artificial Intelligence at Xi'an Jiaotong University and worked on dynamic graph learning, language understanding, and reliable decision systems.
Z. S. T.
Zeal stirs tides.「热望所至，潮涌不息。」