6 papers
From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQL
Jiaqian Wang, Yutao Qi, Wenjin Hou +2
Test-time scaling can correct difficult text-to-SQL queries, but the extra computation is normally discarded after each answer. Systems increasingly retain verified repair episodes…
MAPLE-Guard: Memory-Aware Link Enforcement Against Memory-Link Poisoning in Multi-Agent Systems
Wenjun Xiong, Yijin Zhou, Jiaqian Wang +6
LLM-based multi-agent systems (MAS) increasingly rely on persistent private and shared memories for long-horizon coordination. This memory layer improves continuity, but it also gi…
EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement
Jiaqian Wang, Yutao Qi, Wenjin Hou +2
Text-to-SQL enables non-expert users to query databases in natural language, yet real-world schemas often suffer from ambiguous, abbreviated, or inconsistent naming conventions tha…
Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
Yujie Zheng, Zhuo Li, Shengtao Zhang +8
Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a…
MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
Shengtao Zhang, Jiaqian Wang, Ruiwen Zhou +11
The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evo…
From Query to Logic: Ontology-Driven Multi-Hop Reasoning in LLMs
Haonan Bian, Yutao Qi, Rui Yang +4
Large Language Models (LLMs), despite their success in question answering, exhibit limitations in complex multi-hop question answering (MQA) tasks that necessitate non-linear, stru…