Heng Ji

MemGuard introduces a type-aware memory framework to prevent heterogeneous memory contamination in long-term memory-augmented LLMs, significantly improving memory reliability and efficiency.

MolLingo is a multi-agent system that significantly improves automated molecular design by integrating domain-specific chemical reasoning and structural context into LLMs, outperforming state-of-the-art models on multiple benchmarks.

The paper analyzes observation masking in long-horizon search agents, finding that its effectiveness depends on a complex interaction between the model's capacity and the retriever's strength, exhibiting an inverted-U shaped gain.

The paper introduces Harness-1, a search agent that separates semantic decision-making from state management by using a stateful search harness, achieving state-of-the-art performance across diverse retrieval benchmarks.

ResMerge proposes a residual-based spectral merging framework that improves the combination of multiple reinforcement learning (RL) expert models by stabilizing the aggregation process using a residual backbone.