Memory is Reconstructed, Not Retrieved: Graph Memory Improves LLM Agent Recall by 23%
National University of Singapore
MRAgent replaces the standard retrieve-then-reason memory paradigm with active reconstruction: agent memory is stored as a Cue-Tag-Content graph where associative tags act as semantic bridges. During inference the agent iteratively explores and prunes retrieval paths guided by intermediate reasoning evidence, avoiding combinatorial explosion. Evaluated on LoCoMo and LongMemEval benchmarks, MRAgent achieves up to 23% improvement over strong retrieval baselines.
Why it matters
Static retrieval (embedding similarity search) fails when the right memory depends on what the agent has already inferred mid-task. By fusing LLM reasoning directly into the memory traversal step, this work addresses a fundamental bottleneck for long-horizon agent tasks and suggests graph-structured memory as a more robust alternative to flat vector stores.
Importance: 2/5
Solid research contribution on agent memory; 23% benchmark improvement; addresses a real limitation of vector-store retrieval for reasoning-heavy tasks.