FluxMem: Dynamic Heterogeneous Graph Memory Achieves SOTA on LoCoMo, Mind2Web, and GAIA Agent Benchmarks

arXiv·medium signal

Fang et al. (submitted May 27, arXiv 2605.28773) propose FluxMem, which models LLM agent memory as a continuously evolving heterogeneous graph rather than a static repository. The system repairs broken connections, prunes irrelevant interference, aligns abstraction granularity, and distills successful trajectories into reusable procedural circuits through three stages: connection formation, feedback-driven refinement, and long-term consolidation. Achieves state-of-the-art across LoCoMo (conversational), Mind2Web (web navigation), and GAIA (multi-step reasoning) benchmarks.