Almanac
product

LightMem

productactiveprovisionallightmem-5684e7c3·2 events·first seen 20d ago

Aliases: LightMem, LightMem2

Co-occurring entities

More like this (12)

Recent events (2)

6arXiv · cs.AI·29h ago·source ↗

TokenPilot: Dual-granularity context management cuts LLM agent inference costs by up to 87%

TokenPilot is a cache-efficient context management framework for LLM agents that addresses the trade-off between token sparsity and prompt cache continuity. It combines Ingestion-Aware Compaction (global prefix stabilization) with Lifecycle-Aware Eviction (local segment offloading) to reduce inference costs by 56–87% across benchmarks while maintaining competitive task performance. The system is evaluated on PinchBench and Claw-Eval and has been integrated into the open-source LightMem2 library.

6arXiv · cs.AI·20d ago·source ↗

FluxMem: Connectivity-Evolving Memory Framework for LLM Agents

FluxMem proposes a heterogeneous graph-based memory framework for LLM agents that continuously evolves its topology through three stages: initial connection formation, feedback-driven refinement, and long-term consolidation. Unlike static memory repositories, FluxMem repairs missing links, prunes interference, aligns abstraction granularity, and distills successful trajectories into reusable procedural circuits. The system is guided by a single metric for memory generalizability and evolutionary maturity, achieving state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.