HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
arXiv preprint arXiv:2602.13594 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
DarkForest improves multi-agent LLM reasoning via independent agents, semantic clustering of responses, and calibrated belief estimation with controlled communication, yielding up to 30.7% better benchmark metrics and 6.5x lower token consumption than heavy-communication baselines.
citing papers explorer
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
DarkForest: Less Talk, Higher Accuracy for Multi-Agent LLMs
DarkForest improves multi-agent LLM reasoning via independent agents, semantic clustering of responses, and calibrated belief estimation with controlled communication, yielding up to 30.7% better benchmark metrics and 6.5x lower token consumption than heavy-communication baselines.