Paper: Weighted Memory Tree improves long-horizon agent accuracy
rohanpaul_ai · x · 2026-08-25
A paper proposes Weighted Memory Tree, which scores memories and decays unused ones, improving reasoning accuracy for long-horizon agents. Experiments show it outperforms linear history and unscored tree across models.
More from coding & agent
- The Stack 3 Downloads Surpass Nemotron-CC 2 and UltraFineweb Combined — lhoestq · 2026-08-25
- Qwen3.8-27B demo: Precise coordinate mapping in Computer Use — MaziyarPanahi · 2026-08-25
- NVIDIA and Perplexity Launch Portable Computer with Hybrid Agent Stack — ryanshrout · 2026-08-25
- OpenCode Memory gives AI coding agents persistent memory via local vector DB — tom_doerr · 2026-08-25
- mcpd: Turn your sandbox into an MCP server with just configuration — xwil · 2026-08-25
- Open the specs, keep the code: a new open-source strategy for the agent era — sull · 2026-08-25