MemFuse: Multi-Source Memory Fusion from Fragmented Observations
Ranking
Overall
77
Content
95
Popularity
35
Observed public metrics from 1 member.
Merged summary
TL;DR - MemFuse introduces a benchmark and structured memory system for agents that must combine fragmented, source-tagged observations into coherent long-term memories. It matters because realistic agent memory requires cross-source reasoning without losing evidence provenance.
- MemFuseBench uses a Scene-to-Sensor pipeline to generate controllable observations, evidence-grounded questions, adversarial distractors, and source metadata.
- The benchmark evaluates temporal reasoning, cross-source evidence fusion, and robustness to noise.
- MemFuse stores source-level evidence as atomic events, then organizes related events into fused memories through a causal fusion graph.
- Across three LLM settings, MemFuse achieved the best overall performance among the evaluated memory systems and consistently improved cross-source fusion tasks.
Sources (1)
MemFuse: Multi-Source Memory Fusion from Fragmented Observations
Public signals
Semantic Scholar citations 0 · Semantic Scholar influential citations 0
TL;DR - MemFuse introduces a benchmark and structured memory system for agents that must combine fragmented, source-tagged observations into coherent long-term memories. It matters because realistic agent memory requires cross-source reasoning without losing evidence provenance.
- MemFuseBench uses a Scene-to-Sensor pipeline to generate controllable observations, evidence-grounded questions, adversarial distractors, and source metadata.
- The benchmark evaluates temporal reasoning, cross-source evidence fusion, and robustness to noise.
- MemFuse stores source-level evidence as atomic events, then organizes related events into fused memories through a causal fusion graph.
- Across three LLM settings, MemFuse achieved the best overall performance among the evaluated memory systems and consistently improved cross-source fusion tasks.