Interference
New memories crowd out old ones. Old ones distort new ones. They compete.
In the brain
Memories compete. Proactive interference: older memories impair learning and recall of newer, similar ones. Retroactive: new learning degrades oldUnderwood 1957. The brain actively inhibits competing traces during encoding and retrieval — it doesn’t just file everything side by side and hope.
The model
Interference theory frames forgetting as competition among similar traces at retrieval — scaled by how similar they are and how many compete — rather than as passive decay. The more crowded the neighborhood, the harder any one memory is to find.
In AI
Suddenly urgent for agents. The Unable to Forget benchmark showed an LLM’s retrieval accuracy collapsing toward zero as conflicting values accumulate — proactive interference, measured. FadeMem applies contradiction-triggered graded attenuation (an LLM classifies the conflict); Counterparts has the writer settle a conflict as changed (the old memory fades), corrected (put away, still readable) or still open (both stand), with a trail and an undo; Beijing Lingxin resolves conflicts with a BERT classifier.
The map
Proactive interference — eroded to a narrow claim (FadeMem §2.3, ~5 weeks pre-priority).
5 prior-art references
- Navinfo Europe~2024Catastrophic forgetting + episodic/semantic (neural-net training)patentGoogle Patents ↗
- Beijing Lingxin Intelligent Tech2024LLM memory retrieval; BERT-based "Memory Conflict Resolution"patentGoogle Patents ↗
- Taranjeet, et al.2025Mem0 — scalable long-term memory for AI agentsossarXiv ↗
- Wang, Sun2025PI-LLM ("Unable to Forget") — proactive interference in LLMspaperarXiv ↗
- Wei, Peng, Dong, Xie, Wang2026FadeMem: Biologically-Inspired Forgetting for Efficient Agent MemorypaperarXiv ↗
1 post-priority (field context, not prior art)
- SleepGate2026SleepGate — proactive interference + sleep consolidationpaperarXiv ↗
Interference is well diagnosed and barely solved. There are benchmarks and a few attenuation tricks, but reliably suppressing outdated information — without losing what’s still true — is open.