CAMeR: Keyword-Gated Hybrid Activation for Adaptive Memory Retention in LLM Agents
On the map: LLM agents and tool use → Agent memory systems
Abstract (arXiv)
Large language model (LLM) agents operating over extended dialogues accumulate vast amounts of information, yet existing memory systems either retain everything indiscriminately or apply uniform forgetting heuristics that fail to distinguish relevant from irrelevant knowledge. We present CAMeR (Context-Activated Memory Reinforcement), a memory retention framework combining keyword-gated hybrid activation -- a joint symbolic (word-level Jaccard) and sub-symbolic (embedding cosine) gating mechanism -- with adaptive weight dynamics. CAMeR computes a hybrid similarity score for each memory-query pair; memories exceeding a threshold receive reinforcement while all memories undergo controlled decay. We introduce CAMeR-Bench, a 76-memory, 100-round benchmark spanning 8 topic clusters with graded activation frequency, designed to test adaptive retention where existing benchmarks (LoCoMO, LongMemEval) cannot. On CAMeR-Bench, CAMeR's keyword gate achieves a 1.6× larger retention gap between high-frequency and never-referenced memories compared to embedding-only gating (scissors gap: 0.039 vs. 0.024), while time-driven baselines (Oblivion, SuperLocalMemory) collapse to near-zero weights over 100 rounds. CAMeR's top-5 retrieval saves 83.2% tokens versus full-context approaches (39k vs. 231k cumulative) while producing weight signals that improve retrieval precision. Through 8 ablation conditions we establish that the keyword gate -- not learnable decay -- is the primary performance driver at this scale. Our findings demonstrate that hybrid symbolic-neural gating provides a simple yet effective mechanism for adaptive memory retention in LLM agents.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 10 of its 23 references that are in the map. First posted on arXiv 15 May 2026.
Builds on
10 of 23 references.
Closest ancestors · 3
Same direction, newest first
- 2026SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems6 Apr
- 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning27 Aug
- 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
Other references · 7
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
- 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
- 2021Not All Memories are Created Equal: Learning to Forget by Expiringcited by 32
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
- 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
- 2026Selective Memory Retention for Long-Horizon LLM Agents
- 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
- 2026FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
- 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
- 2026HasMem: Hard-Origin Adaptively Softened Memory for Long-Term LLM Agents
- 2026Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents