ProAct uses idle compute to anticipate user needs via dialogue history and memory, achieving 14.8% fewer turns, 11.7% less user effort, and 28.1% fewer hallucinations than reactive baselines on the new ProActEval benchmark.
Lightweight LLM Agent Memory with Small Language Models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Although LLM agents can leverage tools for complex tasks, they still need memory to maintain cross-turn consistency and accumulate reusable information in long-horizon interactions. However, retrieval-based external memory systems incur low online overhead but suffer from unstable accuracy due to limited query construction and candidate filtering. In contrast, many systems use repeated large-model calls for online memory operations, improving accuracy but accumulating latency over long interactions. We propose LightMem, a lightweight memory system for better agent memory driven by Small Language Models (SLMs). LightMem modularizes memory retrieval, writing, and long-term consolidation, and separates online processing from offline consolidation to enable efficient memory invocation under bounded compute. We organize memory into short-term memory (STM) for immediate conversational context, mid-term memory (MTM) for reusable interaction summaries, and long-term memory (LTM) for consolidated knowledge, and uses user identifiers to support independent retrieval and incremental maintenance in multi-user settings. Online, LightMem operates under a fixed retrieval budget and selects memories via a two-stage procedure: vector-based coarse retrieval followed by semantic consistency re-ranking. Offline, it abstracts reusable interaction evidence and incrementally integrates it into LTM. Experiments show consistent gains across model scales, with an average F1 improvement of about 2.5 over A-MEM on LoCoMo, while achieving higher efficiency and low median latency (83 ms for retrieval and 581 ms end-to-end).
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.
DASH-KV accelerates long-context LLM inference to linear complexity via asymmetric KV cache hashing and mixed-precision retention, matching full attention performance on LongBench.
Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.
A hybrid graph-based training-free framework for LLM context compression matches strong baselines and shows larger gains on long-document benchmarks.
CAP-CoT uses iterative adversarial prompt cycles to improve CoT accuracy, stability, and robustness across six benchmarks and four LLM backbones.
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.
citing papers explorer
-
Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents
ProAct uses idle compute to anticipate user needs via dialogue history and memory, achieving 14.8% fewer turns, 11.7% less user effort, and 28.1% fewer hallucinations than reactive baselines on the new ProActEval benchmark.
-
CAP: Controllable Alignment Prompting for Unlearning in LLMs
CAP is a reinforcement-learning-driven prompt optimization framework that suppresses target knowledge in LLMs while preserving general capabilities, enabling reversible unlearning without any parameter updates.
-
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
DASH-KV accelerates long-context LLM inference to linear complexity via asymmetric KV cache hashing and mixed-precision retention, matching full attention performance on LongBench.
-
Transforming External Knowledge into Triplets for Enhanced Retrieval in RAG of LLMs
Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.
-
From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors
A hybrid graph-based training-free framework for LLM context compression matches strong baselines and shows larger gains on long-document benchmarks.
-
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
CAP-CoT uses iterative adversarial prompt cycles to improve CoT accuracy, stability, and robustness across six benchmarks and four LLM backbones.
-
Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking
InSemRAG combines dynamic intent-aware hybrid retrieval and semantics-preserving chunk repair in an iterative loop, yielding 2.65 F1 gain on HotPotQA and 1.5 accuracy gain on FEVER with 4.32x lower latency than Multi-Hop RAG via SLMs.