Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
Canonical reference
Recursively summarizing enables long-term dialogue memory in large language models
Canonical reference. 100% of citing Pith papers cite this work as background.
10
Pith papers citing it
10
external citations · Pith
Background
100% of classified citations
abstract
Recently, large language models (LLMs), such as GPT-4, stand out remarkable conversational abilities, enabling them to engage in dynamic and contextually relevant dialogues across a wide range of topics. However, given a long conversation, these chatbots fail to recall past information and tend to generate inconsistent responses. To address this, we propose to recursively generate summaries/ memory using large language models (LLMs) to enhance long-term memory ability. Specifically, our method first stimulates LLMs to memorize small dialogue contexts and then recursively produce new memory using previous memory and following contexts. Finally, the chatbot can easily generate a highly consistent response with the help of the latest memory. We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation. Also, we show that our strategy could nicely complement both long-context (e.g., 8K and 16K) and retrieval-enhanced LLMs, bringing further long-term dialogue performance. Notably, our method is a potential solution to enable the LLM to model the extremely long context. The code and scripts are released.
citation-role summary
background 5
citation-polarity summary
roles
background 5polarities
background 5representative citing papers
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation, delivering 9-18% accuracy gains and 11% latency reduction.
Akashic’s MemAttention plus locality-aware placement improves agent task accuracy by up to 10.2 points and throughput by up to 1.21× over prior memory systems across four long-horizon workloads.
CARE fine-tunes LLMs on counselor-validated crisis dialogues to produce responses with stronger semantic and strategic alignment to expert standards than general-purpose models in Hebrew and Arabic.
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
citing papers explorer
-
Evaluating Very Long-Term Conversational Memory of LLM Agents
Creates LoCoMo benchmark dataset for very long-term LLM conversational memory and shows current models struggle with lengthy dialogues and long-range temporal dynamics.
-
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
VitaBench 2.0 introduces a benchmark for long-term personalized and proactive agent behavior, with results indicating substantial gaps in current frontier LLMs.
-
MemGym: a Long-Horizon Memory Environment for LLM Agents
MemGym unifies agent gyms into a memory benchmark with isolated scoring across tool-use, research, coding, and computer-use regimes plus a lightweight reward model for tractable coding evaluation.
-
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
KV cache compression causes task-dependent degradation in high-density reasoning due to disrupted CoT links; ShotKV mitigates this by preserving few-shot examples as indivisible semantic units through phase separation, delivering 9-18% accuracy gains and 11% latency reduction.
-
Akashic: A Low-Overhead LLM Inference Service with MemAttention
Akashic’s MemAttention plus locality-aware placement improves agent task accuracy by up to 10.2 points and throughput by up to 1.21× over prior memory systems across four long-horizon workloads.
-
CARE: Counselor-Aligned Response Engine for Online Mental-Health Support
CARE fine-tunes LLMs on counselor-validated crisis dialogues to produce responses with stronger semantic and strategic alignment to expert standards than general-purpose models in Hebrew and Arabic.
-
Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)
SSAS improves LLM sentiment prediction consistency and data quality by up to 30% on three review datasets via syntactic and semantic context assessment summarization.
-
From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.
-
Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs
wSSAS is a two-phase deterministic framework that uses hierarchical text organization and SNR-based feature prioritization to improve clustering integrity, categorization accuracy, and reproducibility when applying LLMs to large review datasets.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.