REVIEW 8 cited by
ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Large language models (LLMs) with memory are computationally universal. However, mainstream LLMs are not taking full advantage of memory, and the designs are heavily influenced by biological brains. Due to their approximate nature and proneness to the accumulation of errors, conventional neural memory mechanisms cannot support LLMs to simulate complex reasoning. In this paper, we seek inspiration from modern computer architectures to augment LLMs with symbolic memory for complex multi-hop reasoning. Such a symbolic memory framework is instantiated as an LLM and a set of SQL databases, where the LLM generates SQL instructions to manipulate the SQL databases. We validate the effectiveness of the proposed memory framework on a synthetic dataset requiring complex reasoning. The project website is available at https://chatdatabase.github.io/ .
Forward citations
Cited by 8 Pith papers
-
MemTX: Transactional Belief Commit for Stateful Agent Memory
Staging agent-memory writes through a validate-and-commit pipeline with maturity-gated irreversible actions and typed cascading repair yields zero realized downstream harm on five LLM backbones, where eight baselines ...
-
ConsistencyGate: Preventing Memory Contamination in LLM Agents via Self-Consistency Admission Control
A self-consistency admission gate that verifies facts against their source context before writing them to LLM agent memory reduces memory contamination on three planted-corruption benchmarks.
-
AgentMemBench: A Systematic Benchmark for Evaluating Long-Term Memory Management Strategies in Conversational AI Agents
A benchmark comparing five memory strategies for conversational agents on three public datasets finds dense vector retrieval alone maintains long-range recall, at roughly 25 times the token cost of recency windows.
-
G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
G-Memory stores past multi-agent teamwork in a three-tier graph and retrieves it to boost performance on five benchmarks.
-
Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs
Graph-based action memory with dual-stream TD learning improves best-of-N inference scaling for LLM agents, reporting +20.81% success / +6.17% progress over vanilla baselines.
-
SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
SEAL parses conversational questions by extracting a minimal S-expression core, calibrating it against the knowledge graph, and completing it with templates, reporting large gains over KB-Binder on SPICE but not over ...
-
Can Past Experience Accelerate LLM Reasoning?
LLMs can cut reasoning compute by up to 56% on similar questions when memory of past correct solutions is combined with adaptive early stopping, though the benchmark is small and synthetic.
-
Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities
A systematic review organizing LLM-based text-to-SQL methods into pre-processing, in-context learning, fine-tuning, and post-processing paradigms, with a catalog of datasets, metrics, challenges, and future directions.
Discussion (0). Continue with ORCID to comment.