Towards Data Science
Jun 30
Context Engineering for RAG: The Four Typed Inputs Behind Every Answer
Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.
Proxy-Pointer RAG: Temporal Reasoning Without Semantic Precompilation
A technical comparison of Proxy-Pointer and LLM-Wiki The post Proxy-Pointer RAG: Temporal Reasoning Without Semantic Precompilation appeared first on Towards Data Science .
Related stories
Towards Data Science
Jun 30
Context Engineering for RAG: The Four Typed Inputs Behind Every RAG Answer
Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.
Towards Data Science
Jun 30
Context Engineering for RAG : The Four Typed Inputs Behind Every RAG Answer
Enterprise Document Intelligence [Vol. 1 #7bis] - Tobi Lütke and Andrej Karpathy named the practice in 2025.
arXiv AI
Aug 18
STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering
arXiv:2608. 16224v1 Announce Type: cross Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question formulations without task-specific training.
Towards Data Science
Jul 10
RAG Was Always a Temporary Workaround. What is Next?
Vector databases are a temporary bridge. Discover why the next AI infrastructure revolution relies on persistent neural state and strict latency budgets, not on vector databases.
arXiv AI
Jul 14
PRISM Edit: One Vector for All Temporal Answers
arXiv:2607. 11327v1 Announce Type: cross Abstract: Model editing keeps large language models (LLMs) up to date without retraining, but temporal facts expose a limitation of the prevailing locate-and-edit paradigm: an update is not always a replacement.
arXiv AI
Sep 15
Towards a Mechanistic Understanding of Propositional Logical Reasoning in Large Language Models
The paper investigates how large language models perform propositional logical reasoning by conducting a causal mechanistic analysis on the PropLogic-MI benchmark. It identifies four interlocking mechanisms—Staged Computation, Information Transmission, Fact Retrospection, and Specialized Attention Heads—that organize the reasoning process across layers. The study demonstrates that these mechanisms recur across different model families, rule categories, and reasoning hops, indicating a structured, layer‑organized internal process for propositional reasoning.
arXiv AI
Jul 22
Fluid Reasoning Representations
arXiv:2602. 04843v2 Announce Type: replace Abstract: Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking.
arXiv AI
Aug 11
SodaMem: Evidence-Grounded Temporal Graph Memory for LLM Agents
arXiv:2608. 08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said.
arXiv AI
Aug 6
MemSIF: From Structured Interactions to Dual-Track Fact Memory for LLM Agents
arXiv:2608. 01742v2 Announce Type: replace Abstract: Long-term memory is critical for LLM agents operating over long-horizon interactions.
arXiv AI
Sep 1
post-graph-rag: A PostgreSQL-Native Bi-Temporal Graph RAG Engine with Temporal Grounding at Synthesis
post-graph-rag is an open‑source PostgreSQL‑native engine that unifies chunks, embeddings, a canonical entity graph, and community summaries in a single database, using pgvector for search and edge tables for traversal. It validates extraction output—rejecting vague predicates, normalising predicates, resolving entities to unique vertices, and flagging negations—before writing, and employs a bi‑temporal layer to record when a relation held and when the system believed it, superseding incompatible earlier assertions. In benchmarks against LightRAG, it builds denser, more queryable graphs and achieves higher scores on LongMemEval, largely due to its temporal grounding in prompts.
arXiv Machine Learning
Jul 21
Right Knowledge, Wrong Answer: Characterizing Parametric Temporal Conflict in Open-Weight Language Models
arXiv:2606. 20959v2 Announce Type: replace Abstract: Language models may encode both outdated facts and their newer replacements.