arXiv Computation and Language
LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
1d ago
Latent Abstraction for Retrieval-Augmented Generation
arXiv:2604.17866v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has become a standard approach for enhancing large language models (LLMs) with external knowledge, mitig...
arXiv AI
Jun 16
Latent Thought Flow: Efficient Latent Reasoning in Large Language Models
arXiv:2606. 16222v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decoded into tokens, causing high inference overhead.
arXiv AI
Aug 17
Retrieval Grounding Latent Reasoning for Dense Retrieval
arXiv:2608. 14107v1 Announce Type: new Abstract: Reasoning-intensive retrieval requires text representations to capture not only semantic similarity, but also the reasoning needed to determine relevance under a given retrieval instruction.
arXiv AI
Oct 9
From Chain-of-Thought to Loops: Non-Autoregressive Latent Reasoning via Looped Transformers
The paper introduces LLoCoT, a looped latent‑reasoning framework that replaces the traditional left‑to‑right generation of chain‑of‑thought tokens with iterative refinement of a compact latent workspace using a shared transformer. By jointly updating latent slots over a few iterations and sampling latent tokens in parallel, LLoCoT feeds these into an autoregressive decoder for answer generation. Experiments on HumanEval and MBPP show that LLoCoT matches or surpasses explicit‑CoT baselines while dramatically reducing reasoning latency and increasing throughput.
arXiv AI
Jul 14
GRASP: GRanularity-Aware Search Policy for Agentic RAG
arXiv:2607. 10463v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers.
arXiv AI
Aug 17
Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
arXiv:2608. 13570v1 Announce Type: cross Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings.