The paper introduces LatentRec, a framework that replaces inference-time chain-of-thought reasoning in large language model (LLM) recommender systems with training-time per-step supervision. It employs a 2.5 M-parameter Continuous Thought Module, Soft Token Selection, and a Per-step Reasoning Loss to guide intermediate hidden states toward the target semantic ID. After training, the module can be removed, yielding a 4–5 % relative improvement in HR@10 on Amazon benchmarks while reducing inference latency by 18.3×.
LLM-based recommender systems increasingly generate chain-of-thought (CoT) text before each item prediction to activate the LLM's reasoning capacity, costing tens to hundreds of extra tokens per recom...
arXiv:2607.26621v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their use as the backbone of foundation recommendati...
arXiv:2607. 26621v2 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs).
arXiv:2607. 16972v1 Announce Type: new Abstract: Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations.
arXiv:2606. 14142v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge.
arXiv:2606. 16360v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead.
LLMAR is a tuning‑free recommendation framework designed for sparse, text‑rich industrial B2B domains. It transforms user behavioral history into structured semantic motives using LLM inference, employs a reflection loop to self‑correct hallucinations, and operates cost‑effectively with asynchronous batch processing. Experiments on MovieLens‑1M, Amazon Prime Pantry, and a construction risk dataset show LLMAR surpasses state‑of‑the‑art learning models, achieving up to a 54.6% nDCG@10 improvement while keeping inference costs around $1 per 1,000 users.
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:2608. 10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often achieving higher accuracy than fast-thinking models that predict directly.
A*-Thought-V2 is a framework that models Chain-of-Thought reasoning as a geometric trajectory in a 3D PCA space, using explicit-implicit latent tokens to compress steps that deviate from the main question-to-solution direction. The method measures alignment angles to decide which steps remain text and which become latent, and introduces stepwise embedding forcing and label forcing to train the architecture. Experiments on Qwen models show up to 2.6% accuracy gains, halved response length, and significant reductions in computation and training time.
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.
LatentHarness unifies memory access and latent reasoning by treating them as sequential latent actions—THINK, RECALL, and EXIT—within a language model. It is trained via counterfactual policy distillation, which evaluates the impact of each action on the emitted token and learns when to recall evidence versus continue reasoning. On six long‑context reasoning benchmarks, a 1.4B‑parameter LatentHarness model outperforms the strongest baselines by 2.8% and 10.0% relative, while running 5.9× faster than the leading long‑context baseline.