DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval

• URL: http://arxiv.org/abs/2607.26418v1
• Date: Wed, 29 Jul 2026 03:03:03 GMT
• Title: DIRECTOR: Dynamic Index-based Recommendation with Transport-Optimized Retrieval
• Abstract summary: Reranking is a decision problem that aims to select and order a high-utility slate from a request-specific candidate set.<n>We propose Dynamic Index-based RECommendation with Transport-d Retrieval, a transport-guided parallel reranking framework.<n>Experiments demonstrate that DIRECTOR consistently outperforms strong reranking baselines.
• Score: 47.419173509430834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reranking is a combinatorial decision problem that aims to select and order a high-utility slate from a request-specific candidate set. A major line of generative rerankers adopts autoregressive (AR) models, which construct the slate one position at a time to capture inter-position dependencies. However, under practical greedy or bounded-width decoding, prefix-based search may prematurely prune globally promising permutations and incurs inherently sequential latency, restricting the effective search space under a fixed serving budget. Non-autoregressive (NAR) alternatives alleviate this efficiency bottleneck through position-parallel prediction, but naive position-wise factorization treats different positions too independently, leading to insufficient cross-position coordination and potentially duplicate or conflicting item selections. To retain parallel efficiency while introducing global structural coordination, we propose Dynamic Index-based RECommendation with Transport-Optimized Retrieval (DIRECTOR), a transport-guided parallel reranking framework. DIRECTOR maps candidate items into a continuous latent space and generates request-conditioned dynamic retrieval indices for all target positions in parallel. During training, it uses entropy-regularized OT to provide conflict-aware supervision; at inference, it directly performs global hard matching on similarity matrix, producing duplicate-free slates without iterative transport. To further align the generator with an opaque list-wise evaluator that returns only a scalar utility, we introduce a prefix-anchored credit assignment mechanism that converts the global reward into position-specific training signals. Extensive offline and online experiments demonstrate that DIRECTOR consistently outperforms strong reranking baselines, achieving significant improvement in large-scale industrial recommendation scenarios.

Related papers

• SWIM: Step-Wise Integrated Measure for Session-supervised List Evaluation in Generative Re-ranking [50.941707269747866]
  We propose SWIM, a list-level evaluator that models user behaviors as a finite-horizon prefix session-level survival process.<n>We show that SWIM significantly outperforms baselines in listwise reranking tasks, yielding substantial improvements in overall recommendation engagement.
  arXiv  Detail & Related papers  (2026-08-25T19:57:48Z)
• EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment [57.08595331216049]
  Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the shared token space.<n>Recent attempts have introduced Multi-Token Prediction (MTP), yet they primarily inherit its efficiency merit, leaving its potential as dense supervision unexplored.<n>We propose EchoRec, which empowers MTP with cycle-consistent holistic preference alignment across multi-horizon for generative recommendation.
  arXiv  Detail & Related papers  (2026-08-14T06:59:12Z)
• Unifying Generative Recall and Multi-Objective Ranking in a Single Decoder-Only Sequence [26.231002784432842]
  generative recall and ranking scaling share a common Transformer-based modeling philosophy.<n>We propose textbfUniR$2$, a textbfUnified decoder-only Transformer that unifies Generative textbfRecall and Multi-Objective textbfRanking.
  arXiv  Detail & Related papers  (2026-07-27T13:47:38Z)
• TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning [52.67756371231985]
  Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models.<n>We introduce Tree Rollout Allocation for Contrastive Exploration (TRACE), a unified rollout allocation framework.<n>Technically, TRACE allocates rollout budget to both prompt roots and intermediate prefixes that are most likely to yield mixed terminal rewards.
  arXiv  Detail & Related papers  (2026-06-09T17:16:03Z)
• Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval [0.0]
  Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding their responses in external knowledge.<n>This paper presents an Agent-Orchestrated Adaptive RAG framework that introduces dynamic query decomposition, iterative retrieval, and a bounded self-reflective evaluation loop.
  arXiv  Detail & Related papers  (2026-06-04T03:38:46Z)
• Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt Optimization [10.37712840622514]
  Multi-Agent Systems (MAS) empower Large Language Models to tackle complex reasoning computation tasks.<n>Existing black-boxs struggle to attribute trajectory-level failure to specific local components.<n>We argue that tractable MAS optimization needs structural inductive biases to disentangle error signals.
  arXiv  Detail & Related papers  (2026-05-28T16:57:57Z)
• F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking [79.49893545611779]
  Large Language Models (LLMs) can generate a subset and order it within a single autoregressive pass.<n>This flexibility introduces a new optimization challenge: the model must search an output space while receiving utility feedback only after the full ranked list is generated.<n>This credit assignment gap makes end-to-end optimization unstable and sample-inefficient.<n>We propose a unified framework that performs both within a single autoregressive rollout and optimize them end-to-end via factorized group-relative policy optimization.
  arXiv  Detail & Related papers  (2026-05-13T04:52:33Z)
• From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space [50.72071213515985]
  GloRank is a generative framework that shifts reranking from selecting local indices to generating global identifiers.<n>We show that GloRank consistently outperforms state-of-the-art baselines and achieves superior robustness in cold-start scenarios.
  arXiv  Detail & Related papers  (2026-04-28T06:57:00Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Embed Progressive Implicit Preference in Unified Space for Deep Collaborative Filtering [13.24227546548424]
  Generalized Neural Ordinal Logistic Regression (GNOLR) is proposed to capture the structured progression of user engagement.<n>GNOLR enhances predictive accuracy, captures the progression of user engagement, and simplifies the retrieval process.<n>Experiments on ten real-world datasets show that GNOLR significantly outperforms state-of-the-art methods in efficiency and adaptability.
  arXiv  Detail & Related papers  (2025-05-27T08:43:35Z)
• Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation [127.6168183074427]
  We propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data of the target environments. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation.
  arXiv  Detail & Related papers  (2021-12-13T13:19:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.