On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rerankers

Compact instruction-following rerankers are attractive for deployment, but conventional distillation pipelines typically train students by offline imitation of teacher outputs on a fixed set of examples, constraining supervision to the teacher's observed ranking space. We revisit reranker distillation through the lens of reinforcement learning. We propose a two-stage framework combining off-policy teacher optimization with on-policy student distillation. In Stage 1, a 4B teacher reranker is strengthened with off-policy GRPO using LLM-judge feedback on 88K instruction-following examples. In Stage 2, a compact 1B student samples rankings from its own policy and receives soft teacher-derived rewards on those rankings, coupling student exploration with knowledge transfer. Our strongest gains appear under distribution shift. On MAIR-11, the original 11-subset, 869-query evaluation, the proposed student reaches 0.7670 nDCG@6, outperforming offline listwise KD by +4.6 points. Controlled comparisons against offline pairwise RankNet KD and on-policy GKD show that neither changing the offline distillation objective nor moving teacher-distribution matching on-policy reproduces the performance of reward-based on-policy distillation over student-sampled rankings. The advantage persists on MAIR-Full: across all 126 tasks and 9,356 queries, the proposed method obtains the highest task-macro point estimates among the evaluated distillation variants, reaching 0.6808 nDCG@6 and 0.7865 MRR@6. It also exceeds two released 7B RL-trained rerankers on the comparable MAIR-11 evaluation, while the same Stage 2 training procedure consistently improves three architecturally distinct alternative student backbones. On the 9,861-query validation benchmark, the resulting 1B reranker achieves 0.7624 nDCG@6 while providing a favorable quality-efficiency tradeoff relative to larger alternatives.

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Retrieval is the first stage of modern search and advertising systems, selecting a candidate set from a large item universe for downstream ranking and auction. Recent work increasingly leverages LLMs to improve retrieval through query expansion, data synthesis, and retrieval-feedback training. However, the generative component is typically used for query-side augmentation, while final matching is still delegated to a downstream retriever. We introduce CoGR, a retrieval framework that instead trains LLMs to directly construct retrieval representations on both query and item sides. Each generator produces a compact set of keywords, which are matched directly through an inverted index, preserving compatibility with existing keyword-based retrieval infrastructure. CoGR uses a two-stage training pipeline. Supervised fine-tuning first establishes an aligned keyword space, after which co-evolving reinforcement learning alternately optimizes the query- and item-side generators with GRPO against the opposite side's frozen index. Both sides optimize the same query-to-item retrieval $F_1$ objective: the query side receives retrieval $F_1$ directly, while the item side receives a counterfactual marginal reward measuring the change in query-side $F_1$ caused by its generated keywords. Across 10 representative sparse, dense, and generative baselines, CoGR achieves the best performance on both an internal APP Marketplace dataset and the public WANDS benchmark, improving $F_1$ over the strongest baseline by $10.9\%$ and $36.1\%$, respectively. Further analysis shows stable co-evolution and increasingly aligned query--item keyword spaces over training.

SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation

Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured sequential generation remains challenging. This challenge is particularly evident in out-of-town (OOT) POI sequence generation, where a model must infer transferable travel intent from a user's hometown behaviors, adapt to cross-city interest drift, and generate a coherent destination trajectory under structural constraints. Existing approaches either rely on latent ID-based transfer with limited interpretability or directly use LLMs for sequence generation without explicitly grounding inferred semantics into position-aware predictions. To address this gap, we propose SemPOI-RL, a framework that aligns LLM semantic reasoning with structured sequence generation for interpretable OOT recommendation. Specifically, we first fine-tune an LLM to infer destination-oriented travel styles from users' hometown trajectories, using natural language as an interpretable semantic intermediate. We then introduce a Semantic POI Alignment Module (SPAM) to ground these inferred styles into a style-conditioned masked autoencoder for position-aware trajectory generation. Finally, we apply reinforcement learning with recommendation-oriented rewards to align LLM-generated styles with downstream sequence quality. Experiments on two real-world datasets show that SemPOI-RL consistently outperforms both traditional recommenders and direct LLM baselines, while providing interpretable style attribution across different phases of a trip. The code is available at https://github.com/Wind-Flipped/SemPOI-RL .

Difficulty-Aware Semantic-ID Optimization for Generative Recommendation

Semantic-ID-based generative recommendation casts retrieval and ranking as autoregressive generation over hierarchical item identifiers. A common recipe is SFT followed by GRPO, yet vanilla GRPO is poorly matched to this tree-structured task. Under the frozen SFT checkpoint, the exact target is absent from the first 16 candidates of the 50-beam constrained ranking for many prompts, and in harder cases none of these candidates enters the target SID branch. This prompt-level diagnostic motivates a training concern: when on-policy GRPO groups are similarly target-missing, item-level rewards may produce weak or degenerate reward variation even if some candidates follow part of the target path. We propose Difficulty-Aware Semantic-ID Optimization (DASO), a tree-aware post-training method that addresses this failure mode as an online rollout-allocation problem. Instead of using fixed difficulty buckets or uniformly injecting ground-truth completions, DASO profiles each current rollout group by prefix-match depth, locates the bottleneck SID levels where candidates leave the target path, and reallocates a bounded portion of the group to prefix-guided completions while retaining raw rollouts for contrast. A SID-prefix reward provides graded credit, while an auxiliary SFT anchor mitigates regression on examples already solved by the SFT checkpoint. On the public benchmarks, DASO improves over MiniOneRec-style GRPO on 11 of 12 metrics and achieves the best result on 9 of 12 metrics; it also improves most level-wise recall metrics on the internal recommendation task.

Training Documents Reranker with Search Rubrics for Deep Research Agent

Retrieval systems help deep research agents generate high-quality answers by providing relevant documents. However, existing retrievers typically select documents through relevance matching, while individually well-matched top-$k$ documents may not form a \textit{set} that satisfies the complex information needs of an agent query (\eg, diverse, concise and authoritative documents). In this paper, we propose search-oriented rubrics that \textit{explicitly} define the requirements that high-quality document sets should satisfy for each agent query. Our search rubrics are organized into a hierarchical structure and synthesized using a powerful LLM. Based on these search rubrics, we further train a document reranker \textbf{RubricRanker} to select a high-quality subset from retrieved documents. We design a two-stage training framework that consists of rubrics-guided supervised fine-tuning and rubric-based reinforcement learning. Extensive experiments demonstrate that RubricRanker outperforms the strongest baseline by 2.6 points on four deep research benchmarks and generalizes well to five RAG benchmarks.

SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task

Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons. However, training effective search agents remains challenging due to the lack of scalable and long-horizon tasks, and the difficulty of evaluating and correcting intermediate reasoning and tool-use behaviors. We introduce SearchArt, a scalable framework for training long-horizon search agents through verification-driven task synthesis and a multi-stage post-training pipeline. SearchArt constructs large-scale datasets for complex search-, research- and user-oriented tasks by synthesizing diverse information-seeking QA pairs and corresponding search trajectories from web documents and automatically generated evidence graphs. To ensure the reliability of the synthesized data, we design a verification pipeline that jointly evaluates QA consistency, trajectory quality, and the relevance of retrieved evidence. The verified trajectories are subsequently used in a multi-stage training process comprising supervised fine-tuning and reinforcement learning-based policy optimization. Search agents trained with SearchArt exhibit adaptive search planning, iterative evidence aggregation, and complex reasoning over extended interaction horizons. Experimental results demonstrate that, with only (Qwen3.5-) 27B parameters, SearchArt scores 74.39 on BrowseComp-ZH, 70.06 on BrowseComp, and 52.55 on Deepresearch-bench, matching or surpassing frontier closed-source agents on both deepsearch and deepresearch benchmarks.

SalesLoop: Reinforcement Learning from Performance Feedback for Sales Lead Ranking

Lead ranking in Customer Relationship Management (CRM) systems faces a persistent challenge: models achieving high offline accuracy often underperform in production. We identify three fundamental gaps responsible for this disconnect: offline-online metric mismatch, pointwise-listwise objective misalignment, and temporal distribution drift. To address these gaps, we propose SalesLoop, a reinforcement learning framework that establishes a closed feedback loop between model predictions and real-world business outcomes. Our approach introduces (1) a performance-aware reward that encodes conversion outcomes weighted by ranking position and conversion velocity, and (2) Discriminative GRPO, a listwise optimization objective that adapts Group Relative Policy Optimization to discriminative ranking models. SalesLoop improves NDCG@K by +7.9\% and P@K by +15.8\% over the strongest static baseline. A 160-day production A/B test at a New Energy Vehicle manufacturer, spanning 16.5M leads and 280 sales specialists across two provincial markets, validates statistically significant cumulative lift of +4.7\% ($p=0.047$) and +8.7\% ($p=0.002$). In production, the ranking backbone achieves Top-10\% recall of 44.1\% and surfaces high-intent leads at $2.3\times$ the conversion rate of specialist baselines.

Tool-Adaptive LLM Reranker

Generative Large Language Models (LLMs) have revolutionized information retrieval, yet their strictly parametric nature frequently leads to severe factual hallucinations when confronted with complex queries beyond their epistemic boundaries. While external tool-calling can mitigate this, indiscriminately invoking search tools for every document during reranking incurs prohibitive latency overheads, creating an intractable accuracy-efficiency dilemma. To address this challenge, we propose TALRanker, a novel framework that formalizes pointwise relevance scoring as an agentic Markov decision process. We optimize it via a two-stage training paradigm. An initial warm-up utilizes a language-preserving hybrid loss to prevent the catastrophic forgetting of native generative capacities. Subsequently, an asymmetric cost-aware reward equipped in reinforcement learning forces the policy to autonomously bypass tools for maximum efficiency when confident, while selectively retrieving external evidence to avert severe hallucination penalties when uncertain. Extensive evaluations demonstrate that TALRanker achieves state-of-the-art performance across standard and reasoning-intensive retrieval benchmarks, matching throughput with pointwise rerankers while outperforming parameter-heavy reasoning models.

Large Behavior Model: A Promptable Digital Twin of the Retail Customer

Customer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data. We present the Large Behavioral Model (LBM) that learns customer decision making directly from large-scale retail transactions through a unified Person-Environment formulation. Customer state is represented by a behavioral profile derived from historical purchases, while product context is incorporated through retrieval-augmented generation. The model is trained using continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards for evidence-based calibration. We evaluate the proposed framework on purchase prediction, hard-negative discrimination, basket completion, promotion response, and cross-domain voucher redemption. The model consistently outperforms frontier general-purpose language models on in-domain retail tasks while demonstrating strong zero-shot and fine-tuned transfer across retailers and decision domains. Ablation studies show that continued pre-training is the primary driver of behavioral generalization, retrieval is most effective when applied during both training and inference, and reinforcement learning improves reliance on explicit behavioral evidence over generic language-model priors. These results demonstrate that behavioral knowledge encoded in transaction histories can be effectively learned by language models, providing a scalable foundation for customer digital twins and behavior simulation.

GR2 Technical Report

Industrial recommendation systems serve billions of users through a multi-stage funnel -- retrieval, early-stage ranking, and re-ranking -- where the final re-ranking step disproportionately shapes user engagement and downstream performance, particularly for carousel and grid display formats. Despite growing enthusiasm for Large Language Models (LLMs) in recommendation, three gaps hinder industrial adoption: (1) most efforts target retrieval and ranking, leaving re-ranking -- the stage closest to the final user experience -- largely underexplored; (2) LLMs are typically deployed zero-shot or via supervised fine-tuning, underutilizing the reasoning capabilities unlocked by reinforcement learning (RL) on verifiable rewards; (3) deployed catalogs index billions of items with non-semantic identifiers that lie outside any base-LLM vocabulary. We present GR2 (Generative Reasoning Re-Ranker), an end-to-end framework that combines (i) mid-training on semantic IDs produced by a tokenizer with >=99% uniqueness, (ii) reasoning-trace distilled from a stronger teacher via targeted prompting and rejection sampling, and (iii) RL with verifiable rewards purpose-built for re-ranking. To make GR2 resource-viable, we further (iv) introduce a context compressor that amortizes training cost, On-Policy Distillation (OPD) as a scalable alternative to SFT -- which we find collapses at industrial scale -- and reasoning distillation for low-latency serving. GR2 delivers +18.7% R@1, +7.1% R@3, and +9.6% N@3 over legacy baselines on industrial-scale traffic. We further find that reward design is critical in re-ranking: LLMs often hack rewards by preserving the incoming order or exploiting position bias, motivating conditional verifiable rewards as essential industrial components.

NEXT: Reasoning-Driven Video Recommendation via a Vision-Language Model

We present NEXT (Next-interest EXploration Transformer), a reasoning-driven video recommendation framework that reasons over the video a user has just watched, infers the viewer's next intent, and retrieves concrete follow-up videos. Explicit continuations such as episodes are linked directly; implicit cases are handled by generating intent queries and searching for matching candidates. This Item-to-Intent-to-Item formulation produces directed recommendations beyond co-engagement correlation or semantic similarity. To make this framework reliable at scale, we train NEXT-8B, a purpose-trained 8B vision-language model with a three-stage recipe: Perception-Enhanced Reinforcement Learning for query-agnostic evidence extraction, Distribution-Aligned Supervised Fine-Tuning over real and synthetic visual QA mixtures, and Group Relative Policy Optimization for last-mile alignment. NEXT-8B achieves the best single-model DocVQA performance, ranking second overall only behind a multi-agent system while surpassing a substantially larger 200B+ scale model, and improves next-intent logic-wise quality by 3.3% over the base model in a task-specific LLM-as-a-judge evaluation. We deploy NEXT as an additional retrieval path in a large-scale social media recommendation system and observe statistically significant production gains, including +0.53% watch time and +0.51% distinct video exposure. Overall, NEXT shows that a carefully trained compact vision-language model can serve as a practical reasoning engine for next-interest exploration at production scale.

MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS

Unhealthy dietary behavior continues to be a persistent public health issue in the United States, exacerbated by recommendation systems that prioritize user preference without considering nutritional health. The Multi-Objective Personalized Interpretable Health-aware Food Recommendation System (MOPI-HFRS), from which this work extends, addresses this by jointly optimizing preference, health, and diversity through Pareto-based optimization. However, this approach relies on static, per-step tradeoff solutions that fail to capture the sequential nature of dietary decision-making. We introduce MORL-A2C, a sequential decision-making extension to MOPI-HFRS targeting the health-preference axis. Leveraging frozen GNN embeddings, MORL-A2C formulates recommendation as a K-step reranking problem using an Advantage Actor-Critic algorithm with a scalarized relevance/health reward. The policy is warm-started via behavior cloning against a dot-product ranker derived from frozen embeddings. We also identify and correct a non-trivial bug in the MOPI-HFRS evaluation pipeline that understated baseline performance; all results are reported against the corrected baseline. On the macro-nutrient benchmark, MORL-A2C achieves a modest reduction in ranking quality (Recall@20: 25.64% to 23.61%, NDCG@20: 23.52% to 20.64%) in exchange for a substantial improvement in health alignment (H-Score@20: 46.05% to 69.57%), with consistent trends on the full-nutrient benchmark. These findings validate that policy-driven sequential optimization can effectively navigate the health-preference trade-off in multi-objective food recommendation.

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

Retrieving external knowledge is essential for solving real-world tasks, yet it remains challenging when the relationship between a query and its relevant knowledge involves implicit and complex reasoning beyond surface-level semantic or lexical matching (e.g., mathematical problems relying on the same theorem or coding requiring deep reasoning). Existing approaches primarily rely on query-side reasoning (e.g., query rewriting), which introduces significant online latency and underutilizes the opportunity to perform reasoning over the knowledge corpus itself (i.e., index-side reasoning). In this paper, we propose RL-Index, an agentic indexing framework that formulates retrieval index reasoning as a reinforcement learning problem. Instead of performing reasoning at query time, RL-Index shifts reasoning to the indexing stage by augmenting documents with LLM-generated rationales that explicitly encode the latent query-knowledge relationship. To optimize the quality of these rationales, we employ Group Relative Policy Optimization (GRPO) and use retrieval similarity as a verifiable reward signal, enabling direct optimization of indexing decisions for retrieval effectiveness. Extensive experiments on the BRIGHT benchmark demonstrate that RL-Index consistently improves both retrieval and downstream question-answering performance, while significantly reducing online inference latency. Moreover, the learned rationale augmentation generalizes across diverse retrievers and generators, highlighting its robustness as a plug-and-play indexing strategy across different retrieval systems.

Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training

The use of GRPO-style algorithms has become the standard strategy for training LLM search agents under outcome-only rewards. With these algorithms, a query contributes to parameter updates only when its rollout group mixes successes and failures; all-correct (too-easy) and all-incorrect (too-hard) groups are zero-variance and waste rollout cost. Existing approaches treat zero-variance as a static property and either discard or pre-filter such groups. We hypothesize and empirically validate that queries flip between zero-variance and signal-bearing states as the policy evolves during training. Building on this intuition, we propose query recycling, which returns zero-variance groups to a mutable pool for future resampling, so that the effective training distribution co-evolves with the policy. With the proposed technique, a 1.7B parameter model trained on synthetic data can reach 66.0 average Pass@1 accross seven multi-hop QA benchmarks, matching or surpassing systems with up to 7B parameters trained on benchmark-derived supervision. Analysis of recycling patterns shows that recycled queries supply roughly three quarters of the effective batch by the end of training, with contributions split between recovery from policy improvement and policy drift.

Adaptive Loss Balancing for Noise-Robust GRPO in Generative Recommendation

Reinforcement learning (RL) presents a promising avenue for enhancing generative recommendation beyond supervised imitation, leveraging reward signals to guide policy improvement. However, its efficacy is critically contingent on the trustworthiness of the reward model for the samples it evaluates. In practice, production rankers, the widely adopted reward models, are trained on exposure-biased logs, leading to sample-dependent inaccuracies that violate this assumption. Our stratified analysis uncovers a consistent pattern: reward guidance is most beneficial when the policy exhibits uncertainty and the ranker can effectively discriminate the ground-truth item from rollout negatives. On other samples, the reward signal is either negligible or detrimental, highlighting the risk of uniform RL application. To address such an issue, we introduce AdaGRPO, a novel framework that treats reward-guided optimization as selective admission rather than uniform pressure. Training is anchored in supervised negative log-likelihood, while the GRPO objective is gated by a binary, per-sample clip determined by two rollout diagnostics: policy-side difficulty and reward discriminability. Instances failing either diagnostic default to pure supervision, ensuring stability and mitigating the amplification of noisy gradients. We validate AdaGRPO on a large-scale e-commerce dataset. At the best intermediate checkpoint, it elevates HR@10 from 11.01% to 12.18% while constraining hallucination below 0.22%, and maintains robustness at the final checkpoint (HR@10 11.63%, hallucination 0.27%), outperforming fixed NLL--GRPO mixtures across the retrieval--validity frontier. In production A/B tests, AdaGRPO achieves statistically significant gains in click-through rate and dwell time, confirming its practical utility.

OneReason Technical Report

Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the reasoning-style ``think before answer'' paradigm in the LLM field, we conduct preliminary studies (i.e., OneRec-Think, OpenOneRec) to explore reasoning capability in generative recommendation. Nevertheless, we notice an unexpected phenomenon: the thinking mode does not show advantages over the non-thinking mode. Drawing insights from recent findings on CoT robustness in multi-modal language models, we argue that effective reasoning in recommendation rests on two factors: perception, the ability to ground itemic tokens in their underlying language semantics, and cognition, the ability to reorganize a user's behavior sequence into coherent latent interest points. We therefore propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL to enhance the thinking ability.

QueryAgent-R1: Bridging Query Generation and Product Retrieval for E-Commerce Query Recommendation

Query recommendation in e-commerce search aims to proactively suggest queries that match users' potential interests. However, existing methods mainly optimize query-level relevance, while neglecting whether the retrieved products align with users' downstream preferences. This mismatch often leads to high query click through rates (CTR) but low product conversion rates (CVR). To bridge this gap, we propose QueryAgent-R1, a memory-augmented agentic framework that improves end-to-end alignment via chain-of-retrieval optimization. Our QueryAgent-R1 grounds query generation in real inventory retrieval, allowing the agent to validate and refine queries based on retrieved products. We also design a consistency reward in the agentic reinforcement learning (RL) process to jointly optimize query relevance and downstream engagement. In addition, we construct a memory abstraction module for efficient user profiling. To support offline evaluation, we construct two datasets based on both proprietary industrial data and public datasets, on which QueryAgent-R1 consistently outperforms strong baselines. Moreover, on a large scale production platform, QueryAgent-R1 improves Query CTR by 2.9% and guided CVR by 3.1% in online A/B tests.

Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation

Scaling recommender systems via large language models (LLMs) has become a prominent trend in the industry. However, aligning the LLM's semantic space with the recommender's ID space via post-training (e.g., SFT and RL) remains challenging. Existing LLM4Rec paradigms are bottlenecked by two main issues: (1) the difficulty of measuring and improving chain-of-thought (CoT) quality in open-domain recommendation during SFT, and (2) the neglect of the trade-off between LLM semantic rewards and recommendation preference rewards during RL alignment. Inspired by these challenges, we present Taiji, a novel LLM-as-Enhancer framework designed for industrial recommender systems. To overcome the SFT bottleneck, we utilize reverse-engineered reasoning and open-ended rejection sampling to generate high-quality, domain-specific CoT data. To resolve the RL alignment issue, we propose Pareto Optimal Policy Optimization (POPO), which adaptively adjusts cross-domain reward weights. Theoretically, it achieves an optimal trade-off between the semantic world knowledge of LLMs and the collaborative ID features representing online user preferences. Extensive offline evaluations and online A/B tests validate the effectiveness of Taiji. Deployed on Kuaishou's advertising platform since May 2026, Taiji currently serves over 400 million users daily, yielding significant commercial revenue and demonstrating its robust scalability in web-scale environments.