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.

Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation

Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions, but this dependence creates a fundamental cold-start challenge when newly added content has no interaction history. In Tubi's production retrieval system, this challenge is further constrained by the serving interface: new content must be assigned a standalone embedding immediately, and the model must also produce device embeddings suitable for approximate nearest-neighbor retrieval. We address this setting by formulating cold-start recommendation as an inductive graph-completion problem on a temporal bipartite device-content graph. We propose Shallow-RHS, an asymmetric link-prediction architecture in which the left-hand side (LHS) device tower leverages temporally valid watch-history message passing to capture collaborative signals, while the right-hand side (RHS) content tower is intentionally shallow with respect to the graph and encodes content solely from intrinsic features. The RHS tower does not use ID-based embeddings, content-side subgraphs, neighbor aggregation, or interaction-derived representations, forcing the content encoder to map intrinsic features into a collaborative-filtering-aware embedding space. After training, the learned content encoder generates embeddings for both warm and newly ingested content, enabling implicit graph completion through retrieval of warm surrogate neighbors. We further extend the same representation-completion principle to device cold-start by constructing cohort-based embeddings from demographic features. Large-scale online experiments demonstrate consistent relative improvements in content cold-start engagement, promotion speed, impression acquisition, and device cold-start engagement.

The End of Software Engineering: How AI Agents Are Fundamentally Restructuring the Software Paradigm

For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents -- systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource -- constitutes not an incremental improvement but a fundamental restructuring of the software paradigm. Drawing on first-principles analysis of complexity scaling, we formalize the distinction between traditional software (where code is the carrier of decision logic) and agentic systems (where code is ephemeral tooling for an LLM-driven reasoning loop). We trace the historical arc from licensed software to SaaS to what we term Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users. We introduce the concept of Agentic Engineering as an emergent discipline -- distinct from software engineering in its core object of study, control model, and human role. Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models

Medical image segmentation is often framed as a search for stronger architectures, but this can obscure a more fundamental question: what does the dataset require from the model? In medical imaging, this requirement is shaped by foreground occupancy, morphology, boundary ambiguity, topology sensitivity, annotation quality, acquisition variation, and operating point. This paper introduces the Medical Segmentation Dataset Knowledge Card (MS-DKC), a framework for making these factors explicit. MS-DKC records dataset evidence through image/acquisition, morphology, supervision, context-dependence, and deployment-risk descriptors. These descriptors are mapped to failure modes, design priors, and risk-aligned criteria, making segmentation design more traceable than architecture-first comparison. We evaluate MS-DKC on DRIVE, ISIC2018, and ACDC, representing distinct regimes. DRIVE contains sparse, thin, branching vessels, favoring detail-preserving models, sensitivity-aware optimization, threshold analysis, and topology-aware metrics. DKC-TNet-v2 achieved Dice 0.8044 and IoU 0.6730 with 35103 parameters, while SA-UNetv2-DKC-AmbRef reached Dice 0.8141, IoU 0.6865, sensitivity 0.8265, specificity 0.9804, and AUC 0.9853. ISIC2018 involves compact but appearance-variable lesions; validation-constrained score-function selection on Att-Next-Topo/ATTNext produced MS-DKC-AttNextTopo-VCSF-NoAug with Dice 0.8872, IoU 0.8214, precision 0.9173, Boundary F1 0.4878, and ASSD 4.13, while plausible additions failed to improve the risk-aligned profile. ACDC provides a multi-class cardiac case, where MS-DKC recommends four-class softmax segmentation, class-balanced Dice/CE supervision, and class-wise surface evaluation. Overall, the results support dataset-conditioned design: different datasets require different priors, operating points, and evidence before a model can be judged appropriate.

Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads

LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to persistently store, retrieve, and update their own memory across sessions. A rich ecosystem of agent memory systems has emerged spanning flat retrieval, LLM-mediated extraction, consolidating fact stores, and agentic control flows. Yet, their system-level behavior remains uncharacterized. We present the first systems characterization of agent memory. First, we introduce a system-oriented taxonomy classifying agent memory systems along four axes. Second, we build a phase-aware profiling harness attributing cost to construction, retrieval, and generation. Third, we characterize ten representative systems across two benchmark suites, uncovering how design choices shift cost across the write and read paths. Finally, we derive 10 system recommendations covering construction scheduling, capability floors, amortization via query volume, freshness-latency tradeoffs, and fleet-scale management.

Rethinking Sales Lead Scoring with LLM-based Hierarchical Preference Ranking

Sales lead conversion in high-stakes domains (e.g., automotive, real estate) differs fundamentally from e-commerce recommendation due to prolonged decision cycles and multi-stage funnels. Traditional lead scoring methods rule-based scorecards, machine learning, or pointwise CTR models face severe challenges: sparse supervision, a semantic gap in unstructured CRM logs, and inability to capture relative lead priority. While Large Language Models(LLMs) offer superior semantic understanding of customer interactions, general-purpose LLMs are ill-suited for lead ranking: they generate text rather than comparable scores, and lack alignment with the hierarchical priorities of sales funnels. We introduce an LLM-based discriminative framework for sales lead scoring, which supports joint modeling of structured CRM features and unstructured customer interactions. On top of this framework, we propose HPRO (Hierarchical Preference Ranking Optimization), which augments sales lead scoring with a hierarchical preference ranking objective. HPRO employs a margin-aware Bradley-Terry formulation to transform sparse binary labels into dense, funnel-aware preference pairs, enabling lead scoring to leverage both pointwise and pairwise supervision. Experiments on large-scale data from a leading NEV brand demonstrate state-of-the-art classification (AUC 0.8161) and ranking performance (+39.7% precision among top-ranked leads). A 132-day online A/B test validates 9.5% sales volume uplift, confirming real-world commercial impact.

Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety

An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but untrusted AI agents under the oversight of a weaker, trusted monitor and a limited human audit budget. Control evaluations stress-test these protocols by pitting a red-team attack policy against the blue-team monitor, but current evaluations typically assume attackers that do not strategically select when to attack. We study this capability, attack selection, in agentic settings by decomposing attack decisions into a start policy, which decides when an attacker should attack, and a stop policy, which decides when an attacker should abort an ongoing attack. Across two agentic settings, BashArena and LinuxArena, both policies substantially lower measured empirical safety without changing the underlying attack capability. At a 1% audit budget, our start policy reduces safety by 20pp on both BashArena and LinuxArena, and our stop policy reduces safety by 20pp on BashArena and 28pp on LinuxArena. These reductions should be interpreted as upper bounds on the effect of attack selection. Existing control evaluations may therefore yield overly optimistic safety estimates against selective attackers. We recommend that future evaluations, system cards, and safety cases elicit attack selection to produce more realistic safety estimates.

Representation Curriculum: Stagewise Training for Robust Ranking and Allocation

Ranking in digital marketplaces is a dynamic exposure-allocation mechanism: displayed items shape discovery trajectories and success events logged by the platform to update future allocation policies. Modern ranking systems rely heavily on exposure-confounded signals (e.g. popularity estimates, CTR/CVR aggregates, and ID-based representation), because they are highly predictive under stationary demand. Yet this predictive power can become a learning shortcut: early access to exposure-dependent belief signals steers optimization toward over-reliance on them and away from exposure-independent merit signals (e.g., content-based competitiveness and semantic affinity). Consequently, the learned policy tends to entrench incumbents and degrade cold-start generalization and robustness under distribution shift. We propose Representation Curriculum (RC), a training-time intervention that temporally stages feature utilization. RC foregrounds content-based merit signals initially, then introduces exposure-dependent belief signals while anchoring the content pathway near the learned merit representation, curbing shortcut reliance on historical signals and mitigating gradient starvation on content signals. We formalize RC independently of task and hypothesis class and provide ranking-specific instantiations. In a Gaussian linear ridge setting, we derive closed-form solutions and sufficient conditions under which RC strictly reduces population risk on a cold-start target distribution, with a quantified Pareto tradeoff against source performance. Experiments on public learning-to-rank and recommendation benchmarks, and randomized online experiments in a large-scale e-commerce search system, show that RC measurably shifts reliance from historical belief signals toward content-based merit signals and yields consistent gains on cold populations with a controlled trade-off in head performance.

SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks

Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be dominated by repetitive behavior patterns. We identify this phenomenon as semantic state sink, where recurring semantics over-occupy the recurrent state and bias subsequent readouts. To mitigate semantic state sink, we propose SinkRec, a hybrid memory-transition looped architecture that decouples collaborative behavioral pattern storage from dynamic transition modeling. SinkRec externalizes recurring local patterns into a learnable conditional memory through residual vector quantization, reinjects the retrieved codes, and exposes memory key-value pairs to the attention block. It further introduces Temporal-Aware State-Relation Differential Gated DeltaNet (TDGD), which uses memory to purify recurrent writing and reading by suppressing memory-covered updates and removing memory-aligned readout responses. This design turns recurring semantics from state-competing signals into memory-retrievable patterns, allowing the recurrent state to focus on dynamic transitions and alleviating semantic state sink with linear-time efficiency. Experiments on public and industrial datasets demonstrate the effectiveness and efficiency of SinkRec.

Trading Engagement for Sustainability: Carbon-Aware Re-ranking for E-commerce Recommendations

E-commerce recommender systems strongly influence which products users consider and purchase, yet sustainability signals such as Product Carbon Footprint (PCF) are almost never available at catalog scale. We study carbon-aware product recommendation in the realistic setting where PCF labels are missing for most items and must be inferred. We first estimate product-level carbon footprints via a retrieval-augmented PCF estimation pipeline that transfers supervision from the Carbon Catalogue, a small set of life-cycle-assessed products, to a large unlabeled e-commerce catalog using semantic similarity search, few-shot LLM prompting, and a nearest-neighbour fallback. We then apply a carbon-aware post-hoc re-ranking strategy on top of relevance scores produced by three established recommendation models: BPR, NeuMF, and LightGCN. The method trades off predicted user-item engagement against estimated carbon footprint through a single tunable parameter, lambda. In this offline study, engagement is operationalized through Amazon review interactions, which serve as implicit feedback and as a proxy for user interest or purchase behavior. We evaluate the framework on the Amazon Reviews dataset across three product categories: Home and Kitchen, Sports and Outdoors, and Electronics. By sweeping lambda, we construct Pareto frontiers that characterize the achievable engagement and carbon trade-off for each model and category. Substantial carbon reductions are achievable at minimal engagement cost across all models and categories. However, the available carbon headroom varies by model and category, underscoring the importance of model choice and domain context.