Hejin Huang, Jusheng Zhang, Kaitong Cai, Jian Wang, Rong Pan · Mar 31, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
Preference-based alignment objectives have been widely adopted, from RLHF-style pairwise learning in large language models to emerging applications in recommender systems.
With an optional sparse Mixture-of-Experts encoder for efficient capacity scaling, RoDPO achieves up to 5.25% NDCG@5 on three Amazon benchmarks, with nearly unchanged inference cost.
Zhiyuan Peng, Xuyang Wu, Huaixiao Tou, Yi Fang, Yu Gong · Mar 31, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch.
We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking.
Bilgehan Sel, Xuanli He, Alwin Peng, Ming Jin, Jerry Wei · Mar 30, 2026 · Citations: 0
Red TeamGeneral
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning.
Crucially, while prior adversarial fine-tuning approaches report more than 25% capability degradation on reasoning benchmarks, Trojan-Speak incurs less than 5% degradation while achieving 99+% classifier evasion for models with 14B+…
Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido, Alexander P. Christensen · Mar 30, 2026 · Citations: 0
Critique EditGeneral
Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin.
The AIGENIE R package implements the AI-GENIE framework (Automatic Item Generation and Validation with Network-Integrated Evaluation), which integrates large language model (LLM) text generation with network psychometric methods to automate…
He Du, Qiming Ge, Jiakai Hu, Aijun Yang, Zheng Cai, Zixian Huang · Mar 30, 2026 · Citations: 0
Critique EditGeneral
We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe.
On the agent side, Kernel-Smith maintains a population of executable candidates and iteratively improves them using an archive of top-performing and diverse programs together with structured execution feedback on compilation, correctness,…
Kexin Huang, Liwei Fan, Botian Jiang, Yaozhou Jiang, Qian Tu, Jie Zhu · Mar 30, 2026 · Citations: 0
Pairwise PreferenceGeneral
Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models.
However, existing models are largely trained on carefully recorded studio data, which produces speech that is clean and well-articulated, yet lacks the lived-in qualities of real human voices.
Atomic decomposition -- breaking a candidate answer into claims before verifying each against a reference -- is a widely adopted design for LLM-based reference-grounded judges.
Among perturbations examined, reference-quality degradation produced the largest accuracy drops for both judge families.
Zhaopeng Feng, Liangcai Su, Zhen Zhang, Xinyu Wang, Xiaotian Zhang, Xiaobin Wang · Mar 29, 2026 · Citations: 0
Automatic MetricsGeneral
As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck.
Building on this perspective, we propose AgentSwing, a state-aware adaptive parallel context management routing framework.
Jakub Bąba, Jarosław A. Chudziak · Mar 29, 2026 · Citations: 0
Llm As JudgeAutomatic MetricsGeneral
We introduce MAD-ACC (Multi-Agent Debate for Argument Component Classification), a framework that leverages dialectical refinement to resolve classification uncertainty.
Evaluation on the UKP Student Essays corpus demonstrates that MAD-ACC achieves a Macro F1 score of 85.7%, significantly outperforming single-agent reasoning baselines, without requiring domain-specific training.
Jakub Masłowski, Jarosław A. Chudziak · Mar 28, 2026 · Citations: 0
Simulation EnvGeneral
Large Language Models (LLMs) are being increasingly used as autonomous agents in complex reasoning tasks, opening the niche for dialectical interactions.
However, Multi-Agent systems implemented with systematically unconstrained systems systematically undergo semantic drift and logical deterioration and thus can hardly be used in providing ethical tutoring where a precise answer is required.
FARE reveals that routing-level preference shifts are either unachievable (Mixtral, Qwen1.5, Qwen3), statistically non-robust (DeepSeekMoE), or accompanied by substantial utility cost (OLMoE, -4.4%p CrowS-Pairs at -6.3%p TQA).
Critically, even where log-likelihood preference shifts are robust, they do not transfer to decoded generation: expanded evaluations on both non-null models yield null results across all generation metrics.
Trilok Padhi, Ramneet Kaur, Krishiv Agarwal, Adam D. Cobb, Daniel Elenius, Manoj Acharya · Mar 27, 2026 · Citations: 0
Simulation EnvGeneral
Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of reasoning, planning, and acting within interactive environments.
This paper presents a framework for interpreting the temporal evolution of concepts in LLM agents through a step-wise conformal lens.
Shaoxuan Li, Zhixuan Zhao, Hanze Deng, Zirun Ma, Shulin Tian, Zuyan Liu · Mar 27, 2026 · Citations: 0
Automatic MetricsGeneral
We introduce PerceptionComp, a manually annotated benchmark for complex, long-horizon, perception-centric video reasoning.
The benchmark contains 1,114 highly complex questions on 279 videos from diverse domains including city walk tours, indoor villa tours, video games, and extreme outdoor sports, with 100% manual annotation.
We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…
Experiments across multiple model scales and six benchmarks demonstrate that PAPO consistently outperforms ORM, reaching 51.3% vs.\ 46.3% on OlympiadBench while continuing to improve as ORM plateaus and declines.
Raia Abu Ahmad, Max Upravitelev, Aida Usmanova, Veronika Solopova, Georg Rehm · Mar 27, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsGeneral
In addition to standard evaluation metrics (Recall@K and Binary Preference), we adapt an automated framework to assess retrieval quality under incomplete annotations, exposing systematic biases in how conventional metrics rank systems.
