The value of memory lies not only in recall but in using it to provide appropriate assistance. Recent benchmarks test memory use in personalisation and agentic tasks, but seldom evaluate assistance without fixed answers or integration across multiple participants. Group chats make both challenges more acute: an assistant must integrate information from multiple members, track revisions and conflicts over time, and produce one response for the group. Yet existing group memory benchmarks rely on synthetic conversations and inherit constrained evaluation from general memory benchmarks, focusing on recall against fixed answers or decisions over a closed set. We introduce GroupAssistBench, the first memory benchmark from real-world group conversations with a deployed group assistant, covering 80,299 messages in 50 groups and costing over $53K. Over the same histories, GroupAssistBench evaluates memory recall (L1) with reference answers and memory use (L2) with service requests without fixed answers across single, distributed, and conflicting memories (M1--M3). Requests are verified to require group history, memories are anchored to their sources, and L2 uses tailored rubrics with penalties derived from real user feedback. Across evaluations of frontier models with full context, retrieval methods, and memory systems, the strongest memory system rivals full context on recall but falls far behind on use, especially for distributed and conflicting memories. Together, two additions that relate retrieved memories and bind remembered facts as response constraints bring consistent gains, showing that group memory systems must improve use, not recall alone.
Mengze Hong, Ziwei Shang, Di Liang, Zijian Li, Liang Zhu, Hongyu Shan, Robin Zhou, Minlong Peng 等 12 位作者
Real-time omnimodal assistants are expected to support people in everyday life, but audiovisual understanding alone does not establish whether they can provide timely and appropriate help. We introduce Omni-Life, a benchmark grounded in real-world user needs, deployment scenarios, and device-dependent observations. It combines controlled video synthesis for hazardous situations and edge cases with annotated real-world videos under a shared temporal protocol. The benchmark contains 400 videos: 290 requiring assistance, with 555 required intervention events, and 110 requiring silence throughout to test whether models can withhold unnecessary responses when no assistance is needed. We evaluate twelve configurations featuring mainstream real-time omnimodal models, jointly assessing event coverage, response content, timing, and unwanted output. At most 4.48% of videos requiring assistance are handled completely correctly. To examine practical deployment strategies, we study task reminders and response-latency tolerance. Reminders can improve recall by 17.12 percentage points but add approximately 4.6 unwanted responses per minute of reference silence. Increasing latency tolerance by 10s improves recall by at most 5.95 percentage points. These results show that existing models remain insufficient to deliver reliable assistance in real-life applications, calling for tailored model optimization in instruction following, timely proactive intervention, and withholding responses when assistance is not needed.
Mengze Hong, Xia Zeng, Zeyang Lei, Sheng Wang, Chen Jason Zhang, Di Jiang, Taiming Fu, Jinfeng Huang 等 16 位作者
As AI assistants serve millions of users daily, evaluating user experience (UX) beyond general model capability has become increasingly important. We present \textbf{UXBench}, the first user-centric benchmark grounded in real user feedback signals for evaluating preference alignment and dialogue generation. The benchmark consists of three interconnected tasks, UX Judge, UX Eval, and UX Recovery, with 7,400 test instances extracted from over 70K interaction logs of a mainstream Chinese AI assistant. The dataset closely reflects real user distributions, covering 8 scenarios, 83 domains, and diverse failure patterns that pose severe challenges. Extensive experiments on 26 frontier language models provide novel insights into how well models perceive user experience and how improvements in model capability contribute to better dialogue engagement. Through analyses of model behavior and performance gaps, we document six important findings, demonstrating that user feedback prediction is a learnable capability and revealing different aspects that influence user experience. UXBench establishes a new evaluation landscape and calls for greater attention to tailored UX optimization, contributing toward a user-centric scaling law for the development of successful AI assistants. The full project is released at https://github.com/mengze-hong/UXBench.
Tong Zhao, Di Liang, Yiming Zeng, Bo Xu, Yingzhi Tang, Chen Bai
In the era of large models, stereo matching is developing towards generalizable foundation models trained on million-scale synthetic images. However, how model performance scales up with synthetic data is still underexplored. In this work, we preliminarily investigate the in-domain and cross-domain data scaling laws in stereo matching. A realistic synthetic dataset, named XStereo, containing 200 thousand samples is first built to serve as a high-quality benchmark for data scaling research. In-domain training on five large-scale datasets demonstrate a two-regime scaling behavior with data, transitioning from the standard power law to saturation, where the critical transition point is approximately invariant under a fixed model. Cross-domain performance exhibits a substantially weaker and less predictable dependence on the source-domain data scale. The distribution and coverage diversity are more effective for diminishing domain gaps. More instructive suggestions are provided for high-efficiency data construction and training. The insightful findings are significant verification and extension of the existing scaling laws in both language and vision, paving the way to efficient and stronger stereo matching. The XStereo dataset is public at https://huggingface.co/datasets/Tong-Zhao/XStereo.
Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu Beijing Information Science & Technology University, Chenyao Lu Tencent AI Lab 等 14 位作者
Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after convergence, models often fail to correctly reproduce a subset of their own supervised training data. We refer to this behavior as the Incomplete Learning Phenomenon (ILP). This paper presents the first systematic study of ILP in LLM fine-tuning. We formalize ILP as post-training failure to internalize supervised instances and demonstrate its prevalence across multiple model families, domains, and datasets. Through controlled analyses, we identify five recurrent sources of incomplete learning: (1) missing prerequisite knowledge in the pre-trained model, (2) conflicts between SFT supervision and pre-training knowledge, (3) internal inconsistencies within SFT data, (4) left-side forgetting during sequential fine-tuning, and (5) insufficient optimization for rare or complex patterns. We introduce a diagnostic-first framework that maps unlearned samples to these causes using observable training and inference signals, and study several targeted mitigation strategies as causal interventions. Experiments on Qwen, LLaMA, and OLMo2 show that incomplete learning is widespread and heterogeneous, and that improvements in aggregate metrics can mask persistent unlearned subsets. The findings highlight the need for fine-grained diagnosis of what supervised fine-tuning fails to learn, and why.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Zekai Lin University of Glasgow, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu Beijing Information Science & Technology University, Lei Jiang Tencent AI Lab, Yu Lu 等 11 位作者
Supervised Fine-Tuning (SFT) of large language models often suffers from task interference and catastrophic forgetting. Recent approaches alleviate this issue by isolating task-critical parameters during training. However, these methods represent a static solution to a dynamic problem, assuming that parameter importance remains fixed once identified. In this work, we empirically demonstrate that parameter importance exhibits temporal drift over the course of training. To address this, we propose Evolving Parameter Isolation (EPI), a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance. Instead of freezing a fixed subset of parameters, EPI periodically updates isolation masks using gradient-based signals, enabling the model to protect emerging task-critical parameters while releasing outdated ones to recover plasticity. Experiments on diverse multi-task benchmarks demonstrate that EPI consistently reduces interference and forgetting compared to static isolation and standard fine-tuning, while improving overall generalization. Our analysis highlights the necessity of synchronizing isolation mechanisms with the evolving dynamics of learning diverse abilities.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Peiyang Liu, Zhirui Chen, Xi Wang Px Securities, Di Liang, Youru Li Beijing University of Technology, Zhi Cai Beijing University of Technology, Wei Ye Peking University
Monte Carlo Tree Search (MCTS) has been widely used for automated reasoning data exploration, but current supervision extraction methods remain inefficient. Standard approaches retain only the single highest-reward trajectory, discarding the comparative signals present in the many explored paths. Here we introduce Contrastive Reasoning Path Synthesis (CRPS), a framework that transforms supervision extraction from a filtering process into a synthesis procedure. CRPS uses a structured reflective process to analyze the differences between high- and low-quality search trajectories, extracting explicit information about strategic pivots and local failure modes. These insights guide the synthesis of reasoning chains that incorporate success patterns while avoiding identified pitfalls. We show empirically that models fine-tuned on just 60K CRPS-synthesized examples match or exceed the performance of baselines trained on 590K examples derived from standard rejection sampling, a 20\times reduction in dataset size. Furthermore, CRPS improves generalization on out-of-domain benchmarks, demonstrating that learning from the contrast between success and failure produces more transferable reasoning capabilities than learning from success alone.
尚无 AI 解读，展示原文摘要
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表