Yuqi Qiu, Zuyao Xu, Lu Sun, Xiang Li, Fasheng Miao, Fubin Wu, Haixin Duan, Zheli Liu
The Agentic Web needs to support continuous collaboration among agents from different organizations. These collaborative relationships may span multiple tasks, network connections and execution instances. Such interactions require stable communication entries, message reception when instances are offline, and source verification after delayed reading. How to organize these responsibilities so that cross domain communication does not depend on specific execution instances being continuously online is a key issue for building long term agent interaction infrastructure. We propose ATP (Agent Transfer Protocol), a cross organization agent communication protocol adopting a domain mediated architecture. In this architecture, administrative domains maintain stable addresses and receiving entries for logical agents. The domain servers of both parties continuously undertake cross domain transmission. The receiving domain verifies and saves messages for execution instances to read later. The sending domain signs the complete message envelope. This allows the receiving instance to independently reverify the domain source and content integrity after the original connection ends, provided the original verification public key is still trusted and obtainable. We implemented an ATP prototype and evaluated it through a controlled cross organization LLM agent workflow, mechanism checks and latency measurements. The workflow completed subsequent business processing after instances went offline or were replaced. The independent verifier successfully verified the domain source and content integrity of saved messages. Latency measurements further quantified the communication and processing overhead introduced by the continuous mediation of domain servers.
Serverless platforms increasingly host machine learning (ML) inference workflows, modeled as directed acyclic graphs (DAGs) of interdependent functions. Beyond container startup, each ML node must load libraries, model weights, and CUDA kernels before it can run. These costs accumulate along dependent DAG paths and place initialization on the end-to-end critical path. Existing systems optimize one half of this problem. DAG-agnostic pre-loading prepares nodes the request may never reach, wasting host and GPU memory. DAG-aware serving routes and scales whole functions, leaving the loading stages inside a node untouched. This paper presents GearUp, a serverless DAG inference serving system that removes ML-node loading from the end-to-end critical path at low resource cost. GearUp profiles the loading stages of each node and schedules them inside the slack time the DAG exposes, hiding initialization behind upstream execution. It reuses initialized instances within and across requests to avoid redundant cold starts. A probabilistic, traffic-adaptive keep-alive policy sets how long idle instances are retained, balancing memory cost against cold-start risk under bursty load. On the AMBER Alert and FINRA-ML workflows with NVIDIA L40S GPUs, GearUp reduces median end-to-end latency by 64.5% and 75.9% against SMIless, for median speedups of 3.1x and 10.0x over cold execution. Integrated GPU and host memory allocation fall by up to 83.9% and 94.6% against eager pre-loading in InstaInfer. GearUp achieves 4.2x strong scaling on four workers.
Yaqi Qiao, Ping He, Songrun Xie, Ayush Barik, Chensong Zhang, Zhengzhong Tu, Fan Lai
Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding, diffusion inference repeatedly updates high-dimensional spatial or temporal latents over many denoising steps. This all-region execution pattern makes generation latency high and limits serving throughput. Existing multi-GPU parallelization methods can reduce per-step computation, but often introduce substantial activation exchange overhead, causing communication to offset or even outweigh the benefits of parallel execution. This paper presents FlashDiff, a diffusion serving system that improves inference efficiency through adaptive regional execution and scheduling. FlashDiff is based on the observation that diffusion refinement is not uniform across latent regions or denoising steps: different regions often stabilize at different rates, while neighboring steps exhibit strong temporal correlation. FlashDiff leverages these properties to selectively execute only regions that require further refinement and to reallocate the resulting compute slack across concurrent serving requests. FlashDiff consists of three mechanisms. First, it decomposes the latent representation into coherent execution regions using early-stage attention signals, preserving semantic structure while exposing fine-grained parallelism. Second, it uses a lightweight runtime controller to estimate region activity and bypass low-impact updates when further refinement is unlikely to affect output quality. Third, it applies an affinity-aware online scheduler that co-locates dependent regions, balances residual load across GPUs, and reuses reclaimed compute capacity to improve serving efficiency. Across real-world image, video, and audio workloads, FlashDiff reduces end-to-end serving latency by 30-97% and improves throughput by 1.2-2.2x.
Web retrieval-augmented generation (RAG) splits a page into fixed-size text chunks or, in recent visual pipelines, screenshot tiles, and the retrieved item serves at once as the unit of indexing, ranking, and reading. We trace answer evidence from source HTML to reader input over the full English Wikipedia and find that this coupling loses evidence in text and screenshot pipelines alike: evidence present in the source page often fails to reach the reader intact, particularly structured content such as tables and infoboxes, which chunking separates from the headers and context that give it meaning. Stronger extraction, context expansion, and larger reader budgets leave the loss in place. We present Tessera, a training-free evidence delivery layer that decouples what a pipeline retrieves from what its reader reads. Given the pages behind any ranked list, Tessera rebuilds their HTML into fine-grained evidence units, each completed with its page title, section path, and table headers, selects the units relevant to the query, and packs them into the reader context at an unchanged token budget. The index, the retriever, and the reader stay as they are, so Tessera applies to text, screenshot, and agentic pipelines. Across three question answering benchmarks, Tessera improves answer accuracy by 5 to 6 points on text and screenshot pipelines, consistently across readers, retrievers, and reader budgets, and outperforms strong HTML-aware and structure-aware RAG baselines under matched budgets. The gains carry over to multi-step agentic search. Our code is publicly available at https://github.com/sarendis56/Tessera.
Knowledge distillation from large reasoning models (LRMs) often uses raw teacher trajectories as supervision. However, this practice creates a mismatch between the goal of distillation and the nature of teacher trajectories. Advanced LRMs typically improve their reasoning capabilities through reward-driven post-training, such as RLHF. This training optimizes them as strong solvers, rather than as teachers that produce reasoning processes smaller models can easily learn. Since smaller models have different "cognitive capacities" compared to their larger teachers, directly imitating raw teacher trajectories can sometimes be ineffective and often requires a substantial number of high-quality samples. To bridge this mismatch, we propose Cognition-Aligned Reasoning Distillation (CARD), an RL-based framework that transforms solver trajectories into teaching trajectories aligned with the student's cognition. Avoiding expensive resampling, our framework directly transforms existing trajectories. We optimize CARD with two reward signals: (1) a Distribution Alignment Reward that matches the student's predictive distribution, and (2) a Logical Coherence Reward that reduces misleading failed reasoning steps. Comprehensive evaluations across multiple student models and settings demonstrate that CARD outperforms distillation from raw teacher trajectories in in-domain settings while achieving substantial gains in out-of-distribution performance. Code is available at https://github.com/LiteSSLHub/CARD.
Tube-wise video completion reconstructs temporal trajectories at spatial locations unobserved in every frame. We propose a two-stage framework combining regularized masked Kronecker product decomposition (KPD) with cross-fitted self-supervised residual learning. First, we estimate a compact structural backbone directly from observed entries using cyclic component-wise least-squares updates, spatial and temporal factor regularization, and regularizer-optimal scale balancing. The exact updates yield a nonincreasing objective. Second, we address the mismatch between in-sample fitting errors and the prediction errors encountered at missing tubes. We partition observed tubes into folds and construct residual targets using backbone models fitted without the corresponding target tubes. A lightweight 3-D convolutional neural network then predicts corrections from the backbone, visible residual context, observation mask, and local detail features. Exact data consistency preserves observed measurements. Experiments include ablations, sensitivity analysis, grayscale and RGB video completion, and structured missing patterns. Our method achieves the highest mean PSNR and SSIM at the higher tested sampling rates on the grayscale benchmark. On eight selected DAVIS RGB sequences, it achieves the highest mean missing-region PSNR and full-frame SSIM and the lowest mean missing-tube temporal-gradient MAE at every evaluated sampling rate.
Yuhao Li Beijing University of Posts and Telecommunications, Haifeng Sun, Xuesong Zhang, Shu Yao, Haoyu Zheng, Yvchuan Wang Beijing University of Posts and Telecommunications, Huazheng Wang, Zirui Zhuang Beijing University of Posts and Telecommunications 等 11 位作者
Recent advances in large language models (LLMs) have significantly improved code-generation capabilities, particularly through retrieval-augmented generation (RAG) for private libraries. While RAG leverages API documentation to address the scarcity of private code corpora, its performance critically depends on the quality of retrieved examples. Existing approaches often overlook the intrinsic characteristics of these examples, particularly how factors such as complexity, readability, and correctness impact their effectiveness. In this study, we systematically investigate these three critical aspects—complexity, readability, and correctness—and find that optimal examples should exhibit moderate complexity, semantic correctness, and step-by-step execution patterns. Based on these findings, we propose ComboPrompt, a novel example enhancement method that strategically combines existing API examples to improve complexity, refines code structure for readability, and incorporates automated validation ensuring correctness. Extensive evaluations across five private library benchmarks and different LLMs demonstrate that ComboPrompt achieves up to 22% accuracy improvement over baseline approaches. Code is available at Github.
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
Bowei Zhang, Hanbing Liu, Qixin Tian, Siyu Chen, Ziyuan Wang, Qi Qi Renmin University of China
Smart Contracts are the foundation of Decentralized Finance (DeFi), executing financial logic without trusted intermediaries. Recent advances in large language models (LLMs) have substantially lowered the barrier to smart contract development by enabling code generation from natural language. However, because smart contracts are immutable and directly manage financial assets, this accessibility introduces a critical trust gap: generated contracts are easy to produce but hard to trust. To bridge this gap, we present LeVer, the first trustworthy smart contract synthesis framework that integrates LLM-based generation with Lean-based auto-formalization and Verification. LeVer employs a closed-loop multi-agent architecture to iteratively generate, verify, attack, and repair contracts, providing both formal guarantees and empirical robustness. To facilitate the adoption of automated formal verification in smart contract generation and audition, we open-source our framework and datasets at: https://github.com/gl-bowei/LeVer
尚无 AI 解读，展示原文摘要
cs.CL · cs.MA
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表
Yixiao He Beijing University of Posts and Telecommunications, Menghao Zhang Beijing University of Posts and Telecommunications, Haifeng Sun, Jing Wang, Kangheng Lin, Jinghan Wang Beijing University of Posts and Telecommunications, Chenye Xu, Pengfei Ren Beijing University of Post and Telecommunications 等 10 位作者
Video anomaly understanding (VAU) is critical for real-world scenarios. Recent advances in Video Large Language Models (Video-LLMs) enhance the ability of VAU models to describe and interpret anomalies. However, progress in anomaly localization is still limited by two key issues. First, most existing video anomaly datasets only annotate segments that are clearly inconsistent with the context, often omitting subsequent segments that are semantically part of the same abnormal event. Second, the field lacks systematic evaluation protocols. To bridge these gaps, we introduce VALU, a new benchmark that explicitly defines anomalies across five semantic levels and provides comprehensive temporal boundaries and detailed textual descriptions for each. Based on these annotations, we design three evaluation tasks that comprehensively assess models’ capabilities across different dimensions, including temporal grounding, anomaly localization, and anomaly detail discrimination. Evaluation results reveal persistent challenges in current models’ capabilities on VAU. We further analyze and discuss these findings, and hope that both VALU and insights will advance research in VAU and the development of Video-LLMs. Our benchmark will be publicly available.
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
Zisu Huang, Muzhao Tian, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Kaitao Song Apple, Jiakang Yuan Shanghai Artificial Intelligence Laboratory and Fudan University 等 10 位作者
As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most existing systems adopt an “all-or-nothing” approach to memory usage: incorporating all relevant past information can lead to Memory Anchoring, where the agent is trapped by past interactions, while excluding memory entirely results in under-utilization and the loss of important interaction history. We show that an agent’s reliance on memory can be modeled as an explicit and user-controllable dimension. We first introduce a behavioral metric of memory dependence to quantify the influence of past interactions on current outputs. We then propose Steerable Memory Agent, SteeM, a framework that allows users to dynamically regulate memory reliance, ranging from a fresh-start mode that promotes innovation to a high-fidelity mode that closely follows interaction history. Experiments across different scenarios demonstrate that our approach consistently outperforms conventional prompting and rigid memory masking strategies, yielding a more nuanced and effective control for personalized human-agent collaboration.
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
Yun He Meta, Wenzhe Li Princeton University, Hejia Zhang Facebook, Songlin Li Facebook and Stanford University, Karishma Mandyam, Sopan Khosla Facebook, Yuanhao Xiong University of California, Los Angeles, Nanshu Wang Facebook 等 25 位作者
Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)—especially for complex, multi-turn, and system-prompted instructions—remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF, a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. We also open-source the evaluation script of AdvancedIF. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems.
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