DynBranch introduces speculative subgraph reuse for dynamic agentic LLM serving by making unresolved branches addressable before they resolve. This allows candidate subgraphs to run during branch resolution, enabling reuse of completed subgraph results across subsequent requests. Experiments with Qwen3-32B on 4x H200 GPUs show up to 32% mean latency reduction over the best prior system and 46–66% over a no‑reuse baseline, while maintaining correct workflow outputs.
By Junyi Shen, Noppanat Wadlom, Zhengyuan Su, Yao Lu
DepthEvidence is a 4B multimodal language model that integrates dense metric depth predictions into language generation. It employs a camera‑conditioned decoder to produce full‑resolution depth maps and a dense‑to‑language interface that converts these predictions into object‑aligned geometry tokens. The model is trained with geometric supervision and instruction tuning, and it sets new state‑of‑the‑art results on a Depth‑VQA benchmark and on instance‑level metric depth estimation across nine datasets.
By Jiangning Wei, Yuan Yao, Miaomiao Cui, Mingsheng Li, Humen Zhong, Shuai Bai, Zhibo Yang
Pocket-STVG (P-STVG) is a lightweight cascade architecture for Spatio-Temporal Video Grounding that combines efficient pre‑trained components: a temporal‑aware video encoder based on MobileViCLIP, a spatial encoder‑decoder from MDETR, and a shared aligned text encoder. Temporal localization is achieved with a lightweight 1D U‑Net or a simple thresholding strategy, allowing the model to work in both weakly supervised and zero‑shot settings. With fewer than 90 M parameters, P-STVG matches or surpasses prior weakly supervised and zero‑shot methods while offering a more memory‑ and compute‑efficient pipeline for large‑scale video collections.
By Alberto Presta, Michal Byra, Grzegorz Stefa\'nski, Karol Szurkowski, Eryk Ko{\l}odziejczyk, Krzysztof Arendt
The paper investigates how to choose the best quantized model from a family of compressed versions when target labels are scarce or unavailable. It finds that a simple rule based on minimum teacher distortion consistently selects the same eight‑bit, per‑channel, unclipped configuration, though this does not minimize empirical target cross‑entropy. The study also shows that confidence‑based estimators perform poorly in overconfident regimes, while output‑distribution estimators can outperform the teacher in some architectures, and that combining distortion with a supervised term can improve selection. Across 134 candidate families, teacher‑anchored selection reduces mean regret with very few labels, though the benefit diminishes after about 25 labels.
By Alejandro Rodriguez Dominguez, Muhammad Shahzad, Xia Hong
AgentRecommender is a method that uses large language model (LLM) agents to create customizable recommender systems on the user side, eliminating the need for additional data. By leveraging the agents' investigative capabilities and internal knowledge, users can build recommender systems tailored to their own preferences without relying on platform-driven algorithms. This approach addresses issues such as clickbait, filter bubbles, and the spread of fake news that arise from platform-centric recommender systems.
By Ryoma Sato
The paper introduces acoustic-to-text KV compression for full‑duplex speech models, converting acoustic key‑value states into compact textual memory during listening‑time slack. When the KV cache exceeds a target budget, older acoustic states are evicted while transcripts and recent acoustic context are retained. Experiments on ten‑minute LongSpeech sessions show a 64.6% reduction in peak streaming KV‑cache size and improved transcription, temporal question answering, and summarization, with comparable pause‑handling, turn‑taking, and interruption performance in Full‑Duplex‑Bench.
By Yejin Lee, Seungbeom Kim, Yongha Lee, Kyuhong Shim
The paper introduces a post‑training softmax reparameterization technique that selects a functionally equivalent output head before quantization. By subtracting a scalar multiple of the vocabulary‑row mean from each output row and tuning this coefficient via validation KL, the method preserves the full‑precision softmax distribution while enabling efficient W4 quantization. Experiments on seven heads show significant error reductions and latency improvements, with the approach remaining complementary to other quantization strategies and transferable across datasets.
By Asim Kadav, Christian Flores, Chirag Arora, Varun Kotte, Hongbo Zheng, Lan Yan, Priya Shanmugasundaram, Tracy Holloway King
EffectMatch is a runtime system that monitors and validates persistent changes made by large language model agents during software interactions. It collects all side‑effects within a controlled execution boundary and compares them against the application’s approved state, deciding whether to commit the changes and allow subsequent steps. In tests on 206 public business tasks, EffectMatch preserved correct executions and prevented all incorrect commits, with ablation studies showing the importance of each component.
By Haoran Zhang, Hengtong Zhang, Zhiyu Liang, Yu Yan, Decheng Zuo, Hongzhi Wang
AgentXploit is a two‑role auditing system that separates repository‑level attack‑path discovery from runtime exploitation for AI agents. The Analyzer Agent traces attacker‑controlled inputs to sensitive operations and records candidate attack paths, while the Exploiter Agent turns these paths into concrete attacks and refines them using runtime feedback. The system is evaluated on AgentXploit‑Bench, a benchmark of 72 reproducible vulnerabilities across 12 open‑source AI‑agent systems, achieving 59.3% end‑to‑end success compared to 38.4% for Codex, and 79.2% attack success on AgentDojo versus 52.7% for AgentVigil.
By Weida Liang, Shi Qiu, Zhun Wang, Simon Sure, Xiaoyuan Liu, Tianneng Shi, Zhaorun Chen, Wenbo Guo, Dawn Song
The paper introduces Highlight-Then-Summarize (H2S), a two-step approach that first highlights question-relevant evidence in long documents and then condenses it into a compact, question-conditioned summary before generating an answer. The authors built the H2S-Dataset with 6,647 examples spanning 11 benchmark families, and developed H2S-RL to reward evidence selection and summary construction. Evaluated on the H2S-Bench suite, the H2S-14B model outperforms larger open-source models, achieving the highest overall score and maintaining strong performance even with a reduced output budget.
By Zhaoyuan Xia (Peking University, Baidu Inc), Qinghongbing Xie (Tsinghua University), Yung Xiang Hue (Tsinghua University), Jianguang Jiang (Baidu Inc), Gaofeng Lu (Baidu Inc), Zhenyu Jiao (Baidu Inc), Xing Yuan (Baidu Inc), Dai Dai (Baidu Inc), Tong Mo (Peking University), Long Zeng (Tsinghua University)
Intent2Tc is a closed‑loop, language‑model‑driven framework that translates high‑level business traffic‑shaping intents into executable Linux traffic‑control (tc) configurations. It uses an AQM‑based digital twin semantic model, automated metadata extraction, critique‑driven refinement, and Retrieval‑Augmented Generation to improve semantic consistency and configuration reliability. Evaluation on 100 RFC 9315‑compliant intents shows high semantic fidelity and deployment readiness, with Claude Sonnet‑4.6 achieving 0.98 semantic similarity and 0.045 normalized edit distance, while RAG reduces token consumption and latency for compact models.
By Andrea Masini, Sudipta Acharya, Paolo Bellavista, Luca Foschini, Burak Kantarci
The paper "Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers" reports that vision‑language models (VLMs) struggle to read images containing two overlapping text layers—one with sharp contour lines and one with soft shading. Using the DecoyBench dataset of 300 such images, the authors evaluated six closed‑source VLMs under naive and guided prompting at high and low resolutions. While humans could read both layers accurately, the models reliably read only the contour layer at high resolution and failed to extract the shading layer; at low resolution, neither the models nor humans could read the contour layer, but the shading layer remained readable.
"whyItMatters":"The study highlights a consistent limitation of current VLMs in handling typographic structures with multiple spatial frequency layers, underscoring their vulnerability to typographic attacks and the need for more robust text‑recognition capabilities."
By Mert \.Incidelen, Yamen Kashkash, Asya Berker, Murat Aydo\u{g}an
The paper introduces the Active Provenance Gate (APG), a post‑debate verification layer for multi‑agent debate synthesis that audits debate logs, applies self‑correction, and blocks unsupported claims before publication. Empirical studies show that APG more than doubles provenance fidelity in crisis simulations and that users prefer explicit failure reports over fabricated consensus. The work shifts data origin tracing from passive logging to active conditional blocking, addressing safety gaps in large‑language‑model‑based debate systems.
By Jakub Mas{\l}owski, Jaros{\l}aw A. Chudziak
PriceBench is a diagnostic benchmark that extracts price, quality, and brand preferences from large language models (LLMs) by analyzing their hotel booking choices. Using a logit choice model, the study evaluated 28 LLMs from eight providers across 3,600 booking tasks involving 179 New York City hotels. Results show that more capable LLMs exhibit stronger, more consistent preferences, while weaker models either lock onto a single position or show near-indifference, with significant variation in price sensitivity and price/quality trade-offs across providers.
By Pavel Kireyev
The paper presents the first systematic evaluation of cultural awareness in large language models (LLMs) for Haitian Creole, a low‑resource language. Using a benchmark of culturally salient prompts curated by native speakers, the study assesses four dimensions—specificity, bias, diversity, and variation—in a text‑infilling setting. Results show a clear gap between Haitian Creole and higher‑resource French, with Haitian performance more uneven and more affected by French linguistic interference; story generation reveals stereotypical portrayals of Haitian characters even in positive contexts.
By Christelle Clervilsson, Yanzhu Guo
The paper introduces algorithms for aligning the attribute distribution of outputs from black-box generative AI models with a user-specified target. It focuses on minimizing the number of queries needed to achieve exact or approximate alignment, proving optimality as the number of requested outputs grows. Experiments on text-to-image and geocoded persona generation demonstrate that the proposed post-processing methods improve statistical attribute alignment beyond prompting alone.
By Kevin Jiang, Morgane Austern, Edgar Dobriban, Jason M. Klusowski
The paper introduces NarrativeAttack, a jailbreak framework that exploits unified multimodal models (UMMs) by embedding a malicious query within a self‑contained three‑act visual narrative. The attack uses the model’s own image generator to create setup and resolution images, hiding the malicious event as a hidden climax, and concludes with an image‑based guessing game that forces the model to select the relevant answer. Experiments demonstrate that NarrativeAttack outperforms previous methods, achieving up to 88.25% attack success rate on Gemini‑2.5‑Flash, revealing a significant safety vulnerability in UMMs.
By Shaoxiong Guo, Tianyi Du, Lijun Li, Yuyao Wu, Jie Li, Jing Shao
The study presents a pipeline that uses large language models to automatically generate personalized client networks from therapy session transcripts, aiming to aid case conceptualization and treatment planning. Researchers annotated 8,028 utterances from 77 transcripts, then used binary and multi-label classification to identify clinically relevant processes and dimensions, clustered these processes, and generated connections between clusters. Evaluation showed general support for the model’s utility, though interrater agreement varied, and qualitative analysis indicated the networks were coherent and interpretable, suggesting feasibility while highlighting the need for further research on outcome improvement.
By Clarissa W. Ong, Hiba Arnaout, Kate Sheehan, Estella Fox, Eugen Owtscharow, Iryna Gurevych
The paper introduces Stepwise Marginal Information Gain (MIG), an intrinsic process reward that evaluates how each reasoning step of a large language model (LLM) or vision-language model (VLM) improves the likelihood of the reference answer. MIG rewards only new likelihood maxima, preventing duplicate credit, and is combined with outcome, format, and self‑distillation objectives to guide training. Experiments on eight benchmarks show that this method outperforms outcome‑only reinforcement learning and improves accuracy by up to 4.8 points over binary‑reward training, including a 12.6‑point gain on MathVerse and a 12.9‑point advantage on vision‑language transfer at 7B parameters.
By Xiangwei Wang, Wei Wang, Ken Chen, Nanduni Nimalsiri, Sachith Seneviratne, Saman Halgamuge
The paper introduces the Latent Generative Solver (LGS), a neural PDE solver that combines a Physics VAE, a Pyramidal Flow-Forcing Transformer, and input noising to achieve generalization across twelve PDE families and stable long-term rollouts. LGS matches or surpasses deterministic baselines on one-step predictions, outperforms them on 5- and 10-step rollouts, and significantly reduces long-horizon error while cutting compute costs. It also adapts efficiently to unseen higher-resolution systems, demonstrating strong empirical performance on 2D regular-grid PDE simulations.
By Zituo Chen, Sili Deng