跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1673新增论文
+1257其中 AI 相关
+198已有论文修订
+101新增 AI 导读

arXiv 最近完成扫描：2026-11-14 00:45 · 全站最近入库：2026-11-13 20:44各信源进度 →

统计口径与数据新鲜度

统计 2026-11-13 01:29 — 2026-11-14 01:29（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-14 00:45最近发现新增版本：2026-11-13 20:44库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,727 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 23,208 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-14 00:42（北京时间）
新论文 · v1arXiv:2611.16414

Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency

Sailendra Kolluru, Maheshkumar Duvvarapu

原文摘要

Optional reasoning, retrieval, web search, and tool use can improve large language model responses but incur unnecessary computation when activated indiscriminately. This study investigates whether prompt optimization can compensate for limited router capacity and whether classification gains translate into downstream efficiency. The proposed framework uses prompt-driven small language models to make four independent capability decisions, allowing multiple capabilities to be selected per query. Qwen2.5 routers ranging from 1.5B to 14B parameters are compared across five prompting strategies, followed by an evaluation of capability-specific optimized configurations using a fixed GPT-OSS-120B downstream model on 127 questions. Under minimal prompting, increasing router capacity does not consistently improve classification performance. Prompt optimization narrows the capacity gap for reasoning and calculator routing, whereas RAG and web search retain larger benefits from higher capacity. Similar classification F1 scores do not necessarily imply equivalent downstream behavior: false-positive activations increase unnecessary computation, while missed capabilities can reduce answer quality. The 14B router achieves a mean BERTScore F1 of 0.8408, compared with 0.8418 when all capabilities are enabled, while reducing average downstream token consumption by 68.7\% (8,837 to 2,764 tokens) and median downstream latency by 80.5\% (9.79 to 1.91 seconds). These savings exclude router overhead, which is measured separately in a different inference environment and increases with router capacity. The findings demonstrate that the relationship between router capacity, prompt design, and downstream efficiency is capability-dependent. Consequently, router selection must consider error profiles and routing overhead alongside classification performance.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16413

RICapBench: A Fine-Grained Visual Understanding Benchmark Dataset for Vision-Language Models in Remote Sensing

Xue Wang, Yubin Xu, Kun Tan

原文摘要

Advances in vision-language models (VLMs) have improved remote sensing image analysis and supported geospatial decision-making. However, fine-grained understanding of remote sensing imagery remains challenging for VLMs. Large variations in object scale, complex geospatial relations among instances, and limited visual detail hinder precise instance localization, visible attribute identification, and spatial relation understanding, potentially leading to descriptions that lack visual grounding. Existing datasets and benchmarks insufficiently assess end-to-end instance localization and captioning without target-specific textual cues. To support this evaluation, we introduce RICapBench, a dataset and benchmark that unifies instance localization and fine-grained captioning in remote sensing. RICapBench contains 245,466 instance-level annotations and 498,005 spatial relation tuples spanning general remote sensing, UAV remote sensing, and dense small-object scenarios. Each annotation pairs an object's oriented bounding box with a natural language description of its visible attributes and spatial relations to surrounding instances and environmental elements. To evaluate the accuracy and completeness of spatial relation captioning, we propose a remote sensing spatial relation parser and the RelCap-F1 metric. We combine RelCap-F1 with instance localization and attribute captioning metrics into a composite metric, RICScore. Our evaluation of 15 advanced open-source and closed-source VLMs identifies instance localization as a major bottleneck for these models. LocateAnything achieves the highest RICScore of 31.68, but scores lower on spatial relation captioning than other task-fine-tuned open-source VLMs. Code and dataset are available at https://github.com/Xldln/RICapBench.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16412

Exact Quantum Algorithms for Composed Boolean Functions

Gagan Chiruvella, Chandrima Kayal, Rajat Mittal, Manaswi Paraashar, Nitin Saurabh

原文摘要

We study exact quantum algorithms for block compositions of total Boolean functions. For an outer function $f$ of degree $D$ and an inner function $g$ on $m$ bits, we prove $$ Q_E(f\circ g)=O\!\left(mD+Q_E(f)Q_{1/(4D)}(g)\right). $$ The algorithm combines approximate inner evaluations with a finite exact correction. Its two costs are governed by different parameters of the outer function: exact query complexity determines the cost of simulation, whereas polynomial degree determines the number of inner blocks used in the correction. We first establish the construction with an arity-dependent error threshold and then obtain the degree-dependent threshold above. For recursive ternary not-all-equal, this gives an exact algorithm using $(3/\sqrt2)^{k(1+o(1))}$ queries asymptotically. More generally, for every fixed nonconstant total gadget $h$, we determine the exact recursive rate as $\max\{\textrm{deg}(h),\operatorname{Adv}^{\pm}(h)\}$ and prove $Q_E(h^{\circ k})=\widetilde O_h(R(h^{\circ k})^2)$. The composition limit also allows to transfer separations from $Q_{\varepsilon}$ and $°$ to exact quantum query complexity $Q_E$ (similar to fractional block sensitivity to block sensitivity transfer in Tal and Kulkarni 2016, Chicago Journal of Theoretical Computer Science). We construct a family with $s=\operatorname{bs}=\operatorname{fbs}\ge Q_E^{3/2-o(1)}$, improving the previous exponent $1.1527\ldots$. A second construction gives $R \ge Q_E^{2-o(1)}$, improving the previous exponent $3/2$. We also allow different inner functions and give analogous quantitative separations in quantum communication.

cs.CC · quant-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16411

Flexible Intelligent Metasurfaces for Enhancing Secure MISO Communications

Zihao Teng, Zihao Zhao, Jiancheng An, Lu Gan, Arumugam Nallanathan, Bo Ai

原文摘要

This letter investigates flexible intelligent metasurface (FIM)-aided secure multiple-input single-output (MISO) communications in the presence of a multi-antenna eavesdropper. By exploiting the morphing capability of the FIM, the transmit array geometry can be dynamically reconfigured to reshape the legitimate and eavesdropping channels. We formulate a secrecy rate maximization (SRM) problem by jointly optimizing the transmit covariance matrix and the FIM surface shape. For a given FIM surface shape, the optimal transmit covariance matrix is shown to be rank one and is obtained in closed form from the dominant generalized eigenvector. For a fixed transmit covariance matrix, a projected gradient ascent (PGA) method is developed to optimize the FIM shape. Based on these two subproblems, a block coordinate ascent (BCA) algorithm is proposed. Moreover, for the special line-of-sight (LoS) scenario, we derive a globally optimal closed-form joint transmit covariance matrix and FIM surface shape design under a sufficient morphing-range condition. Numerical results demonstrate that FIM effectively improves the secrecy rate over a conventional rigid antenna array (RAA). Moreover, FIM achieves a transmit-power saving of about 2.5 dB compared with the RAA benchmark at the same secrecy rate.

eess.SP · cs.IT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16409

Experience-Handoff Reinforcement Learning for Recursive Self-Improvement

Doyoung Kim, Byeongguk Jeon, Kailin Zhang, Sherry Yang

原文摘要

It is common to train Large Language Models (LLMs) for agentic tasks with Reinforcement Learning (RL) from scalar rewards. However, this throws away the fine-grained information about the environment that the agent experienced during the trial (e.g., error logs). To utilize this rich information, recent works wrap the agent in a harness that refines its own inputs through reflection or compaction and hands past experience to future rollouts, but the construction of the handed-off artifacts (e.g., a playbook) is itself not learned. We want the best of both worlds: gradient updates from a scalar reward, while also utilizing environment information to hand off experience. As a concrete testbed, we fix the Agentic Context Engineering (\ace{}) harness and train one model to act, reflect, and curate task-local playbooks. Our method, \acerl{}, evaluates candidate experience-handoff artifacts by their downstream effect on future actor rollouts, and co-optimizes the role-specific behaviors (action generator, insight reflector, and playbook curator) under a fixed scaffold. Across agentic benchmarks, \acerl{} achieves higher held-out performance than baseline methods. The results suggest that agent training should optimize not only the actions in the current rollout, but also the model-written experience that future rollouts inherit.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16408

Gravity and Flight: Learning to Navigate Fine-Grained Remote Sensing Scenes

Yuheng Zong, Minghua Wang, Xin Zhao, Xiaobin Liu, Yongjian Dong, Chanho Eom

原文摘要

Vision-language models are increasingly capable, yet their reasoning in complex remote sensing scenes can remain coarse-grained and insufficiently grounded in task-relevant visual evidence. We propose Gravity and Flight (G&F), a framework for scene specialization with limited supervision that separates visual and reasoning verification while coupling policy updates. It combines Evidence-of-Thought supervised fine-tuning (EoT-SFT) and Relational Transfer Policy Optimization (RTPO). EoT-SFT teaches fine-grained observation and faithful reasoning through description, analysis, and supported conclusions. RTPO independently samples responses to scene-matched image pairs with fine-grained visual differences under a shared task. Its rubric-based verification combines Gravity, which checks visual fidelity and description coverage, and Flight, which takes descriptions as premises to assess evidence use and relations between paired judgments. Their scores and task correctness yield a shared pair-level advantage that couples policy updates from both responses. Using 1,008 demonstrations and 500 training pairs for harbor specialization, G&F achieves a mean score of 69.12 across six evaluation sets, exceeding the backbone and supervised initialization by 9.76 and 4.56 points. Matched controls show gains over single-image and joint-input RL, and removing either verification view reduces performance. Applying G&F to urban specialization also improves on the base model and supervised initialization across three evaluation subsets. Project details and updates are available at https://github.com/Z0ngL1ng/Gravity-and-Flight.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.34302

CAT-Free: Calibration-, Annotation-, and Target-Training-Free Multi-View BEV Pedestrian Detection and Tracking

Taigo Sakai, Hiroki Kouno, Naoki Kato, Kazuhiro Hotta

原文摘要

Multi-camera pedestrian detection and tracking often require camera calibration, position annotations, and target-scene training. CAT-Free removes all three requirements and uses only synchronized RGB video. From this video, CAT-Free estimates camera poses and the ground plane. With the estimated poses and ground plane, CAT-Free triangulates detections across cameras and links pedestrian positions into tracks. However, camera errors and mismatched detections produce false positions. Two geometric filters remove these false positions: one rejects unstable estimates, and the other rejects positions off the ground. Both filter thresholds are estimated from the unlabeled video. Without calibration, annotations, or target-scene training, CAT-Free achieves 89.2, 84.1, and 76.1 MODA on WildTrack, MultiviewX, and GMVD. CAT-Free is also less affected by camera errors than methods that assume known camera parameters, and it outperforms a domain adaptation method without any adaptation.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16405

AntEmbed: Dual-Mode Multimodal Embedding Model for Efficient and Fine-Grained Retrieval

Kehang Jia, Teng Liu, Juntao Li, Hua Chen, Jinxiong Chang, Xiaobo Liang, Min Zhang

原文摘要

Discriminative embeddings encode original multimodal inputs efficiently but struggle with fine-grained semantics. Generative embeddings use reasoning to capture query intent and relevance evidence, but incur higher computational costs. We propose AntEmbed, a dual-mode multimodal embedding model that supports efficient retrieval and reasoning-enhanced fine-grained matching in a unified embedding space. First, we construct retrieval-oriented reasoning content that captures query intent and confusion-aware semantic evidence. We treat original and reasoning-enhanced candidate inputs as semantically equivalent views, and use multi-positive contrastive learning with a single embedding token to align discriminative and generative embeddings. Second, cross-mode self-distillation transfers fine-grained semantic information from reasoning-enhanced to original representations through candidate similarity-distribution distillation and query representation alignment. This strengthens discriminative embeddings without requiring additional online reasoning. Both retrieval modes share a single candidate index. On MMEB-v2, AntEmbed-8B achieves an overall score of 81.5 with reasoning-enhanced embeddings, outperforming the strongest baseline by 3.1 points.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16404

ReSID: Rethinking Long-Tail Retrieval in Generative Recommendation through Item Reachability

Muyu Zou, Shunye Tang, Yi Xu, Haibo Xing, Yandong Wang, Lingyu Mu, Jinxin Hu

原文摘要

Generative recommendation (GR) represents items with discrete Semantic IDs (SIDs) and casts retrieval as sequence generation. Under skewed interaction distributions and tight serving budgets, GR struggles to retrieve long-tail items. In this work, we are the first to study long-tail reachability across the complete pipeline of SID construction, decoding, and matching. We find that under equal code lengths, parallel SID construction consistently outperforms sequential SIDs on tail items. Moreover, even when full generation fails, decoded sequences carry locally consistent information that retrieves relevant tail items via partial matching. Yet this recovery is bounded by upstream search, failing once beam search prunes all prefixes completable within a fixed mismatch tolerance. Motivated by these findings, we propose ReSID to jointly preserve and recover tail candidates. Built on long parallel SIDs, ReSID pairs popularity-debiased and user-semantic-aware beam search to keep promising paths alive with partial SID matching to recover items from surviving tokens. ReSID achieves state-of-the-art long-tail retrieval while maintaining competitive overall accuracy, with lower latency and higher throughput under narrow beams. ReSID is deployed in our production system, serving main user traffic with substantial business gains. We release our complete code and model checkpoints to support full reproducibility and real-world deployment at https://github.com/Gabriel-reina/ReSID.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16402

Teach with Blinks: Breaking Linguistic Momentum in On-Policy Distillation for Fine-Grained Multimodal Perception

Tangzheng Lian, Hang Zhang, Guanyu Hu, Renjiu Hu, Zhensong Zhang, Jiankang Deng, Jifei Song

原文摘要

On-policy distillation (OPD) has emerged as an effective post-training approach to improving fine-grained perception in multimodal large language models by amortizing costly inference-time zooming operations into a single-pass recipe. However, vanilla OPD is inherently susceptible to linguistic momentum: the teacher can follow the student's erroneous prefixes, thus weakening corrective supervision. To address this, we propose Blink On-Policy Distillation (BlinkOPD), in which the teacher "blinks" at every token: it reads the same prefix once with its eyes open and once with its eyes closed. A first-glance gain further strengthens the correction on rollouts that conflict with the teacher. By extracting more effective supervision from each on-policy trajectory, BlinkOPD achieves state-of-the-art average performance across six fine-grained benchmarks using only 500 training images (12x less data) than existing OPD methods. Beyond fine-grained perception, BlinkOPD also demonstrates strong zero-shot improvements across ten held-out benchmarks spanning general visual perception, visual hallucination, and multimodal reasoning abilities. Code: https://github.com/Supltz/BlinkOPD

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16400

FuGIBench: Evaluating Reliable Preparation in Streaming Video

Changheng Cai, Zhichao Huang, Song Ren, Zhichen Zhao, Hongsen Liu, Chaoyang Zheng, Wenxi Wu, Yuan Fang 等 11 位作者

原文摘要

An assistant watching a worker can prepare for an emerging need before the worker is ready to receive help.As the need evolves, the assistant must maintain preparation until a response is due, or withdraw it if the need disappears. Video anticipation and interactive response benchmarks leave this interval between early evidence and response largely unmeasured. We introduce FuGIBench (Future-Grounded Interaction), a streaming-video benchmark in which a model chooses among waiting, reversible preparation, and response given a causal video prefix and a task contract. The benchmark contains 19,893 synthetic tool-assistance videos across ten tool tasks, in handover, ordinary-activity, and cancelled-need tracks. One primary score credits sustained preparation, incorporates response-interval alignment, and penalizes activity when the reference prescribes waiting. On a frozen set of 1,000 episodes, a reference system with a longer preparation lead has poorer response alignment, while similar handover leads accompany different levels of activity during ordinary work in matched scenarios. Together with cancellation analyses, these results show why evaluating preparation requires tracking decisions as needs develop, become actionable, or disappear.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16399

Saidzoda-Kazakh-EmbeddingGemma-300M: How Far One Epoch of Generated Questions Takes a Small Kazakh Embedder

Tohir Saidzoda, Madina Abdusalomzoda, Abubakr Abdullozoda, Amin Jalilov, Faroiz Bobokhon, Aibek Shokanuly

原文摘要

EmbeddingGemma-300M is a small open embedder, and used as released it finds the right passage first for 60.8% of the Kazakh Belebele retrieval questions. We present Saidzoda-Kazakh-EmbeddingGemma-300M, the same model fully fine-tuned for one epoch on 208,511 pairs: 166,263 Kazakh questions that our own language model wrote about source passages from encyclopedias, Wikipedia, news and books, each checked by a second model, plus English and Russian replay. On Kazakh Belebele, recall@1 rises from 60.8% to 78.0% and recall@10 from 76.3% to 91.4%. Our model scores above 161 of the 194 models with a published MTEB score on the same test, among them OpenAI text-embedding-3-large (47.1%). The other 33 score higher: the ten best are large multi-billion-parameter or closed models, reaching up to 92.2%, and at least 9 are open models of up to 0.6B parameters, the smallest with 339M. We also scored 6 Kazakh-specific embedders shared on Hugging Face with the same code in one run: our model (77.3% there) is ahead of 4 of them, including the two E5-base models of similar size (72.6% and 69.0%), and behind kaz-embedder (86.0%, three towers with 1,695M parameters in total) and a BGE-M3 fine-tune (81.0%); at recall@10 its interval overlaps those of its nearest neighbours on both sides. Our four-language model, trained with a capped share of the same Kazakh pairs, is 2.8 points lower at recall@1, with overlapping recall@10 intervals. The Kazakh model also scores higher than the released model on the Uzbek and Kyrgyz versions of Belebele, but our Tajik model, trained without any Turkic pairs, gains as much there, so these gains are not specific to Kazakh training. Our Kazakh Wikipedia test questions come from the same generator family as the training questions, so we rest the main claims on Belebele.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.27025

Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization

Zhenhua Xu, Dongsheng Chen, Jian Li, Yitong Lin, Zhebo Wang, Jiafu Wu, Yizhang Jin, Chengjie Wang 等 10 位作者

原文摘要

Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. Explicit reasoning can help models deliberate before responding, but generic reasoning does not necessarily preserve character fidelity. We therefore propose Psy-CoT, a psychology-grounded chain-of-thought framework that decomposes pre-response reasoning into three role-specific steps: Interaction Perception, Psychological Empathy, and Logical Construction, so that the model thinks dynamically from the profile rather than merely mimicking surface patterns. While structured reasoning provides a foundation, it alone is insufficient; reinforcement learning is essential to further align the model with character fidelity. However, we observe that under LLM-based reward models, both generic phrases that hack the reward model and genuinely role-specific phrases receive identical gradient signals. This hacking accumulates over training, misleading the model into treating both as equally optimal choices. To address this, we propose Role-Aware Policy Optimization (RAPO), which uses profile-induced entropy differences to weight gradients asymmetrically, amplifying role-specific tokens under positive advantage while attenuating them under negative advantage. Experiments on CoSER, CharacterBench, and CharacterEval demonstrate that Psy-CoT outperforms existing role-playing CoT methods, and RAPO consistently surpasses GRPO across multiple model scales.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.14009

Coding Agent Memory Post-Training II: Unlocking the Memory Potential of Pre-trained File Operations for Long-Horizon Tasks via On-Policy Distillation

Lirui Luo, Kelong Mao, Xinwei Yang, Rongqing Li, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang 等 13 位作者

原文摘要

Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. They must therefore decide what to write down and what to read back, and when to do either. Recent work has begun to use on-policy distillation (OPD) to make memory control part of the policy, relying on memory tools and compaction protocols that lie outside either model's pre-training. However, this weakens the distillation on both sides: the teacher cannot give useful guidance on an interface it has never used, and the student samples too few meaningful memory actions for that guidance to take effect. To study this problem, we introduce Coding Agent Memory Gym II (CAMG-II), a suite of long-horizon agentic-RL environments spanning Shop, Coding, AutoResearch, General, and Visual. Alongside each environment's native task interface, CAMG-II provides ordinary Bash access and an episode-persistent workspace, enabling the policy to create, revise, search, and reuse files as memory across context replacements. We also introduce Coding Agent Memory Post-Training II (CAMP-II), which trains a single policy jointly across all five environments with fully asynchronous OPD to learn this file-based memory behavior directly from a frozen teacher with a prior for file operations. On CAMG-II, CAMP-II obtains 2.97 times the gain of the strongest OPD baseline. The memory behavior CAMP-II learns generalizes to two external benchmarks, Terminal-Bench 2.1 and SWE-Bench Pro V2, with improved success rates.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16395

TriGen: A Generative Paradigm for Trigger-Induced Recommendation

Muyu Zou, Haibo Xing, Shunye Tang, Liyan Tie, Lingyu Mu, Yandong Wang, Jinxin Hu

原文摘要

Generative recommendation typically operates under the User-Induced Recommendation (UIR) setting, predicting target items by autoregressively generating semantic IDs as a passive continuation of long-term user history. However, this paradigm overlooks Trigger-Induced Recommendation (TIR), an essential industrial scenario where a user click triggers an immediate follow-up feed. In TIR, recommendations must dynamically align with the instant trigger intent without compromising historical preference continuity. Traditional TIR methods rely on discriminative scoring and cannot guide token-level generation, while existing generative models lack mechanisms to reconcile this structural tension. To address this challenge, we propose TriGen, establishing a tailored generative paradigm for trigger-induced recommendation. TriGen introduces calibrated tail injection to re-encode local history, adaptively arbitrates between persistent tastes and immediate impulses via dynamic gating, and applies position-specific transformations to sustain level-aware trigger guidance across decoding steps. Extensive offline evaluations confirm consistent gains over competitive baselines. Furthermore, online A/B tests across six country markets demonstrate significant revenue and GMV improvements, leading to the full production deployment of TriGen.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16393

TransXplainRRG: A Radiologist-Evaluated LVLM for Chest Radiograph Report Generation

Chayan Mondal, Duc-Son Pham, Tele Tan, Ashu Gupta, Vincent T. Y. Tiong, Shreya Ghosh, Tom Gedeon

原文摘要

Recent advancements in Large Vision-Language Models (LVLM) enhance X-ray report generation, but often neglect clinical context, overlook workflow integration, and lack explainability, which hinders clinical adoption due to interpretability and reliability concerns. This paper addresses the dual challenges of performance and expert explainability in automated X-ray report generation for clinical AI applications. Our proposed approach, TransXplainRRG, utilises an off-the-shelf Swin Transformer model along with a transformer-based text encoder that incorporates patient medical history to generate a radiology report. Further, we explore an expert-guided `inside-out' approach and extract only abnormal findings for radiology report refinement. Thus, this study bridges the gap between high-performance automation and interpretability critical for clinical practice by combining state-of-the-art transformer-based vision encoders, text encoders, and LLMs. TransXplainRRG is trained and tested on the large-scale MIMIC-CXR dataset and further evaluated on the unseen IU X-Ray dataset to demonstrate its generalizability and robustness. We employed the GREEN metric as a complementary measure of clinical consistency, achieving scores of 0.327 on MIMIC-CXR and 0.605 on IU X-Ray, both higher than those achieved by MAIRA-2 under the same evaluation setting. It also performed competitively across standard evaluation metrics, frequently matching or surpassing state-of-the-art models. Additionally, we introduce qualitative evaluation metrics developed from radiologists' viewpoints and conduct a preliminary radiologist evaluation on 100 generated reports to assess their clinical relevance. Quantitative and qualitative analyses further demonstrate the potential of our TransXplainRRG framework for reliable and explainable radiology report generation.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.12109

SkillDuet: Co-Evolving Models and Skills through Response Feedback

Xingguang Ji, Ziqiang Dong, Yubo Zhang, Xi Leng, Ninghua Yan, Yang Yang, Guanjun Jiang

原文摘要

During reinforcement learning, experience can be both internalized in LLM parameters and retained externally as reusable textual skills. Parameter updates alter the model's behavior and the interaction experience from which new skills are extracted. These skills, in turn, guide the model's subsequent interactions and parameter updates. As the model's capabilities evolve, previously beneficial skills may become redundant or detrimental. We present SkillDuet, a framework that coordinates parameter updates and skill evolution through model response feedback. Skills extracted from on-policy trajectories guide parameter updates through OPD at every step. A response-based score, Strength, ranks candidate skills by the magnitude of the shift they induce in the current model's responses, and the highest-scoring skills are periodically consolidated into a persistent global skill set (Global). The updated model and Global jointly guide subsequent interactions, generating experience for further parameter and skill updates. With Qwen3-4B, SkillDuet achieves success rates of 98.57% on ALFWorld and 92.97% on WebShop, exceeding the matched SEED-API baseline by 2.86 and 5.47 percentage points, respectively. Ablations show that response-based skill selection and Global consolidation improve task performance. Further experiments show that the benefits of retained skills depend on both their content and their compatibility with the model. SkillDuet provides a concrete mechanism for model-skill co-evolution and skill-level recursive self-improvement.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.23670

Automata from Agent Traces: Failure and Next-Step Prediction

Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed, Zekun Wu, Kleyton Da Costa, Ilham Wicaksono, Adriano Koshiyama

原文摘要

LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtime monitoring that deployment requires. Existing approaches operate per-trace or success-only, so they miss the cross-run topology that links next-step and failure prediction. To recover that shared structure, we collapse an entire trace corpus into a single, compact finite-state machine (FSM) that serves as a structural substrate for the otherwise unpredictable behavior of LLM agents. Across twelve public datasets, the FSMs are compact (7-43 states), replay held-out data at >=0.997 fitness with near-identical topology across splits, and build in milliseconds. This substrate addresses both prediction goals. For next-step prediction, FSM-state context outperforms Agent Workflow Memory on every ground-truth-matched dataset. For failure prediction, per-state behavioral features reach held-out AUROC up to 0.94, and an online monitor ranks failing runs above passing ones from a partial trace, triggering early stopping well before completion. Behavioral topology thus appears shaped more by the deployment harness than by the LLM, providing a model-agnostic structural primitive for safety auditing and runtime monitoring.

cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2602.10437

Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features

Seonglae Cho, Zekun Wu, Adriano Koshiyama

原文摘要

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement Learning (CRL), which trains a policy to select SAE features for steering at each token, producing interpretable intervention logs: the learned policy identifies features that change model outputs when amplified. Adaptive Feature Masking encourages diverse feature discovery while preserving singlefeature interpretability. The framework yields new analysis capabilities: branch point tracking locates tokens where feature choice determines output correctness; critic trajectory analysis separates policy limitations from value estimation errors; layer-wise comparison reveals syntactic features in early layers and semantic features in later layers. On Gemma 2 2B across MMLU, BBQ, GSM8K, HarmBench, and XSTest, CRL achieves improvements while providing per-token intervention logs. These results establish learned feature steering as a mechanistic interpretability tool that complements static feature analysis with dynamic intervention probes

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16388

Strategically Robust Multi-Agent Control

Boris Velasevic, Nicolas Lanzetti, Eric Mazumdar

原文摘要

A key source of uncertainty in multi-agent systems is the behavior of other agents. Game-theoretic control approaches ignore this uncertainty, while robust control approaches treat others as fully adversarial. In this paper, we introduce strategically robust multi-agent control to populate the spectrum between these two paradigms. Specifically, in dynamic games, we propose that players are strategically robust and seek protection against misspecified control policies of the other players. This formulation induces a novel equilibrium concept, strategically robust dynamic equilibrium, that interpolates between game-theoretic control and robust control. We study this concept across canonical open- and closed-loop settings and show that accounting for strategic robustness also has computational benefits over classic approaches in game-theoretic control. Numerical experiments on vehicle platooning, inventory management, and network control illustrate resilience to misspecification, and also exhibit a "free-lunch" phenomenon in which strategic robustness can improve performance or social welfare.

math.OC · cs.GT · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16386

Remember What Changes the Odds: Critic-Gated Event Memory for Long-Horizon Manipulation

Xuanzhuo Liu, Chuankang Li, Maoqing Yao, Guanghui Ren

原文摘要

In long-horizon manipulation, a robot may need to take different actions under identical observations, depending on task progress and the outcomes of earlier attempts. We refer to this ambiguity as decision aliasing. Resolving it requires the policy to maintain memory of its execution history. To reduce the cost of processing full observation histories, recent methods build compact event memories using perceptual, semantic, or kinematic cues. However, these criteria may miss events that matter for task success. We instead propose an outcome-grounded principle: remember events that substantially change the predicted probability of eventual success. Following this principle, we introduce CGEM, a critic-gated event memory that uses a critic to select events with large estimated changes in success probability. Positive and negative changes are encoded as progress and failure records, respectively. Failure records are discarded once the corresponding subtask is completed. In a ten-subtask diagnostic environment with exactly computed success probabilities, CGEM achieves 88.0% success, compared with 0.0% for both a 36-step observation window and a kinematic event memory. Removing failure records reduces success to 1.7%.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16384

Beyond Compressing Everything: Contrastive Memory Learning for Selective Context Compression

Sikui Zhang, Haowei Liu, Ziyun Gan, Chunfeng Yuan, Guangze Gao, Nian Liu, Boyu Cai, Bo Li 等 12 位作者

原文摘要

As large language models (LLMs) advance toward increasingly long inputs, soft context compression offers a promising approach to efficient inference by converting long inputs into compact memory slots. Under limited memory budgets, effective context compression remains challenging because task-relevant evidence varies substantially across queries, ranging from localized evidence to multiple distant spans or information dispersed throughout the full document. Instead of compressing everything indiscriminately, we propose CoMem, a query-guided selective context compression framework that learns memory representations conditioned on both the document and the query. CoMem develops Contrastive Compressor Learning to achieve query-sensitive yet context-preserving memory representations. To inject a strong prior over query-dependent evidence distributions, we devise a same-context hard negative mining strategy by pairing a single document with multiple queries, requiring the compressor to selectively retain information according to each query's distinct evidence needs. To address the restricted information flow imposed by causal masking, we further enable bidirectional attention among memory slots. Experiments demonstrate that CoMem consistently outperforms existing context compression methods across compression ratios on question answering and RULER-NIAH benchmarks. Our code is available at https://github.com/scar-on/CoMem.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.11451

SAIL: Scientific Agentic Intelligence via a Science-Aware Loop

SAIL Model Team, Boyuan Sun, Bryan Dai, Che Liu, Chi Liu, Derek Li, Hongming Piao, Mengzhuo Chen 等 12 位作者

原文摘要

We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows. SAIL is developed through a science-aware improvement loop: agents built on frontier AI models analyze its task failures and construct training tasks that address the underlying capability gaps. The diagnosis examines search and evidence selection in literature tasks, scientific assumptions and reasoning in coding, and planning and revision in longer investigations. The agents draw on paper collections and scientific code repositories to build problems, interaction trajectories, and executable tasks with the required environments and tools. We repeat this loop over multiple development cycles and train SAIL through supervised fine-tuning, specialist training, multi-teacher on-policy distillation, and agentic reinforcement learning. SAIL achieves competitive performance across scientific research tasks with substantially fewer parameters than leading open-weight models.

cs.CL · cs.DL · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.23740

AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace

Seonglae Cho, Donghyun Lee

原文摘要

Concurrent multi-agent coding offers a division of labor across modules, robustness through redundancy and parallel exploration at the natural granularity of multi-file projects. Realtime collaborative editing protocols solve this coordination problem for human teams with Conflict-free Replicated Data Types (CRDTs), but the LLMs underneath generate one token at a time, and existing multi-agent coding systems inherit this serial limit, since they either sequence agents through phase handoffs or pool independent samples without coordination, and a single agent abandons up to half of hard tasks with a one-file stub-and-exit. AgentRoom is a realtime collaborative editing protocol for concurrent coding agents. Its runtime layer exposes file-level claim, status and broadcast as MCP tools on a CRDT-merged shared filesystem. Five frontier coding-CLI models ran four backend coding tasks, with cross-language checks in Python DevBench and Rust+axum. For CLI-stable models, AgentRoom with 2 agents abandons fewer tasks than Solo and varies less from run to run. At matched compute, one positive mean LLM-judge contrast puts AgentRoom over parallel-merge. The other contrast, a bundle probe, puts full AgentRoom above each partial case: an ordering rather than a percentage split. Coordination, not parallelism or CRDT-merge, is the key design choice.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.24937

Anatomy-Decomposed Chest Computed Tomography (CT) Projections as Scalable Supervision for Bone Suppression in Chest Radiographs

Mrunmay Angaitkar, Piyush Kumar, Aarjav Satia, Pranav Rao, Ashish Mittal, Manoj Tadepalli, Preetham Putha

原文摘要

Bone overlap can obscure abnormalities in chest radiographs, while scarce paired training data limit supervised bone suppression. We address this challenge with a digitally reconstructed radiograph (DRR) framework that converts chest computed tomography (CT) into paired supervision for component suppression. A novel bone segmentation algorithm enables CT decomposition into bone, non-lung soft-tissue, and lung components, which are projected separately. Their weighted combination yields synthetic radiographs with pixel-registered component images that sum exactly to the full DRR. Models trained on these data suppress bone or lung components by predicting the target component and recovering the remainder by subtraction, transferring to real radiographs without real paired training data. As an extension, their outputs on real radiographs provide target domains for unpaired, component-wise DRR translation, reducing the appearance gap while retaining anatomical details. Across multiple public datasets, downstream detection experiments demonstrate the utility of bone suppression, with gains concentrated on abnormalities with substantial bone overlap. Compared with open-source DRR engines applied to the same CTs, our unmodified DRRs achieve comparable realism and preservation of label-relevant anatomy, while translated DRRs achieve the best Fréchet inception distance (FID), lung-field sharpness, and agreement with source-CT anatomy among the evaluated methods. Models and inference code: https://huggingface.co/qureaiorg/bone-suppression ; Translated projections: https://huggingface.co/datasets/qureaiorg/ct2xr-projections.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16382

RADIANT: Redundancy-Aware Information Allocation for Universal Multi-Modal Fusion

Shenghai Wu, Yue Lin

原文摘要

Universal multi-modal fusion often fails not because modalities are insufficiently aligned, but because the fusion process allocates information poorly: redundant evidence is repeatedly amplified, modality-unique evidence is over-smoothed during alignment, and task-dependent synergistic evidence is insufficiently activated. We present RADIANT (Redundancy-Aware Dynamic Information Allocation Network), a task-general framework that organizes fusion around three complementary roles: suppressing redundant cross-modal overlap, preserving modality-unique evidence, and composing task-conditioned synergy through cross-modal interaction. Specifically, stable matrix-exponential projections are used to reduce interference among shared and modality-unique streams, while task memory with hard positive updates selects which synergistic interactions should be activated for the current fusion regime. Extensive experiments across six heterogeneous fusion tasks show consistent improvements over the compared methods. On FLIR, RADIANT improves downstream detection mAP@0.5 from 91.2% to 96.8%, a gain of 5.6 percentage points (6.1% relative) over GIF. RADIANT also exhibits strong direct cross-dataset transfer, with further gains from inference-time task-memory adaptation while keeping all network weights frozen. Additional ablations and sensitivity studies support the robustness of the allocation mechanism.

cs.CV · cs.MM

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16378

Evidence-Governed Adoption of Self-Generated Updates in Autonomous AI Agents

Subodh Lonkar

原文摘要

Autonomous agents modify prompts, memories, tools, workflows, and policies using interaction histories. Yet a plausible modification is not necessarily suitable for persistent adoption: candidate selection is adaptive, evaluators may be imperfect, and local gains can hide degradation against an earlier baseline. We introduce Evidence-Governed Evolution (EGE), a framework for governing adoption of self-generated agent modifications. EGE separates candidate generation from confirmatory adoption, evaluates frozen candidates on fresh paired audits, requires meaningful improvement on a prespecified primary objective, protects declared capabilities through reference-relative non-inferiority tests, and applies governance constraints before bounded canary deployment. We establish an evaluator-calibrated simultaneous lower-bound construction for a countable sequence of adaptively generated candidates. It combines candidate-wise Hoeffding bounds with independent calibration samples comparing the operational evaluator with a prespecified reference procedure. We also formalise reference replacement through bridge tests, derive a cumulative degradation bound along a versioned reference lineage, and provide an audit-planning condition relating effect-size margin, sample sizes, and acceptance probability. A Monte Carlo stress test illustrates calibration under candidate-dependent evaluator optimism; it is a stylised statistical experiment, not an evaluation of a deployed agent. The guarantees are conditional on bounded paired scores, fresh sampling, a valid reference-evaluation construct, and declared evaluation distributions; they do not establish universal agent safety or robustness to arbitrary distribution shift.

cs.AI · cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.16377

Universal optimality on finite Lee tori

Tao Zhang

原文摘要

We study subsets of finite Lee tori that minimize pair energy among sets of the same cardinality for every discretely completely monotone potential. At half occupancy on a product of even cycles, the two checkerboards minimize both total pair energy and maximum individual energy. They are the only minimizers for every nonconstant classical completely monotone potential on $(0,\infty)$, proving the checkerboard conjecture of Bouman, Draisma, and van Leeuwaarden for this class. At the independence number of the distance one graph on $\Z_q^n$, universally optimal sets exist exactly when $q$ is even, $q=3$, $n=1$, or $(q,n)=(5,2)$. In these cases they are precisely the maximum independent sets and form a single Lee isometry class. At density $1/5$ in $\Z_5^n$, $n\ge2$, universal optimality is characterized by a weighted count of pairs at distances one and two. We prove these results using integer box occupancy bounds that strengthen Fourier linear programming and, in the quinary case, Fourier certificates with a common zero set.

math.CO · cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.14856

RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction

Zilai Li

原文摘要

Semantic watermarks for diffusion models embed ownership information into the generative process while preserving perceptual quality, but Gaussian-Shading extraction conventionally requires multi-step diffusion inversion to recover the initial noise. Recent one-step methods show that this cost can be reduced substantially. We study this problem through extended flow matching and conditional regression. The key observation is that, near the high-SNR image endpoint, recovering a useful noise statistic given by the first-step output of the extended flow matching in the high-SNR regime is much simpler than reconstructing the full inverse trajectory, and Gaussian Shading only requires the recovered latent to remain in the correct watermark decision region. Based on this observation, we propose a lightweight, prompt-free extractor that decomposes endpoint recovery into an image-like anchor and a noise-oriented residual, which increases the capability of the model to utilize GPU parallel computation. The resulting method avoids iterative inversion and repeated evaluation of a diffusion-scale U-Net, providing an efficient one-step extraction pipeline with a concise theoretical interpretation. The computational cost of extracting noise is lower than that of both OSI and FARI. The github repo is there: https://github.com/TheLovesOfLadyPurple/RAIN-lightweight-NN-for-one-step-semantic-watermark-extraction

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.30768

CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy

Zekang Yang, Jiamin Li, Zhenghua Li, Jiaqi Fan, Zengcai Guo, Xiaolin Hu

原文摘要

Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved encouraging results on local image blocks, it remains unclear whether such progress translates to reconstruction that is both structurally accurate and scalable to the whole-brain scale. We present CORAL, the first benchmark for structure-aware evaluation of automatic neuron reconstruction from light microscopy images at both local and whole-brain scales. Built on a high-quality whole-brain fMOST dataset with carefully curated annotations, CORAL establishes two progressive tasks: block-level reconstruction, which evaluates reconstruction methods under limited spatial context, and brain-wide reconstruction, which assesses complete neuron reconstruction at the whole-brain scale. To account for topological correctness beyond geometric distance similarity, we introduce a structure-aware metric based on fiber prediction. To further achieve complete neuron reconstruction across the entire brain, we develop a brain-wide neuron tracing framework that extends arbitrary local reconstruction methods to the whole-brain scale through an iterative local-to-global process. Using this benchmark, we provide the first structure-aware comparison of mainstream methods for local neuron reconstruction and further evaluate their performance in brain-wide reconstruction. Our results underscore the importance of structure-aware evaluation and the need for more robust methods for complete neuron reconstruction.

cs.CV

查看论文
arXiv ↗PDF ↗