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

+0新增论文
+0其中 AI 相关
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-08 00:56 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-07 01:43 — 2026-11-08 01:43（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：2026-11-08 00:56最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,056 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-08 00:54（北京时间）
新论文 · v1arXiv:2611.05605

Transport along Local Annealing Paths: Wasserstein Geometry and Multimodal Sampling

Han Chen, Sifan Liu

原文摘要

Variational approaches to learning transport maps for multimodal sampling can suffer from mode collapse. One way to mitigate this problem is to learn transport along a prescribed path of intermediate distributions defined by geometric annealing. We show that annealing can take a substantial detour in Wasserstein space: when mass moves between modes, the path can be much longer than the distance between its endpoints. We further link path geometry to transport learning, showing that long annealing paths can slow population optimization, while sufficiently regular paths permit rapid convergence. Motivated by these findings, we propose componentwise annealed transport (CAT) to reduce the need for mass transfer between modes. Starting from a mode-informed mixture reference, CAT constructs an exact mixture decomposition of the target and learns separate transport maps along componentwise annealing paths. We estimate the component weights separately and show that these estimates remain consistent even when the learned flows are inexact. We also develop adaptive annealing schedules guided by transport effort. Experiments on multimodal synthetic distributions and Bayesian inference problems demonstrate improvements in transport learning and sampling efficiency.

cs.LG · stat.CO · stat.ML

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.23394

Markov State-Space Modeling and Channel Characterization for DNA-Based Molecular Communication

Ruifeng Zheng, Zhihan Xu, Veronika Volkova, Pengjie Zhou, Martín Schottlender, Juan A. Cabrera, Frank H. P. Fitzek, Pit Hofmann

原文摘要

DNA-based molecular communication with microarray-style reception under reversible hybridization is of interest for emerging DNA-enabled sensing and Internet of Bio-Nano Things (IoBNT) systems. In such channels, the bound-state observation exhibits both inter-symbol interference (ISI) and colored counting noise. To capture these effects in a communication-oriented form, we develop a Markov state-space framework based on a voxelized reaction-diffusion model, in which a block-structured transition matrix describes molecular transport and binding/unbinding dynamics. For the microarray specialization, this representation yields the channel impulse response (CIR), the equilibrium gain, and a settling-time-based characterization of the effective channel memory. Building on the resulting symbol-rate observation model for on-off keying, we derive a grouped-binomial counting model and obtain a closed-form expression for the covariance of the counting noise. Based on these statistics, we further develop a differential-threshold detector and a finite-memory decision-feedback equalizer and benchmark them against a symbol-by-symbol maximum a posteriori detector with decision feedback (MAP-DF). Numerical results validate the theoretical correlation behavior and show that the relative performance of the proposed receivers depends strongly on the channel-memory regime.

eess.SP · cs.ET

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.02523

Approximating two-terminal network reliability

Weiming Feng, Yucheng Fu, Heng Guo

原文摘要

We present fully polynomial-time randomised approximation schemes (FPRAS) for the two-terminal reliability problem on general graphs, both directed and undirected. For directed graphs with $n$ vertices and $m$ arcs, the running time is $\widetilde{O}(nm\varepsilon^{-2})$, where $\varepsilon$ is the relative error. For undirected graphs with $n$ vertices and $m$ edges, it runs in $\widetilde{O}(m+n^2\varepsilon^{-2})$. We also show that the complementary unreliability problem is #BIS-hard.

cs.DS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.03623

Thought-deciphering via hierarchical EEG-to-text alignment

Xiaopeng Mao, Morten Mørup, Xin Xu, Sang Wan Lee, Sadasivan Puthusserypady

原文摘要

Non-invasive brain-to-text interfaces offer alternative communication pathways for people with communication disabilities. However, sentence-level decoding from electroencephalography (EEG) remains challenging. We propose a hierarchical EEG-text alignment framework that retrieves sentences by progressively decoding coarse-grained semantic information and fine-grained sentence representations. We hypothesize that broader semantic context can be more reliably captured from EEG than individual sentences. Accordingly, EEG representations are first aligned with semantic classes, followed by sentence retrieval within the predicted class. Among over 2,000 unique text samples, our approach achieves average top-5 and top-10 retrieval accuracies of 62.6\% $\pm$ 1.0\% and 83.5\% $\pm$ 1.0\%, respectively, compared with 50.3\% $\pm$ 2.3\% and 68.3\% $\pm$ 2.0\% for direct EEG-sentence alignment. Qualitative analysis further reveals that decoding performance depends strongly on textual context. These findings demonstrate the potential of hierarchical semantic alignment for improving sentence-level EEG-to-text decoding.

cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.26969

Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling

Alan Zhu, Mihran Miroyan, Carolyn Wang, Andrew Zhou, Lisa Dunlap, Narges Norouzi, Joseph E. Gonzalez

原文摘要

User modeling aims to use language models (LMs) to mimic an individual's behavior from a corpus of past context-action pairs (e.g., conversation turns), enabling the simulation of users in settings like behavioral science, human-AI collaboration, and market research. Recent approaches augment these corpora with synthesized reasoning traces, typically generated by conditioning on both context and action. However, action-conditioned traces are post-hoc rationalizations and need not reflect the user's underlying decision process. We propose Recon, which uses action reconstruction to score reasoning traces by their predictive power: given a context and candidate reasoning, a reconstruction model predicts the action, and reconstruction fidelity determines reasoning quality. Across four domains, Recon achieves a 54.7% win rate over Backward Synthesis, a standard post-hoc rationalization baseline. Further, we find that training a reasoning synthesis model with rewards derived from Recon improves downstream user modeling performance, achieving a win rate of up to 70.0% over baselines. We further show that Recon-synthesized reasoning transfers across models, and improves user modeling beyond the reconstruction model. Our work demonstrates that post-hoc rationalization is insufficient for reasoning synthesis, and that useful and interpretable reasoning should naturally elicit the action from the context.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05602

Private Online Release of Adaptive Linear Queries

Aleksandar Nikolov, Haohua Tang

原文摘要

In this paper we study answering counting and other linear queries online under differential privacy constraints. Recent work by Nikolov, Tang, and Ullman [STOC 2026] gave the first online algorithm that answers \emph{obliviously chosen} online linear queries privately, and achieves poly-logarithmic competitiveness against an optimal offline factorization mechanism. This also implied poly-logarithmic competitiveness against arbitrary private offline mechanisms when the private dataset is large enough. The error guarantees of their algorithm, however, can fail when the queries are adaptive. We give a new algorithm that also achieves poly-logarithmic competitiveness, while being able to handle \emph{adaptively chosen} queries. This implies that there is no large separation between the optimal error bounds for privately answering, respectively, offline linear queries, obliviously chosen online linear queries, and adaptively chosen online linear queries. Our algorithm combines the online factorization approach from prior work with a novel layered Euclidean iterative database construction, presenting a new way to use factorization in private algorithms. We also give a lower bound that shows that some poly-logarithmic factor in the competitive ratio is unavoidable. Our lower bound first shows that any interactive private mechanism implies a deterministic online factorization algorithm, and then gives a new lower bound for the competitive ratio of any deterministic online factorization algorithm.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05601

RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents

AL Muqshith Mohammed Shifan, Kevin Christopher Chua, Ali Neshati, Loutfouz Zaman, Cristiano Politowski

原文摘要

A deep RL agent trained on a fixed persona reward plays one way: an Explorer keeps exploring while starving, a Survivor hoards on an empty map. Since each persona fixes its own reward, automated playtesting trains N agents for N styles. Changing reward composition mid-episode runs into the switching-stability dilemma: PPO degrades under non-stationary rewards. We present RIDGE, a single-agent architecture that sidesteps the dilemma with two design choices: a state-conditioned blender that computes softmax-normalized sigmoid weights from slow-moving state variables, and a multi-head critic that trains one value head per persona on its own stationary signal. On Crafter with four personas, one \ridge agent acquires both branches of the wood-tier crafting/combat split that no fixed-persona baseline solves jointly, and a sharpness ablation confirms state-conditioning drives the gain. We position these results as demonstrations of the blending mechanism's dynamics across n=3 seeds per condition; larger multi-seed sweeps remain future work.

cs.LG · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05599

CAPTOR: text-encoder-free grounding by counting caption co-occurrence over the visual words of a frozen encoder

Elad Yoshai, Natan T. Shaked

原文摘要

Grounding a text query in an image needs a matrix scoring every term against every patch. Vision-language models compute it with an aligned text encoder, which many image encoders, such as histopathology-related models trained on slides alone, lack. The Caption-Anchored Patch-Term Occurrence Representation (CAPTOR) estimates the matrix without a text encoder. It clusters a frozen image encoder's patch tokens into visual words and describes each captioned image by its share of patches in each word. A term signature is the standardized difference of those shares between images whose captions mention the term and the rest. The matrix factorizes into a term-by-word table and a query-independent image factor, so an image is encoded once and a new term adds one table row. Against every training-free baseline, CAPTOR leads on Common Objects in Context (COCO), Pascal Visual Object Classes (VOC) and Cityscapes. On COCO, scored on the cells one object owns, it reaches 0.565 mean intersection over union (mIoU) against 0.502. On all three, it is also level with a text alignment trained on the same backbone, which needs gradients, a text encoder and several times the captions. On held-out breast-cancer slides, it exceeds the strongest baseline scoring patches with a pathology text encoder by 0.160 mIoU. Read through CAPTOR, UNI, an encoder trained on slides alone, exceeds such baselines by 0.132 on a common grid. Counting can therefore give a text interface to any image encoder trained without language, wherever captioned images exist.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05598

Fast Quantum Byzantine Agreement with Nearly Linear Quantum Communication

Jan Olkowski

原文摘要

We consider synchronous binary Byzantine agreement among $n$ processes connected by authenticated point-to-point classical and quantum channels. The adversary is computationally unbounded, sees all classical information, adaptively corrupts up to $t\le(1/3-\varepsilon)n$ processes, and may suppress messages sent by a process in the round in which it is corrupted. We give a quantum algorithm that solves Byzantine agreement in this model with probability $1$. It uses $O(\log^4 n)$ rounds, $O(n\log^8 n)$ qubits, and $O(n^2\log^8 n)$ classical bits in expectation, with constants depending on $\varepsilon$. This reduces the quantum communication of the protocol of Ben-Or and Hassidim (STOC~2005), which achieves $O(1)$ expected rounds but whose Byzantine coin implementation requires $Ω(n^4\log n)$ qubits and classical bits. We also extend the quadratic message lower bound of Abraham et al.\ (PODC~2019) to quantum channels, obtaining an $Ω(t^2)$ lower bound on worst-case expected total communication. For $t=Θ(n)$, the communication and round complexity of our algorithm are therefore optimal up to polylogarithmic factors.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05596

RAGCompass: Generalizable Retriever Routing via Reranking

Valentin Six, Mufei Li, Dongqi Fu, Yinglong Xia, Hong Li, Pan Li

原文摘要

Different retrievers exist for retrieval-augmented generation, yet none performs best for all queries. Therefore, the key question is: given a query and retrieved passages from different retrievers, which one is most suited for that query? Existing routers usually make predictions from query-specific features and a fixed pool of retrievers; such routers have no output for an unseen retriever and are incapable by design on a new corpus. To fill these gaps, RAGCompass reads the retrieved passage sets themselves: passages from an unfamiliar retriever or corpus stay directly comparable to other passages, so routing stays well designed where a query-only map would fail. We contrastively fine-tune a reranker against the answer each evidence set produces, which accounts for most of the gain; a small comparison head adds a moderate improvement, and neither component has retriever-specific parameters. RAGCompass improves answer F1 by 28% relative to the best fixed retriever, and outperforms fusion baselines, three query-only routers, and a prompted 8B language model. Generalization experiments show that RAGCompass keeps most of its gain under an unseen corpus, retriever, or reader, while query-only baselines fall to the best fixed retriever or below.

cs.CL · cs.IR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.10822

Benchmarking Sensor-Fault Robustness in Forecasting

Alexander Windmann, Philipp Wittenberg, Gianluca Manca, Marcel Dix, Jens U. Brandt, Oliver Niggemann

原文摘要

Cyber-physical system (CPS) forecasting models depend on sensor streams with noisy, biased, missing, or temporally misaligned readings, yet standard forecasting evaluation often selects models by nominal error without showing whether they remain robust under such faults. We introduce SensorFault-Bench, a CPS-grounded protocol that evaluates forecasting architectures and robustness-improvement methods through controlled synthetic stress tests of isolated input faults, together with an operational taxonomy of the methods. Across four real-world datasets and eight scored scenarios governed by a standardized severity model, it reports worst-scenario degradation, clean mean squared error (MSE), and worst-scenario fault-time MSE, separating relative robustness from absolute error. Explicit fault-training methods train on adjacent fault families disjoint from the scored scenarios. Empirically, forecasting architectures favored by clean MSE can degrade sharply under faults, and clean-MSE rankings can disagree with worst-scenario fault-time error rankings. Chronos-2, the evaluated zero-shot foundation model, matches or trails the last-value naive forecaster in clean MSE on the two single-target datasets and has the largest worst-scenario degradation on ETTh1 and Traffic, where all channels are forecast targets. For the evaluated robustness-improvement method set, paired deltas show selective degradation reductions: projected gradient descent adversarial training and randomized training lead where value faults dominate observed degradation, and fault augmentation leads on Traffic, where availability faults dominate. High degradation reveals fault sensitivity that clean MSE misses, while low degradation supports robustness only within the evaluated scenarios. The benchmark therefore screens forecasters before use in a specific deployment, which requires validation against its recorded faults.

cs.LG · eess.SP

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08605

Lattice Deduction Transformers

Liam Davis, Leopold Haller, Alberto Alfarano, Mark Santolucito

原文摘要

We introduce the Lattice Deduction Transformer (LDT), a recurrent transformer that approximates logically sound deduction by projecting its latent state through a lattice between forward passes. We train on-policy in a process that mirrors deduction in a search-based constraint solver and supervise training via a domain-agnostic approximation of the set of solution candidates based on abstract interpretation. An $800$K-parameter LDT outperforms prior small recurrent reasoners on Sudoku-Extreme with under $2\%$ of their estimated training FLOPs, solving $99.999\%$ of the $422{,}786$ test puzzles. The model is nearly always sound, in that it gives a wrong answer for $4$ of $1.27$M puzzle evaluations, and otherwise returns a correct answer or abstains. A $1.8$M-parameter LDT variant reaches $99.8\%$ accuracy on Maze-Hard. Our code is available at github.com/lcrh/lattice-deduction-transformers.

cs.LG · cs.AI · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05594

Relevance Propagation as Entropic Optimal Transport on Filippov Neural Networks: Sinkhorn Propagation and Region Relevance in Image Classifiers

Olivier Gibaru, Eric Nyiri

原文摘要

Relevance propagation, which redistributes a network's prediction backward through the layers, is usually treated as a heuristic. We show that it is the solution of a single variational problem: Layer-wise Relevance Propagation (LRP) is the divergence-free flow on the active computational graph of zero relative entropy to the backward transition law of the forward activation flow; for a non-negative reference, this is a relative entropy between Markov measures on backward paths. The rules LRP$_0$, LRP$_{z^+}$ and LRP$_{α,β}$ follow from this principle by the choice of a reference, and are instances of one rule, LRPN$_{α,β}$, whose weights may vary from node to node, for instance with the node's activity, in the spirit of Hebb's principle. The principle rests on a measure-theoretic formalization of feed-forward networks as directed acyclic graphs of Filippov operators, which covers piecewise-smooth and discontinuous architectures (e.g. hard-routed Mixture-of-Experts) with a Clarke-Filippov generalized-gradient calculus; it also characterizes backpropagation as the adjoint equation of a Lagrangian relaxation. On networks of ReLU and max-pooling nodes, LRP$_0$ is Gradient$\times$Input, with an explicit jump across a kink where LRP$_{z^+}$ stays continuous. Taking the entropy edge by edge yields a new rule, Sinkhorn Relevance Propagation. Aggregated over an input region, the flow of a non-negative reference tells, with exact accounting, which hidden units carry its evidence, the conditioned flow being a Schrödinger bridge. On VGG-16, the conservation identities hold to round-off, and the rules are told apart by the sign of their maps, the share of the output left to the bias nodes, faithfulness, localization and class dependence; on ConvNeXt-Tiny, LRPN$_{α,β}$ conserves the output and its Hebbian weights give the highest ABPC of the rules tested.

cs.LG · cs.CV · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2603.14689

Less Is Harder Than More: Proving Unnecessary Complexity

Tristan Simas

原文摘要

When can a sensor, feature, or API field be removed without changing a fixed system's decisions? We require the remaining inputs to recover its complete optimal-action set, including ties, at every admitted state. Admitting every input combination guarantees one smallest preserving set. Yet checking one deletion is coNP-complete when circuits give utilities on Boolean products, even with two actions and at most two optimal-action sets. Missing combinations permit alternative preserving sets, so an auditor must choose inputs within budget and check the chosen set. Requiring every declared reading to have a positive-probability state adds a support check. We classify choosing and checking exactly for circuit-defined Boolean models, with and without the support requirement. A unique winner after averaging hidden states can still change the original decisions. Certifying such winners requires weighted score comparisons: finding inputs within budget is $\mathsf{NP}^{(\mathsf{NP}^{\mathsf{PP}})}$-complete even with two actions and independent uniform inputs. Explicit tables admit logarithmic approximation of the minimum preserving input count; succinct Boolean products admit no polynomial-time $o(Λ/\logΛ)$ approximation in total encoded length $Λ$, unless $\mathsf P=\mathsf{NP}$. Supplied decompositions and symmetry proofs can make audits polynomial-time; discovery and validation are additional work. For a frozen digit classifier, eleven blocks suffice on held-out rows but fifteen are needed on the full product; four conflicting pairs expose the gap. Building the required response from retained inputs establishes sufficiency, not minimality. Preserve the structure that makes the dependence checkable.

cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.21095

Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems

Balkrishna Giri, Md Toufique Hasan, Jussi Rasku, Muhammad Waseem, Pekka Abrahamsson

原文摘要

Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge, but RAG systems usually trust whatever they retrieve, creating a Security-Reliability Gap: high semantic relevance does not guarantee factual truth. Adversaries exploit this through knowledge poisoning, inserting malicious documents to cause targeted misinformation. We propose an Evaluation Agent, middleware that combines Natural Language Inference (NLI) factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index T = 0.4 F + 0.35 C + 0.25 (1 - P ) with a non-linear dampener for high-contamination contexts. On TruthfulQA with Llama 3.3 70B, the agent reaches 91% accuracy and 100% precision, with 100% recall on instruction injection, while in-place edits, such as entity swaps, remain hard to detect. Across three LLMs the Trust Index stays discriminative, with a Receiver Operating Characteristic Area Under the Curve (ROC-AUC) of 0.73 to 0.81; generation style matters more than model size, and per-LLM threshold calibration restores baseline competitive accuracy, whereas a weaker FEVER result shows that cross-dataset generalization requires domain-specific calibration. In a software-engineering use case, a secure-coding assistant over guidance from the Open Worldwide Application Security Project (OWASP) Top 10 and the Common Weakness Enumeration (CWE), the agent reliably blocks instruction injection of unsafe advice (F1 92%), while contradiction and subtle semantic weakening remain hard. Throughout, the agent measures detection of poisoned context before generation, not whether the LLM adopts the injected misinformation. We release the proposed approach, attack generator, and experimental artifacts at the link: https://github.com/GPT-Laboratory/TrustworthyRAG.

cs.SE · cs.AI · cs.CL · cs.CR · cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05593

GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats

Shahaf Valencia Levy, Sagie Benaim

原文摘要

Can a neural network learn to render 3D Gaussian splats on its own, with no rasterizer in the renderer? We present GaussianRenderFormer, a transformer that takes a set of Gaussians and a camera and outputs the image directly. Each Gaussian becomes one token in a view-independent encoder, and a view-dependent decoder turns small patches of camera rays into pixels by attending to those tokens. Trained on 26,820 Objaverse objects pruned to 20,000 Gaussians each, GaussianRenderFormer renders 300 unseen objects at 38.08 dB PSNR against the full, unpruned splats, while rasterizing the same pruned input reaches 44.02 dB. The gap is not one of generalization, and our diagnostics are consistent with a bottleneck in the view decoder: telling it the projected footprint of each Gaussian, which it could in principle infer, adds 1.4 dB. Under-training is not ruled out. Code, trained models and videos: https://svlwoof.github.io/gaussianrenderformer

cs.CV · cs.GR · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.12642

PriMoRetarget: Humanoid Motion Transfer Through Prioritized Motion Retargeting

Nicholas Ioannidis, Dun Yang, Max Smith, Tue Vu, Ziyu Zhang, Ali Agha, Shayegan Omidshafiei, Xue Bin Peng

原文摘要

Motion retargeting is a critical preprocessing step for transferring human motion data to humanoid robots. While existing methods are effective for single-character motions, interactions involving multiple characters and objects introduce additional contacts and spatial relationships that must be preserved. Retargeting is commonly formulated as a weighted multi-objective optimization problem, where conflicting objectives can require careful tuning of relative weights and can still compromise important motion characteristics. We introduce PriMoRetarget, a prioritized motion-retargeting framework that replaces relative objective weighting with an explicit priority hierarchy. Lower-priority updates are constrained to preserve higher-priority objectives, allowing critical characteristics such as foot placement and interaction contacts to take precedence over lower-priority pose objectives. The method is evaluated on four datasets spanning single-character motion, character-object manipulation, and character-character interactions. The resulting motions better preserve task-relevant interactions and provide reference trajectories that can be tracked more reliably than those produced by widely used retargeting methods.

cs.RO · cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05591

C-GRPO: Conformal Group Relative Policy Optimization

Arya Fayyazi, Seyedarmin Azizi, Mehdi Kamal, Massoud Pedram

原文摘要

Reasoning-oriented language model training increasingly relies on multiple on-policy rollouts, but standard Group Relative Policy Optimization (GRPO) uses a fixed group size, wasting compute on easy prompts and under-exploring hard ones. Existing adaptive-budget methods alleviate this inefficiency, yet their stopping rules are heuristic and do not provide a finite-sample calibration guarantee. We propose CGRPO, which replaces the fixed rollout budget of standard GPRO with calibrated conformal thresholds over task-specific nonconformity scores, combining Adaptive Prediction Set (APS)-style calibration for closed-form reasoning, a first-success score for execution-based code, automatic miscoverage selection, and periodic re-calibration. We prove finite-sample coverage for the resulting stopping rule and show that, under monotone policy improvement, recalibration induces a non-increasing expected training budget. Across six benchmarks spanning mathematics, graduate-level science, and code generation, CGRPO reduces mean training rollouts by 49-70% relative to fixed-budget GRPO while retaining strong fixed-budget accuracy, achieves the strongest pass@1 among evaluated static and dynamic baselines on different datasets, and transfers across model families with up to 82% rollout savings.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.16951

The Little Scientist: What Does the Scientific Method Buy an LLM Agent?

Travis Smith

原文摘要

Scientific discovery emerges from cycles of hypothesis, implementation, empirical testing, and feedback. Can this process be automated? We approach automated algorithm design through the lens of the scientific method, where an LLM-based agent goes through each step of the process in an iterative fashion. Results: We present The Little Scientist, a framework that maps the scientific method onto an LLM agent in a loop: a Scientist agent iterates hypothesis, prediction, code, test, and reconciliation inside an evaluation environment that returns structured diagnostics, and a Kuhn agent injects paradigm-shifting reframings at plateaus. On DNA motif discovery, the process wrote an algorithm from scratch (DALE) that outperforms STREME across 132 ENCODE transcription factors on the shuffled-negative benchmark (mean AUROC 0.842 vs. 0.803) while running 11x faster. We then asked why this method worked, and that question became the paper's scientific core: a preregistered, controlled teardown of the framework's own scaffolding consisting of ten ablation arms against one-shot bandit nulls. The answer overturned the premise. Seven of ten loop arms fail to beat a bandit drawing samples from the same model and prompt, the full scaffold performs below blind sampling at 7-8x the token cost, and a floor-prompt arm with no framework at all wins on both score and value per token. On a held-out genomic benchmark, the best loop artifact and the best bandit draw agree to within 0.002, and the DALE algorithm from the initial experiment scored similarly. The convergent picture is that LLM agents do not reason their way past what training placed in the weights. Autoresearch, on this evidence, is sampling, selection, and remixing, which is the bet the Evolve-family architectures made when they chose populations and external selection over scratchpad reasoning, and why those choices were right.

q-bio.QM · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.23479

HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World

Hongcheng Gao, Jianshu Zeng, Alex Zhou, Shijia Ge, Xuan Shangguan, Yazhe Wang, Yexing Wan, Zelin Zheng 等 16 位作者

原文摘要

Agents built on vision language models (VLMs) now control robots by writing code, but the strongest of them refine task-specific code over many rounds of trial and revision. Such code tends to overfit the benchmark on which it was tuned, can exploit the benchmark's shortcuts, and is costly to carry over to a new benchmark or robot. We present HexaShell, a thin, task-agnostic harness designed to test how far general tools can go instead. We design a simple and complete set of 14 basic tools, 4 for motion, 5 for perception and 5 for state, which the agent calls in one Python cell per turn. Perception pairs SAM 3, which segments an object from a few words or a click, with NumPy and OpenCV geometry that turns its outlines in several cameras, or a depth image, into its position, size and grasp angle. The API, agent loop and sandbox are shared across all tasks; a new simulator or robot needs only an adapter of 350 to 1,450 lines and a prompt describing its world, and the only task-specific input is an optional skill of about a page of guidance. The same code runs on four simulated benchmarks, built on three simulators with two kinds of arm, and on real robots. With GPT-6-Astra and no task-specific input, HexaShell reaches success rates of 69.9% on RoboDojo, 59.3% on RoboCasa365, 78.3% on LIBERO-PRO and 82.2% on RoboTwin 2.0. With task skills, it reaches 85.0% (score 88.8), 85.6%, 96.7% and 96.8%, respectively, above the best published result we are aware of on each benchmark. The RoboCasa365 result is listed first on its leaderboard. On real dual-arm robots, HexaShell succeeds in 76 of 90 episodes across nine tasks.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05590

Verified but Vacuous: Three Failure Surfaces of LLM-Driven Verified Code Generation

Aditya Vempaty, Himaneesh Sompalle, Manan Tayal, Mowafak Allaham, Prasenjit Dey, Ashish Jagmohan, Ravi Kokku

原文摘要

What should ``verified'' mean when evaluating LLM-generated code? Many existing pipelines report a single verification number. We argue this collapses three distinct properties measured in a conditional audit sequence: verifier acceptance (Surface A), \emph{syntactic specification binding (Surface B: does the proof obligation bind to the spec?), and \emph{semantic specification fidelity} (Surface C: does the spec capture the informal requirement?). Two empirical demonstrations show the surfaces separate. \textbf{First ($A \neq B$), via Li@Opus (a same-model reproduction of \citet{li2025dafny}'s Dafny-as-intermediate-representation (IR) pipeline under Claude Opus 4.7) on three Python benchmarks}: it reaches \textbf{99.1\% verifier acceptance} on HumanEval while only \textbf{1.9\%} carry a certificate binding to a spec-defined predicate or function. \textbf{Second ($B \neq C$), via VCG on two Rust benchmarks}: we use VCG (which is our own in-house Dafny-as-intermediate pipeline) on Rust because the Rust target lets us enforce fully-verifiable output (every component ships as a Dafny certificate, ensures-binding gate passing by construction). Even inside that construction, \textbf{11.48\% (MBPP-Rust) and 14.82\% (VeriContest LC slice) of structurally-verified samples still fail hidden tests}. On the LC slice of VeriContest, \textbf{VCG's reported End2End rate is 7.79\% (535/6870).} The cited external rates are 5.51\% (GPT-5.5) and 1.88\% (single-shot Opus 4.7). These give descriptive differences of 2.3 percentage points and 4.14$\times$, respectively; task-budget, repair and harness differences prevent a matched-performance claim.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2508.06199

Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning

Mateusz Praski, Jakub Adamczyk, Wojciech Czech

原文摘要

Pretrained molecular embedding models spanning graph neural networks, text transformers, and hybrid architectures have been widely used in drug discovery, yet no large-scale, rigorous comparison of their representations existed. We evaluated 28 models across 25 classification datasets under a controlled framework using hierarchical Bayesian Bradley-Terry statistical testing. All neural models except CheMeleon failed to outperform the classical ECFP count fingerprint; CheMeleon was the only model rated as better. However, further testing on external validation datasets, based on scaffold cross-validation and a Bayesian hierarchical correlated t-test, revealed no definite advantage of either embedding method. As a practical takeaway, we recommend evaluating both ECFP fingerprints and CheMeleon embeddings in novel QSAR/QSPR studies. Overall, in the context of all neural networks evaluated, these results also challenge the perceived progress in molecular representation learning and highlight the need for rigorous evaluation standards in the field.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2508.01128

When Reviews Are Scarce: Structure-Aware Review Imputation for Recommendation in Realistic Sparse Review Settings

Leyao Wang, Xutao Mao, Qinwen Ge, Xuhui Zhan, Yuying Zhao, Bo Ni, Ryan A. Rossi, Nesreen K. Ahmed 等 9 位作者

原文摘要

Textual reviews enrich recommender systems with fine-grained preference signals and enhanced explainability. However, in real-world scenarios, users rarely leave reviews, resulting in severe sparsity that undermines the effectiveness of review-aware recommenders under partial observability. A natural remedy is to synthesize the missing reviews to restore the textual signal these recommenders rely on. Yet, conventional imputation techniques, such as matrix completion and LLM-based augmentation, either lose contextualized semantics by embedding texts into vectors or overlook structural dependencies on the user-item graph. To address these shortcomings, we propose TWISTER (ToWards Imputation on Sparsity with Textual Edge Graph Representation), a unified framework for sparse-text recommendation that synthesizes missing reviews by jointly modeling semantic and structural signals. Specifically, we represent user-item interactions as a Textual-Edge Graph (TEG), treating reviews as edge attributes. To capture relational context, we construct line-graph views and employ an LLM as a graph-aware aggregator. For each interaction lacking a textual review, our model aggregates natural-language representations from neighboring interactions to generate a coherent and personalized review. Experiments on multiple datasets show that TWISTER consistently outperforms traditional numeric, graph-based, and LLM baselines, delivering higher-quality imputed reviews and, more importantly, improved downstream recommendation. In summary, TWISTER is a drop-in, structure-aware imputer that recovers the textual signal that review-aware recommenders need when reviews are scarce.

cs.IR · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05587

Cibersapiens: Gamifying Cybersecurity Education to Engage Secondary Students

Soraya Frías-Guadalupe, Pedro Paredes, Carlos Castaneda-Marroquín

原文摘要

Cybersecurity education and awareness are often tailored for businesses, leaving general citizens, especially young people, unprepared. Despite the availability of educational resources, cybersecurity training is not provided equally to all individuals, particularly children and teenagers. As digital risks such as sexting, grooming, and cyberbullying, among others, increase, young users remain vulnerable. However, existing awareness efforts fail to engage them effectively and current content lacks the motivation needed to drive meaningful behavioral change. This paper introduces "Cibersapiens: Digital Well-being for a Connected Generation," an interactive, gamified environment designed to teach cybersecurity to secondary school students. The project focuses on developing and implementing gamified educational resources that actively engage students, improve their understanding of cyber risks, and promote best practices in digital security. By leveraging active learning methodologies, this approach transforms cybersecurity education into an engaging and meaningful experience.

cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05586

Anduin: A sybil-resistant agentic marketplace reputation system

Reza Ramji, Preston Vander Vos, Ziming Zeng, Duc V. Le

原文摘要

As autonomous AI agents enter permissionless onchain markets, selecting new service providers remains a core challenge. Existing reputation systems depend on scarce resources like human curation, identity credentials, or voluntary reviews, while naive volume rankings are vulnerable to Sybil attacks. We evaluate whether existing onchain payment histories can yield provider ratings that are resilient against Sybil attacks. Using a 157-day dataset comprising 66M agentic transactions worth $6.1M across 16 blockchains, we model payment flows as a bipartite graph between buyers and providers. A provider's rating is derived from graph paths linked to a buyer's existing trusted network. We propose three Sybil-resistant rating algorithms: a max-flow rating and two relaxed algorithms optimized for stronger rating performance. Evaluating these algorithms against simulated adversaries across 813 buyers, we show that rating manipulation costs 20% of those buyers' total spend and is around 23x harder to manipulate than the standard similarity rule (collaborative filtering).

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05585

Contact-Implicit Whole-Body Trajectory Optimization for Dynamic Humanoid Locomotion on Parameterizable Uneven Terrain

Roberto Mauceri, Stefano Dafarra, Giulio Romualdi, Marco Gabiccini, Daniele Pucci

原文摘要

This letter presents a trajectory planner for humanoid robots to perform dynamic motions on complex, parameterizable terrains using a contact-implicit whole-body optimization framework. The planner generates feasible movements without predefined contact sequences, considering the robot's full dynamics and kinematics. To plan bipedal locomotion on steps, ramps, and other terrains, we propose a mathematical model to approximate ground geometry with a smooth surface. The rigid interaction between the robot and the ground is modeled via novel contact constraints, extending the domain of applicability from flat and horizontal surfaces to any arbitrary smooth surface. Effectiveness is demonstrated using nonlinear programming to plan motions on various terrain topologies. We also explore dynamic trajectory generation by embedding high-level requirements in the cost function and the initial guess. Preliminary feasibility tests were conducted over non-coplanar terrains, both in simulation and on the real robot ErgoCub.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.08517

Learning vs. Optimizing Bidders in Budgeted Auctions

Giannis Fikioris, Balasubramanian Sivan, Éva Tardos

原文摘要

The study of repeated interactions between a learner and a utility-maximizing optimizer has yielded deep insights into the manipulability of learning algorithms. However, existing literature primarily focuses on independent, unlinked rounds, largely ignoring the ubiquitous practical reality of budget constraints. In this paper, we study this interaction in repeated second-price auctions in a Bayesian setting between a learning agent and a strategic agent, both subject to strict budget constraints, showing that such cross-round constraints fundamentally alter the strategic landscape. First, we generalize the classic Stackelberg equilibrium to the Budgeted Stackelberg Equilibrium. We prove that an optimizer's optimal strategy in a budgeted setting requires time-multiplexing; for a $k$-dimensional budget constraint, the optimal strategy strictly decomposes into up to $k+1$ distinct phases, with each phase employing a possibly unique mixed strategy (the case of $k=0$ recovers the classic Stackelberg equilibrium where the optimizer repeatedly uses a single mixed strategy). Second, we address the intriguing question of non-manipulability. We prove that when the learner employs a standard Proportional controller (the "P" of the PID-controller) to pace their bids, the optimizer's utility is upper bounded by their objective value in the Budgeted Stackelberg Equilibrium baseline. By bounding the dynamics of the PID controller via a novel analysis, our results establish that this widely used control-theoretic heuristic is actually strategically robust.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05582

Exploring the Privacy--Size Tradeoff for Differentially Private Self-Attentive Variational Autoencoders

Rohit Sadavarte, Dhruvi Kothari, Sparsh Gupta, Eric Van Oeveren

原文摘要

Data tends to be most useful when it is shared, and the data most worth sharing is often the data that privacy obligations restrict. Synthetic data from a generator trained under differential privacy (DP) is one way to reconcile the two, but its utility depends on the privacy budget $\varepsilon$ and on how much data the generator sees - a parameter that most data sharing applications of synthetic data control. We present SAVANT, a self-attentive variational autoencoder for tabular data trained with DP-SGD that, to our knowledge, is the first to combine attention, a VAE, and DP in one tabular model. We evaluate it against two marginal mechanisms, PrivBayes and MST, jointly over the privacy budget and the dataset size on two public datasets, measuring the utility a downstream classifier loses by training on synthetic rather than real data. We find that, under the same DP guarantee, more data generally means more utility. For the marginal mechanisms it absorbs most of what a strict budget costs, and a noise-scaling argument suggests DP-SGD exchanges data fo budget at a worse rate. Two independent membership-inference attacks, judged against a measured null, found no aggregate membership signal.

cs.LG · cs.CE · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.08901

Mitigating Memorization Where It Happens

Xuanqi Zhang, Haoyang Shang, Xiaoxiao Li

原文摘要

Large language models (LLMs) can memorize and reproduce training sequences verbatim, raising privacy and copyright concerns. Existing mitigation methods apply interventions uniformly, often degrading predictions at the many positions unrelated to verbatim recall. We study a token-level log-likelihood ratio between a target model and a domain-competent reference with lower exposure to the evaluated sequences. Exposure-controlled experiments support its use for localizing positions associated with sequence-level verbatim recall. Across evaluated settings, a minority of positions carries a disproportionate share of the positive signal, motivating selective activation correction. From a first-order surrogate of the memorization-reduction objective, we derive a probe-steer framework, which decomposes intervention into a probe that flags high-signal activations and a steer that applies a correction only when the probe exceeds a threshold. We propose Gated Subspace Steering (GSS) as its practical instantiation: under a background normalization constraint, the probe-steer pairs that are optimal for this surrogate follow in closed form from the leading singular vectors of a whitened gradient-weighted activation matrix. Across four benchmarks, GSS achieves memorization suppression comparable to strong baselines, with favorable utility trade-offs in several settings, while requiring 10-100$\times$ less compute than optimization-based alternatives. Code is available at https://github.com/ubc-tea/Mitigating-Memorization-Where-It-Happens.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.05581

BrainBind: Bridging Synchronized EEG and fMRI through Long-Form Naturalistic Video Representations

Shixiao Wang, Rining Wu, Jian K. Liu

原文摘要

Real-world vision is dynamic and scene-rich, while EEG and fMRI resolve it at complementary temporal and spatial scales. Most neural decoding systems, however, align one modality in isolation and mostly against static images or short clips. We study the synchronized case: EEG and fMRI are recorded during the same long-form naturalistic viewing, giving a shared stimulus but also recurring narrative context and many semantically similar candidates. We present BrainBind, a framework that maps synchronized EEG and fMRI into frozen long-form video embedding spaces and treats those spaces as common visual-semantic references, not literal neural codes. On CineBrain, a five-seed Recall@K 2 x 4 matrix across two video anchors and four system configurations shows distinct retrieval profiles. With Omni, fMRI organizes the full candidate list most strongly (MRR = 23.82, nDCG@10 = 25.31), while Joint-Dual gives the highest mean label-aware R@1 (13.52%) with a distinct rank-wide profile. The complementary episode-disjoint evaluation quantifies the contribution of repeated stimulus identity and narrative context to the random split. Across these experiments, proxy choice and system configuration produce distinct top-rank and rank-wide retrieval profiles within the present synchronized dataset. The code is available at https://github.com/Forainest789/Brainbind.

cs.AI · cs.CV

查看论文
arXiv ↗PDF ↗