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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 02:57 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 03:45 — 2026-11-10 03:45（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：2026-11-10 02:57最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 18,172 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 02:55（北京时间）
新论文 · v1arXiv:2610.34435

CyberDual: AI Attackers versus AI Code Reviewers in Real Software Maintenance

Chenyuan Yang, Hwiwon Lee, Jongseong Kim, Yihan Yang, Dongjun Kim, Yinfang Chen, Lingming Zhang

原文摘要

Open-source projects now let AI agents review incoming code, but the code under review may itself come from an AI attacker. We present CyberDual, an arena for this dual role of AI: attacker agents hide an exploitable bug in real maintenance work on widely used open-source projects, and reviewer agents try to find and repair it. Execution decides each match: we rerun the attacker's proof of concept (PoC) on the code that comes out of review. Every attack is new, and the windows can be rebuilt each quarter from the latest upstream history. Three agentic reviewers catch 85-91% of 1,088 valid attacks from six attackers. Yet when the attacker spreads the bug over real upstream commits, about one in six attack slots still ends with a working exploit after review. The strongest attacker has open weights: GLM 5.3 almost never refuses, and its attacks make up 13 of the 28 that get past all three reviewers. When they miss, Claude reviewers mostly approve the attack, while GPT-6-Sol mostly repairs the wrong code; a reviewer from a second vendor catches about two thirds of a Claude reviewer's misses. Beyond a leaderboard, CyberDual has three uses. First, PoC execution gives both sides a reward that agent reports cannot game, so its surviving attacks can train reviewers against stronger attackers. Second, it can gate a release on both scores: Claude Sonnet 5 refuses one in five attack slots, yet attacks about as well as GPT-6-Sol, so refusal alone does not remove attack capability. Third, it can warn the teams behind a deployed reviewer when a new attacker crosses a threshold: GLM 5.3 in Claude Code already gets an exploit past Sonnet 5 in 17% of its attack slots.

cs.CR · cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2607.18451

CANDOR: Chance-Calibrated Neighborhood Discordance in Frozen Encoders for Medical Imaging

Soroosh Tayebi Arasteh, Sven Nebelung, Daniel Truhn

原文摘要

In medical imaging, one frozen foundation encoder is often reused for many tasks. The encoder is usually chosen by the area under the receiver operating characteristic curve (AUROC) of a head trained on its features. The AUROC does not measure whether the encoder separates positive from negative images in its feature space. Chance-calibrated neighborhood discordance (CANDOR) measures this separation without training a head. Among images acquired the same way, a positive image is discordant when its k nearest negatives are more similar to it on average than its k nearest positives are. The discordance rate D is the share of discordant positives. When the neighbors come from positive and negative candidate sets of equal size, D has the chance level 1/2 for features without information about the label. With unequal candidate sets, all 11 chest encoders have rates above 1/2 (0.732 to 0.927) on the 12 chest findings of MIMIC-CXR and CheXpert. These rates increase as the finding becomes rarer. With equal sets, the same encoders have rates below 1/2 (0.277 to 0.463). On the chest test split, linear heads miss 0.301 of the discordant positives and 0.165 of the other positives. Across 22 encoders, 605,443 images, and 8 tasks in 7 domains, the best encoder of every task has a rate below 1/2. Because computing D takes one forward pass per image, a hospital can compare candidate encoders before it trains any head.

cs.LG · cs.AI · cs.CL · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34434

Envy-Free Allocations for Random Non-Additive Valuations

Pasin Manurangsi

原文摘要

Benade et al. (EC 2024) introduced a semi-random model for non-additive fair division in which each agent starts with an arbitrary base valuation over bundles of items and independently permutes the item names uniformly at random. While they proved that envy-free allocations exist with high probability as the number of items grows for $n = 2$ agents, they left open whether the same holds for $n > 2$ agents. We resolve this open question in the affirmative: for any fixed number of agents $n$ and any number of items $m$ divisible by $n$, an envy-free allocation exists with probability $1 - o(1)$ as $m \to \infty$. Our proof combines the second moment method with a connection to the (small-set) expansion of generalized Johnson graphs, which may be of independent interest.

cs.GT · math.CO

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2601.17668

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction

Jang-Hyun Kim, Dongyoon Han, Sangdoo Yun

原文摘要

Efficient key-value (KV) cache management is crucial for the practical deployment of large language models (LLMs), yet existing compression techniques often incur a trade-off between performance degradation and computational overhead. We propose a novel gating-based KV cache eviction method for frozen-weight LLMs that achieves high compression ratios with negligible computational cost. Our approach introduces lightweight sink-attention gating modules to identify and retain critical KV pairs, and integrates seamlessly into both the prefill and decoding stages. The proposed gate training algorithm relies on forward passes of an LLM, avoiding expensive backpropagation, while achieving strong task generalization through a task-agnostic reconstruction objective. Extensive experiments across the Qwen2.5-1M, Qwen3, and Gemma3 families show that our method maintains near-lossless performance while evicting up to 70% of the KV cache. The results are consistent across a wide range of tasks, including long-context understanding, code comprehension, and mathematical reasoning, demonstrating the generality of our approach.

cs.LG · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34433

Non-Ergodic Markovian Mirror Descent with Unbounded Noise

Yunus Alp Biyikoglu, R. Srikant

原文摘要

We analyze stochastic mirror descent for minimizing a convex objective expressed as an expectation under the stationary distribution of a Markov chain, using noisy subgradient observations along a single sample path. Through Poisson's equation, we decompose the Markovian noise and control its contribution under regularity and moment conditions that allow the stochastic subgradients and the Poisson solution to be unbounded across the state space. We establish an $O(T^{-1/2})$ bound on the expected suboptimality gap of the weighted-average iterate for an appropriately chosen step size. The analysis does not require aperiodicity or convergence of the chain's marginal distributions to stationarity. For irreducible finite-state chains, we verify the required conditions on the Poisson solution and derive explicit bounds that quantify the effect of periodicity. For irreducible countable-state chains, we verify the required regularity and moment conditions under a geometric Lyapunov drift condition and suitable growth bounds on the stochastic subgradients.

math.OC · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34432

On Detection Reliability for Small Object Segmentation

Olivier Rukundo

原文摘要

This study investigates whether predicted bounding boxes are reliable for determining where small-object segmentation should be performed without risking false negatives outside those boxes. The investigation leverages adenovirus particles as small objects, YOLO26x for detection, YO-LO26x-Sem for segmentation, and Mask R-CNN for both detection and segmentation. Segmenta-tion-model predictions were matched to ground-truth adenovirus masks or reference objects using their centroids, with ground-truth mask centroids preferred over ground-truth bounding-box centroids as references for matching. Matched predicted-mask centroids were considered as inside at least one detector-predicted bounding box or outside all such boxes, while ground-truth masks without matched predictions were recorded as having no matched segmentation. For the YOLO26 models, 34 reference objects (47.89%) had matched segmentation centroids inside at least one pre-dicted box, 8 (11.27%) had centroids outside all predicted boxes, and 29 (40.85%) had no matched predicted segmentation. For the Mask R-CNN model, the corresponding counts were 69 (97.18%), 0 (0.00%), and 2 (2.82%). These preliminary experiments demonstrated that restricting segmentation to detector-predicted bounding boxes risks excluding matched segmentation predictions outside those boxes, potentially introducing false negatives.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34431

SymLift: Neural Semantic Lifting for Compile-Free Vulnerability Detection in Context-Incomplete Code Fragments

Xiarun Chen, Jiaxing Xu, Bozhi Wu, Chenhui Cui, Chunrong Fang, Weiping Wen, Tao Li, Rubing Huang 等 9 位作者

原文摘要

Missing project context can prevent build-dependent analyzers from constructing program relations required for vulnerability detection, while neural predictions alone do not establish auditable derivations. We present SymLift, a compile-free framework centered on Vulnerability-Oriented Neural Semantic Lifting for context-incomplete code fragments. A fine-tuned large language model reconstructs vulnerability-relevant control-flow, data-flow, memory, and resource relations in a constrained LLVM-like intermediate representation (IR), without reconstructing the full project context or directly predicting vulnerability labels. A deterministic parser validates the IR and maps its supported operations and relations into normalized evidence facts. Explicit Datalog rules derive findings with supporting facts and derivation traces, ensuring deterministic reasoning for fixed facts and rules. We evaluate SymLift on FormAI, Juliet, and MegaVul. Reducing complete Juliet programs to function-level fragments lowers Clang compilation success from 100% to 12.00%, whereas SymLift's analysis completion rate decreases by only 1.17 percentage points. After task-specific fine-tuning, the lifter achieves a control-flow intersection over union (IoU) of 96.85% on FormAI. SymLift-Qwen-7B achieves a Target-F1 of 94.41% on FormAI and, across six vulnerability families on MegaVul, a micro-averaged precision of 98.24% and a micro-averaged Target-F1 of 91.66%. These results support accurate and auditable detection in the evaluated context-incomplete settings, even with partial program relations.

cs.SE · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34428

Matter that learns what matters

Natalia G. Berloff

原文摘要

Can a material learn what deserves its attention? We show that it can in a model optical network, in which action outcomes train a persistent record in each link. The record biases whether a source is consulted and sets how strongly it changes a stored answer, so useful sources gain attention and influence without being identified in advance. The network's experience thus shapes the information available for its future learning. Resonant readouts make this learning fragile: reinforcement can carry a record past resonance, where it persists but its influence weakens. We derive bounds within which relevant signals guide the answer, irrelevant signals are rejected and stored answers remain open to revision. These bounds guide a learning rule that limits reinforcement as records form; in simulations, it acquires useful records and keeps them functional. When relevance changes, an obsolete record can block its own replacement. A local state that strengthens negative writing after unsuccessful actions releases obsolete records and completes the learning sequence more often. How a memory is read should decide how it is written.

cs.ET · nlin.AO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34427

ScaleRLT: Exact Log-Probabilities and Fast Deferred Rollouts for Reinforcement Learning on Looped Transformers

Dezhen Lu, Zixiang Ni, Runguo Li

原文摘要

Looped language models such as Ouro reuse one block of layers several times per token. A rollout engine can batch the deeper loops of several response positions and run them only when a deep readout is due. This deferred schedule is fast, but the learner of an on-policy RL algorithm recomputes the sampled tokens' log-probabilities with a dense pass, and the two computations differ in floating point: in FP32 at 4096 tokens about 18% of the sampled tokens miss a $10^{-5}$ same-weight gate, and with bf16 weights nearly every token does. We use a hybrid learner log-probability, $\ell=\ell_{\mathrm{dense}}+\mathrm{sg}(\ell_{\mathrm{sched}}-\ell_{\mathrm{dense}})$, where $\mathrm{sg}$ denotes stop-gradient. Its value is a no-grad replay through the rollout's own schedule, and its gradient is the dense learner's. The replay reproduces the rollout bit for bit in all 167 FP32 and 28 bf16 real-weight cells we ran on three platforms, including rollouts whose batch shrinks at stop tokens, and the gradient has the same FP32 error as other dense implementations in all 102 pre-registered comparisons from 96 to 4096 tokens; the full GRPO loss of a training step matches a float64 reference to $3.1\times10^{-4}$. On one GPU, deferral raises rollout throughput by $1.47$ to $1.56\times$, and by $1.18$ to $1.54\times$ once every step runs from CUDA graphs, bit for bit. In a two-node GRPO loop, one-wave KV admission and CUDA graphs shorten an update by $2.71\times$ with the gate bitwise at every update, and four nodes keep the update time within 2% at the same per-GPU load. In 100-update runs held-out GSM8K accuracy rose from 23% to 82% with the mixed-depth readout that deferral relies on and from 34% to 90% with the native readout, which reached a higher accuracy in less time. For looped models beyond one node we analyse a ring mapping of layers to GPUs and measure its communication paths.

cs.LG · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34386HF 社区推荐

ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains?

Haojin Wang, Yangzhen Wu, Zeyi Chen, Jian Xie, Jiaying Ye, Lili Meng, Shuyun Tang, Shangding Gu 等 9 位作者

原文摘要

Recursive self-improvement (RSI) requires an agentic system to design, train, and evaluate its own successor. Data-driven post-training is a central part of that loop, yet existing evaluations measure it on a single benchmark, where an agent selects from a static pool or distills a stronger model to push one score up in one run. Real post-training is multi-domain, and a gain in one domain has to be weighed against a regression in another. We propose ParetoRSI-Gym, in which an agent searches for data, curates it, trains, reads back per-domain results, and repeats, with everything but the data held fixed: the initial LLM, the five domains (math, code, finance, medicine, science), the toolset, and the SFT pipeline. Generalization benchmarks in each domain separate capability gains from overfitting to the scores the agent optimizes against. Across three agent systems, three base models, five rounds and multiple seeds, the strongest system, Claude Code with Opus-5, raises the generalization scores of its proxy-best checkpoint by 9.2% relative to the starting model (+2.3 absolute points), averaged with equal weight over three base models and five domains, with a single-domain relative gain of up to 63% (medicine on Ministral-3-3B). Further analysis shows that the harness matters as much as the model it drives, and that each agent keeps a unique data selection strategy. We see our work as a step towards evaluation of RSI systems in real-world machine learning engineering.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34298HF 社区推荐

Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents

Zhenning Shi, Liang Pang, Yongqi Li

原文摘要

Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model Context Protocol (MCP) and command-line interfaces (CLI) can expose the same semantic operations through markedly different model-facing representations. We study whether these representational differences change agent behavior when executable capabilities are matched. We introduce Matched Interface Comparison and Analysis (MICA), which renders MCP and CLI from a shared semantic action contract and routes decoded actions through the same runtime. Across six models and three interactive environments, matched interfaces produce substantial differences in task performance and interaction cost. These effects extend beyond surface validity to semantic action selection, failure pathways, and recovery. Matched-state probes localize sensitivity to capability presentation, realization, and feedback. Paired natural trajectories reveal structured divergence in 94.3% of 2,004 episodes and show that early differences propagate through subsequent interaction. This analysis identifies interface realization as a direct intervention boundary. We therefore introduce Decoupled Action Realization and Targeted Repair (DART), which preserves validated semantic commitments while repairing interface-specific realization. DART improves benchmark score in all six evaluated settings by up to 9.0 points and reduces MCP token cost in all three environments by up to 27.1k tokens per task. Together, these results establish interface representation as part of the closed-loop decision environment shaping agent behavior.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34283HF 社区推荐

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Yihao Hu, Yitong Lin, Pan Wang, Zhihao Wen, Hang Wang, Yiwen Zhao, Deyuan Liu, Yutong Li 等 11 位作者

原文摘要

Training a spatial VLM to answer which side an object lies on does not require it to preserve the metric displacement that determines that answer, while supervision for a distance estimate may leave categorical relations largely unconstrained. When post-training emphasizes one readout, improvements can therefore concentrate on that interface while transfer to others remains weak or even degrades; we call this observed specialization interface lock-in. ChronoReplay addresses it by replaying heterogeneous spatial supervision as chronologically ordered episodes, retaining source-native targets, and balancing supervision across families. Under the same observation access, a single ChronoReplay checkpoint improves OVO-S-Bench, OST-Bench, and UCS-Bench together, including a 13.41-point gain on OST-Bench, and achieves the highest three-benchmark mean among the supervision settings compared here. Same-data controls further separate the ingredients of this transfer: answer serialization redistributes gains across OST and UCS, family-balanced learning improves over ordinary joint SFT and natural turn weighting, and chronological replay exceeds a shifted-order control by about 2.41 OST points across two paired seeds. Adaptive frame selection then changes evidence access while keeping the trained model fixed, providing an additional inference-time gain at lower visual cost. Streaming spatial performance depends on what distinctions supervision preserves, how heterogeneous histories are organized during learning, and what causal evidence inference makes available at test time.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35962HF 社区推荐

h1: A Taste of the Bitter Lesson in Automated Theorem Proving

Skander Moalla, Ahmad Rammal, Niket Patel, Remi Munos, Julia Kempe

原文摘要

While progress in informal mathematics has come largely from scaling the chain-of-thought and agentic reasoning of frontier language models, formal theorem proving has increasingly relied on human-designed workflows around these models, such as planning, decomposition, and orchestrating specialized provers. This raises a bitter-lesson question: can a simple agentic loop that scales test-time compute match these workflows? The answer matters as formal verification must scale to keep up with frontier models producing research mathematics, yet new workflows rarely settle it, as their gains are often confounded with stronger models or more compute. We study this question with h1, a simple harness that gives a model an efficient interface to Lean 4 and keeps it working through verifier feedback and self-reflection, without imposing a decomposition or search structure. h1 reaches state-of-the-art results on PutnamBench, FATE-X, and FormalConjectures100-Solved, settles eight open problems in FormalConjectures, and, at matched models, matches or outperforms specialized workflows such as Goedel-Architect and AlphaProof Nexus, surprisingly showing that a single attempt (pass@1) can often scale to solve open problems. Through ablations and matched-model comparisons with Claude Code and AxProverBase, we find that simplicity alone is not enough: an efficient Lean interface largely determines cost and solve rate. We thus recommend that future work evaluate frontier models with efficient execution feedback before prescribing workflows, at the risk of bitter lessons.

cs.LG · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34186HF 社区推荐

HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience

Yang Liu, Jiacheng Liu, Hengtao Li, Yuheng Huang, Zijian Yang, Ji Dai, Maoxin Wang, Yi Gao 等 17 位作者

原文摘要

Extending Vision-Language-Action models (VLAs) to humanoid robots requires coordinated whole-body control and diverse demonstrations that are costly to collect in real-world scenarios. Although egocentric human demonstrations provide a complementary source of task experience, differences in visual embodiment and missing robot proprioception complicate transfer to humanoid policies. To address these challenges, we introduce HuGe, a family of Humanoid Generalist VLAs pre-trained on over 2,000 hours of egocentric human and robot data. Specifically, HuGe employs three existing representative VLA architectures to predict latent motion tokens for a pretrained whole-body controller, together with hand-control signals. Based on this, we introduce a three-stage training pipeline that combines egocentric pre-training, humanoid adaptation, and downstream fine-tuning. To facilitate transfer across embodiments, we construct pseudo-proprioceptive states through simulation playback during pre-training and modify arm appearance in egocentric observations through re-rendering during downstream fine-tuning. With this pipeline, HuGe achieves the state-of-the-art on simulation benchmark HumanoidArena. Furthermore, real-world experiments on the Unitree G1 indicate that augmenting robot demonstrations with visually adapted egocentric demonstrations significantly increases success on a pick-and-drop task.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.34073HF 社区推荐

Memory Tax: Dissecting the Net Value of Agent Memory

Xuan He, Sining Zhoubian, Ruozhen Yang, Yuhao Wen, Zhineng Wang, Yuyang Hu, Ke Yang, Yuyu Zhang 等 11 位作者

原文摘要

Memory is increasingly used in long-horizon agents, yet the net value of building memory over direct retrieval from raw history remains largely unclear. Through a large-scale evaluation across multiple benchmarks and model backbones, we find many dedicated memory systems underperform naive RAG in many cases, indicating a negative net value. Taking RAG as a reference, we dissect the net value of memory into the gains and losses over direct retrieval, termed memory benefit and memory tax. These gains and losses arise because memory process changes how the raw information is organized and accessed. We view such changes as the double-edged deviations from the raw history. They are originally designed and introduced to benefit the task, for example by reorganizing facts or distilling preferences, but some may also remove or obscure evidence, giving rise to memory tax. Since memory benefit reflects the expected gains of its design, we then focus more on the overlooked memory tax, study how it arises from the system and evaluation side, and generalize the concept to more application scenarios of memory. We hope the notion of memory tax can provide a new lens and shift more attention from standalone performance to the net value of memory, informing more reliable memory designs and evaluations. We will open-source the code and results to the community. Project Page: https://hexuan21.github.io/MemoryTax/

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.33645HF 社区推荐

PreView: Enhancing GUI Grounding with Preprocessed Views and Cues

Wenjun Hou, Kaishuai Xu

原文摘要

GUI grounding requires locating small controls in cluttered screenshots and identifying which control a natural-language instruction refers to. Cropping and enlargement can expose local detail, but the resulting image may still leave ambiguity about the intended target. We propose PreView, an auxiliary preprocessor that improves the inputs to an existing grounding model without further training that model. PreView prepares two complementary types of input features: task-relevant views for localization and candidate-specific cues for target understanding. A trained lightweight auxiliary model predicts and refines a center, crops the screenshot into a local view, and enlarges that view for zoomed-in grounding. It also prepares a visual cue (i.e., a red-circle marker with a location hint) and a textual cue describing the candidate's identity or function. The frozen grounding model uses the prepared inputs to predict the final click. Across five benchmarks, PreView improves the average grounding accuracy of Qwen3-VL-2B, OS-Atlas-4B, and Qwen3-VL-4B without further training these grounding models. Extensive analyses examine the contributions of views and cues, center refinement, and visual input budgets.

cs.CV · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.33624HF 社区推荐

RSI Arena: Towards Recursive Self-Improvement with Human Feedback

Yue Huang, Yanbo Wang, Lichi Li, Yuanyuan Chen, Andreas Haupt, Xiaonan Luo, Zheyuan Liu, Jihye Choi 等 18 位作者

原文摘要

Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training as a step toward recursive self-improvement. Ten frontier models act as training agents, each starting from NVIDIA Nemotron 3.5 Lightning 30B-A3B Base. During a six-day first stage, each agent has 1,000 GPU-hours and $300 in API credit on a shared 64-GPU cluster, independently selecting data, implementing training procedures, and choosing checkpoints. We evaluate their models on 20 benchmarks and through blind human evaluations. All ten agents produce working assistants, with the strongest model, trained by GPT-6 Astra, closing a median of 76% of the base-to-Instruct gap across 12 capability benchmarks. Its human-preference rating is also close to NVIDIA Instruct after statistical adjustment for answer length and formatting. In Stage 2, each agent receives the comparison records and votes involving its Stage 1 model and is given three additional days for further training. Using NVIDIA Instruct as a common reference across the two evaluation rounds, we observe an improvement from Stage 1 to Stage 2 in the style-adjusted relative rating of eight of the ten models. We show that benchmark gains were modest, with no clear link to preference gains, while some agents encouraged longer responses and one model showed increased harmful compliance on StrongREJECT. RSI Arena provides an auditable setting for studying how human feedback can guide autonomous model development. It takes a step toward recursive self-improvement with human feedback (RSIHF), in which people help define what improvement means for the AI systems they use.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.37695HF 社区推荐

After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System

Bo Zou, Chao Xu

原文摘要

In September 2026, a new large language model was released. Soon after, a new way of making explainer videos became very popular: people asked the model to write a program, and the program produced the video. "One-click video" content then appeared in large amounts on many platforms. On the surface, this is a rise in creative power at the level of the individual. We argue that, at a deeper level, it changes the structure of the content industry. This judgment rests on two observations. First, this wave of content is service-type content. People watch it to meet a need, not to enjoy the content itself. The other kind is work-type content. AI makes both kinds faster to produce. But anyone can come in and make service-type content, while work-type content is limited by the number of people who have something to say. So the ratio between the two slowly becomes unbalanced. Second, free platforms choose content through layers of trial viewing, and this uses up user attention. The total amount of attention is fixed. The unbalanced ratio also dilutes good content. A simplified mathematical model shows that, as long as these conditions hold, the recommendation pool mechanism will fail once new content grows past a certain multiple. Based on this, we discuss one possible way out. Machines and entry rules judge whether service-type content passes the bar. Trusted people judge work-type content. We call this the BoLe system. At the end, we briefly imagine how the two kinds of content may develop from here.

cs.IR · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.33245HF 社区推荐

AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science

Atharva Naik, Vivek Chari, Pol Llado, Daniel Fried, Carolyn Rosé, Benjamin Van Durme, Sam Thomson, Justin Svegliato

原文摘要

Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration, unsound validation, coding bugs, and poor use of a fixed budget (re-running the same exploratory data analysis and baseline models in every attempt). We propose AdaPRA to address these issues: a persistent coding agent harness that accumulates knowledge across attempts on the same task, with rubric-guided process supervision that identifies and corrects errors. Our process reward agent audits the agent's trajectory and workspace by executing checks, and adapts its rubrics to each task. We find that rubrics seeded from easier tasks generalize to harder tasks, with rubric adaptation further improving performance. With five attempts per task, AdaPRA improves an 80B Qwen model's leaderboard percentile by 24.5 points on DSPredict-Easy and 14.8 points on DSPredict-Hard while reducing process errors. We also show that supervision with rubrics mined from one base model's runs improves another (DeepSeek-V3.2), and that AdaPRA beats DataPRM, a competitive PRM for data science. We also share our code for reproducibility.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.32749HF 社区推荐

Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes

Wendi Sang, Kai Li, Yifan Li, Jianqiang Huang, Xiaolin Hu

原文摘要

Streaming audio-visual target speaker extraction (AVTSE) is essential for latency-sensitive applications. However, current causal systems face two coupled gaps. First, standard benchmarks fix the number of speakers at two and ignore the near-/far-field interference, reverberation, and sudden noise of real scenes. Second, high-performance causal architectures are too heavy for edge deployment. Lightweight alternatives try to reclaim capacity by repeatedly invoking a small separator, which offsets the savings. To address the first gap, we release RealSSA, a realistic AVTSE benchmark consisting of RealSSA-Sim and RealSSA-Real. RealSSA-Sim provides controllable simulated scenes with 1--5 dynamic near-field interfering speakers; scenes with far-field interference additionally include 10--15 far-field interfering speakers. RealSSA-Real provides a held-out real-recorded evaluation set. To address the second gap, we propose Falcon, a causal AVTSE method. Its Separator performs multi-scale time-frequency separation in a single encoder--decoder pass. We train Falcon with an encoder-space speaker contrastive loss. This loss suppresses near-field leakage at zero inference cost and transfers across backbones. Falcon achieves state-of-the-art extraction quality on RealSSA-Sim, LRS2-2Mix, LRS3-2Mix, and VoxCeleb2-2Mix. Compared with the causal AV-TFGridNet baseline, it cuts parameters by 91.9%, computation by 20.2 times, and GPU inference latency by 11.1 times. Code and demo are available at https://cslikai.cn/Falcon/.

cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.32411HF 社区推荐

A Broader Look into MLLM's Retrieval Heads

Jia Wang, Yuqing Li, Jiangnan Li, Zheng Lin, Mo Yu

原文摘要

Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that transfer information from the context to the output. However, these analyses are confined to a limited set of modalities and the corresponding models. Moreover, how retrieval heads can be leveraged to enhance the model calls for further exploration. In this paper, we ask whether this mechanism expands together with the input modalities of the model. Taking audio-visual input as a newly added modality, we construct paired inputs in which the same answer is either spoken or shown on screen. With the evidence content fixed, retrieval heads remain sparse in the new modality and are shared to a large extent across modalities. Across 18 language, vision-language, and omni-modal checkpoints, omni-modal models largely preserve the retrieval heads of their backbones. Ablating these heads eliminates nearly all audio-visual retrieval. The heads shared across modalities make up fewer than 2\% of all heads, yet ablating them also degrades document understanding, spatial perception, and visual mathematics. Building on these findings, we turn retrieval heads into a target of optimization by training their attention with a ranking objective. This raises the page Recall@1 of Qwen3-VL-8B on MMDocIR by 6.03 points and improves document retrieval across three model families. Functional attention heads can thus serve both as a lens on multimodal models and as a target for improving them.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.31670HF 社区推荐

Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success

Yunfei Xie, Howard H. Qian, Shiyi Lan, Kaiyu Hang, Chen Wei

原文摘要

Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests that as representations improve, modalities such as vision and language converge toward a shared statistical model of reality. We ask whether motion trajectories form another such modality: as embodied models become more capable, should their sensory representations converge toward the structure of physical motion? To test this, we propose Sensorimotor Alignment ($S^2$), a training-free offline metric that measures how well a model's sensory representation aligns with the geometry of physical motion. We find that $S^2$ correlates positively with downstream robot task success across model families, making it a low-cost offline proxy for prioritizing models before closed-loop evaluation. $S^2$ can also identify promising vision-language model (VLM) backbones before costly fine-tuning into vision-language-action models (VLAs). Beyond this correlation, $S^2$ offers representation-level explanations for phenomena observed in VLAs and world action models (WAMs). With $S^2$, we extend PRH to robotics and make sensorimotor alignment measurable, offering a low-cost, representation-level view of robot foundation models that closed-loop success rates alone cannot reveal.

cs.CV · cs.LG · cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.32177HF 社区推荐

$Ψ$-0.6: Adaptive Streams of Thought in a Unified Vision-Language World Model

Khai Loong Aw, Klemen Kotar, Baihan Zhang, Yifan Liu, Lilian Chen, Atlas Kazemian, Rahul Venkatesh, Daniel Yamins

原文摘要

Humans reason about the physical world by flexibly combining different forms of inference as a problem unfolds. Achieving this flexibility is a major open challenge in AI: capabilities often remain separated across specialized models, limiting how they can be composed and jointly adapted to a task. We introduce $Ψ$-0.6, a unified vision-language world model that adaptively composes perception, language, geometry, and simulation within a shared reasoning process we call streams of thought. These streams interleave images, text, and explicit representations of geometry and motion, all of which the model can generate and interpret through a shared token interface. $Ψ$-0.6 surpasses leading open-weight models zero-shot on multi-view spatial reasoning, with further gains from reasoning through geometric intermediates. It also supports counterfactual simulation: generating and interpreting imagined scenes to determine, for example, whether moving an object would obstruct a pathway. Reinforcement learning from task feedback jointly optimizes the selection, generation, and use of intermediate representations, improving visual question-answering accuracy with gains that transfer to unseen benchmarks. $Ψ$-0.6 offers a path toward adaptive physical reasoning -- not only predicting the physical world but also choosing the representations through which to reason.

cs.AI · cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.32046HF 社区推荐

Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?

Yepeng Liu, Shengmai Chen, Xuandong Zhao, Chengzhi Liu, Dawn Song, Xin Eric Wang, Yuheng Bu

原文摘要

Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery tasks. However, TTT introduces additional computational cost for online weight updates during the discovery process, making computational efficiency an important consideration when scaling to larger models. This motivates us to explore an efficient \emph{test-time adaptation} method for scientific discovery. We introduce \emph{Test-Time Memory Evolution} (TTME), a plug-and-play test-time adaptation method, as an alternative to TTT. TTME continually updates the external memory by distilling the experience to guide subsequent discovery without updating model weights. To have a clean comparison, we evaluate TTME and TTT under the same discovery framework, replacing only the test-time adaptation method. Our evaluation shows that TTME outperforms TTT on all five mathematical tasks, while reducing computational cost by $82.8$-$84.6\%$ in FLOPs and $47.7$-$58.4\%$ in runtime. These results establish TTME as an effective and computationally efficient alternative to TTT in the evaluated discovery settings.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.15351HF 社区推荐

OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning

Md Khairul Islam, Zeyu Xia, Adam S. Bolton, Judy Fox

原文摘要

Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed across heterogeneous instruments. We identify this coordinate mismatch as a structural limitation in cross-instrument representation learning, and propose OmniSpectra, a wavelength-native foundation model for spectral representation learning: a continuous-coordinate masked autoencoder that discards the integer pixel indexing of sequence modeling. Mapping physical coordinates to a logarithmic basis turns the multiplicative scaling induced by cosmological redshift into a uniform additive shift. In continuous rotary position embeddings, this shared shift cancels from relative token distances rather than producing grid-dependent positional distortion. We further counter the spectral bias inherent to implicit neural decoders with a physics-grounded, resolution-gated Fourier decoder that provides anti-aliasing. Pretrained on eight surveys and benchmarked against seven baselines, our model reaches state-of-the-art performance with only 12.2M parameters while outperforming substantially larger models, indicating that encoding physical structure can substitute for parameter scale.

astro-ph.IM · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.33106HF 社区推荐

VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team

Wenbo Hu, Ken Li, Jiazhe Wei, Yukang Cao, Weiyi Hong, Jiayi Dai, Chenjun Bai, Jiajun Liang 等 16 位作者

原文摘要

Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable game requires coordinating code, scenes, assets, animations, physics, and configurations, while allowing developers to validate their integrated behavior through interactive testing. We introduce VibeGame, a framework for creating complete 2D game projects from natural-language prompts and optional reference images. Its AI-native game engine represents project state as schema-validated structured text and provides frame-synchronous runtime control, enabling agents to inspect game states, execute actions, and verify behavior at their own pace. Built upon this interface, we design an Adversarial Agent Team of eight specialized agents to separate implementation from review, so that problems are found and fixed through multi-round loops. For each conducted and accepted project, we further introduce a training-free self-evolution mechanism to distill it into reusable skeletons, modules, and collaboration contracts for future development. We evaluate prompt-assets-to-game (PA2G), where agents are given an asset library, and prompt-to-game (P2G), where agents generate their own art. On a GameCraft-Bench subset, VibeGame in P2G consistently outperforms a range of agent harnesses in either P2G or PA2G with the same underlying model, including GPT-6.1-Sol.

cs.MA

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.31566HF 社区推荐

CellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Models

Ilan Theodoro, Jordão Bragantini, Loïc A. Royer

原文摘要

Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent efforts are shifting models' training to include scientific problems that often live in highly specialized domains beyond text, such as protein structure and biological images. However, in these scenarios, their general-purpose accuracy compared with specialized algorithms remains in question. One such domain is cell tracking, which requires spatiotemporal awareness of cell dynamics. To evaluate this, we created a new benchmark, CellTrack-Bench, which assesses Vision-Language Models' (VLMs) cell-tracking-related performance against specialized trackers. The full benchmark draws from 15 standard cell-tracking datasets across four imaging modalities and comprises 1,537 problems corresponding to 9,041 cell-linking decisions. We selected a hard subset requiring greater reasoning effort by identifying failures shared across distinct algorithmic trackers. With this proposed dataset, we: (i) evaluated different environment harnesses for VLMs; (ii) benchmarked 9 frontier closed-source models and 13 open-weight models; and (iii) provided a detailed analysis of their failure modes. Code, the stored model outputs, and a pipeline that regenerates the benchmark from the source datasets are available at https://github.com/royerlab/celltrack-bench.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.30435HF 社区推荐

Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models

Taewhoo Lee, Minju Song, Jungwoo Park, Chanwoong Yoon, Junha Jung, Hyeon Hwang, Sanghoon Lee, Minbyul Jeong 等 9 位作者

原文摘要

Recent advances in search agents have enabled large language models to tackle complex tasks by retrieving and synthesizing external information. However, existing search agents often lack search-state awareness, i.e., the ability to recognize what information has been obtained and what remains missing, leading to hallucinated reasoning and prematurely terminated search. To address this limitation, we propose Self-Assessment Reinforcement Learning (SARL), a reinforcement learning framework in which models learn to recognize their own search state during training and improve their search behavior accordingly, without requiring additional assessment at test time. SARL achieves this through a dual reward design that captures the corrective effect of each assessment while penalizing excessive reliance on it, jointly encouraging effective and efficient search trajectories. Under this setup, SARL achieves a 24.3% relative improvement over the strongest baseline, with average gains of 35.9% on multi-hop reasoning and 27.9% on deep research benchmarks against the strongest per-benchmark baselines. SARL further surpasses methods built on auxiliary supervision or multi-agent coordination, despite operating as a standalone RL framework with no inference-time scaffolding. Beyond final performance, SARL maintains training stability under extended search horizons, a regime where existing methods consistently degrade, enabling sustained gains as task complexity grows.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.30132HF 社区推荐

LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

Zhennan Wan, Jianfei Chen

原文摘要

Reinforcement learning (RL) is an effective way to strengthen the long-context reasoning of large language models (LLMs), but it needs training data that are long, diverse, challenging, and verifiable. Human annotation of such data is expensive, naturally occurring data are too scarce to sustain RL, and existing synthesis methods depend on external corpora or stronger teacher models, which become harder to obtain as the trained models get stronger. Recently, RL from zero data, in which a model learns from tasks it proposes itself, has achieved excellent performance, but existing methods target short-context tasks. Therefore, we propose $\textbf{LongZero}$, a method that lets an LLM improve its own long-context reasoning without any external data. Instead of writing questions and answers over existing documents, LongZero first has the model synthesize the question and answer with its supporting evidence in a compact structured form, and only then separately expands the evidence into a long multi-document context. LongZero combines these self-written multi-hop reasoning tasks with self-written multi-round retrieval tasks and trains the model with GRPO. We evaluate LongZero on two LLMs across five long-context reasoning benchmarks and compare it with RL on data synthesized from external corpora. Experimental results show that LongZero can generalize to real tasks, and outperforms both baselines, suggesting a viable and promising path to improving long-context reasoning of LLMs.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.29927HF 社区推荐

Your Benchmark Is an Empirical Measure Over Difficulty

Yifan Sun, Naicheng Yu, Jiawen Gong, Jingyan Shen, Huan Zhang

原文摘要

A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation. This perspective allows us to identify and formalize two central failure modes: measure mismatch, where the benchmark difficulty distribution differs from the intended difficulty distribution, and coverage gaps, where uncovered regions along the difficulty axis prevent benchmarks from detecting meaningful localized training progress. We propose two diagnostic metrics that capture these two failure modes and provide rigorous theoretical guarantees. Empirically, we analyze 25 popular benchmarks spanning 7 domains using carefully estimated item difficulties. Our results show that many benchmarks implicitly overweight certain difficulty regions, so their leaderboard conclusions should be interpreted with caution; others leave substantial portions of the difficulty axis uncovered, limiting their ability to monitor the model improvement process. Finally, we turn diagnosis into action by introducing BenchFill, a simple difficulty-targeted item rewriting algorithm that effectively reduces local coverage gaps.

cs.LG · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗