Research

• General in-context learning for embodied agents1 paper raises it · 0 address it

  Enables models to adapt to new tasks and environments without retraining, improving robustness in real-world deployment.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Cost and latency in embodied control loops1 paper raises it · 0 address it

  High computational and time costs limit real-time applicability of agentic systems in dynamic environments.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Physical-state verification and failure recovery1 paper raises it · 0 address it

  Agents must reliably detect and correct errors in physical interactions to avoid irreversible failures in real-world tasks.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Long-horizon task preservation in embodied agents1 paper raises it · 0 address it

  Maintaining progress over extended sequences is critical for complex, multi-step tasks in robotics and navigation.

  • Has GPT-6-Astra Achieved Embodied Intelligence?raises
• Open-source stacks for generalist computer-use agents1 paper raises it · 1 addresses it

  Closed systems hinder reproducibility and systematic study of agent design for real-world computer tasks.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses

Named by an AI from these papers' abstracts.

• Small LLMs11+1000.0%
• AI safety42+740.0%
• Training & fine-tuning56+600.0%
• Robotics28+600.0%
• Image & video generation34+580.0%
• Evals93+520.0%
• Computer vision43+437.5%
• Code models20+400.0%

• arXiv cs.AIOct 18

  Fix, Not Just Resample: Bounded Compiler-Guided Repair in Lean 4

  Haotian Deng, Chris Farber, Sonal Narasimha, Samskrithi Sivakumar, Yexiang Xue

  Automated theorem provers often rely on sampling language models, but proof assistants like Lean reject each failed step with a precise error message --- information that pure sampling discards. To overcome this, we introduce a bounded, online step-level repair module. Our search samples $K$ candidate tactics at each step and repairs a failed tactic at most $R$ times. Instead of discarding failed tactics, we feed the compiler's error message to a pretrained repair model to fix individual rejected steps in place. This approach improves the solve rate over a sampling-only baseline across all tested candidate budgets ($K \in \{1,3,5,8\}$), achieving up to a $32\%$ relative gain and solving $82$ additional theorems on a $1{,}990$-theorem subset of the LeanDojo benchmark. Repair is not free: it trades extra runtime for reachable proofs. But the trade is predictable: repair pays most when sampling is constrained; its return is front-loaded, with the first repair attempt capturing $84\text{--}96\%$ of the total gain; and the gain comes almost entirely from shallow tactic-execution failures rather than structural errors such as type mismatches. This targeted repair successfully…

  PDF
• arXiv cs.CVOct 18

  ReTrace: Visual Backtracking for Efficient Multimodal Large Language Models

  Guangzong Si, Dong Wang, Yifan Yu, Miao Liu, Panwang Pan +1

  Multimodal Large Language Models (MLLMs) encode images into dense visual token sequences, creating substantial attention and KV-cache overhead. Existing visual token compression methods reduce this cost by pruning low-saliency tokens in shallow layers, but this practice couples temporary computational deactivation with irreversible information deletion. We show that this coupling breaks an intrinsic inference pattern in MLLMs. Through layer-wise attention analysis, we identify \textbf{Visual Backtracking}: visual pivots remain spatially stable, yet in middle layers they actively retrieve context from tokens that appeared unimportant earlier. Thus, early low-saliency tokens can be inactive for computation while still being useful for later reasoning. Motivated by this finding, we propose \textbf{ReTrace}, a backtracking-aware compression framework that introduces a dormant token state. ReTrace caches non-pivot tokens outside expensive layer-wise computation, restores them during the backtracking window, and prunes only after their information has been absorbed. Experiments on Qwen2.5-VL and InternVL3 demonstrate nearly 90\% reductions in FLOPs and KV cache, a 2.83$\times$…

  PDF
• arXiv cs.LGOct 18

  UpLoop: Upcycling Large Language Models with Gated Loop

  Tieyuan Chen, Huabin Liu, Yingtao Zhang, Shijie Li, Tengyu Pan +2

  Looped large language models trade parameter storage for recurrent computation, but most are trained from scratch. In practice, pretraining with looped depth is expensive, making post-training upcycling of a pretrained non-looped LLM an attractive alternative. We introduce \textbf{UpLoop}, a post-training recipe based on \emph{layer-wise} recurrence. Instead of looping a whole model or a middle block, UpLoop loops each selected layer locally, preserving the pretrained depth hierarchy and avoiding feature-space mismatch. To make loop execution useful, we add hidden-wise gates on the attention and MLP residual branches, so later loops act as progressive refinements rather than redundant rewrites. Empirically, UpLoop breaks the commonly observed saturation at two loops ($R=2$) in prior looped models. Starting from Qwen3-4B Base and applying SFT, UpLoop improves the average accuracy across 20 benchmarks by 6.17\% at $R=3$. We use $R=3$ as the main setting for the best accuracy--cost trade-off, while both native and extrapolated $R=4$ yield further gains.

  PDF
• arXiv cs.LGOct 18

  UtoMe: Observation-Uncertainty-Guided Token Merging for Weather Foundation Models

  Yunbei Zhang, Janet Wang, Xi Xiao, Jihun Hamm, Xiao Wang

  Weather transformers process dense reanalysis fields whose reliability varies across variables, locations, and weather regimes. Token merging can reduce computation, but feature similarity alone does not account for this heterogeneous input uncertainty. We introduce UtoMe, an observation-uncertainty-guided token merging framework that combines dynamics saliency with ensemble data assimilation spread as a relative input-reliability proxy. The resulting importance score protects selected tokens as anchors and calibrates bipartite matching between the remaining tokens. Three variants use external uncertainty at both training and inference, during training only, or neither stage. In ERA5 72-hour forecasting at two spatial resolutions, UtoMe improves Overall error over train-time ToMe at matched token budgets. At $1.40625^\circ$ and 50% token reduction, UtoMe-E lowers Overall error from 67.32 to 53.00 at the same 0.55x encoder FLOPs. Small reductions remain close to the full-token baseline; larger reductions incur measurable accuracy losses. Component ablations and spatial uncertainty controls support combining dynamics with aligned uncertainty when allocating a weather transformer's…

  PDF
• arXiv cs.CROct 18

  SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space

  Stavros Damianakis, Konstantinos Psounis

  Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are constructed. More than twenty public datasets describe prompt injection using incompatible vocabularies, often organized around delivery vector, attacker goal, or generation method. In this Systematization of Knowledge, we present PIAtlas, a taxonomy organized instead around how the injected instruction is constructed to subvert the underlying model. Its six classes, one per subversion mechanism, form the roots of a hierarchy of techniques and sub-techniques that researchers can use to describe attacks consistently and design more systematic evaluations. We derive the taxonomy from how LLMs are trained, prompted, and influenced by human-like framing, and compare it with historical attack data. To ground this comparison, we release PICorpus, to our knowledge the largest license-clean collection of public prompt-injection datasets, and map thousands of its records to PIAtlas under a human-verified protocol. The mapping shows that attacks usually combine several techniques drawn from only a few mechanisms. It also…

  PDF
• arXiv cs.LGOct 18

  Block Recursive Transformers for Structured Parameter Sharing

  Josep Marques, Hyunyoung A. Cho, Youngeun Kim, Youjia Zhang, Aecheon Jung +2

  Recursive Transformers depend not only on how many parameters are shared, but also on how shared parameters are organized across depth. Existing static schemes adopt two extreme reuse topologies: layer-wise repetition, where each layer is reused independently, and global cyclic reuse, where the entire stack is repeatedly applied as a single shared function. We argue that sharing granularity is an important factor in recursive parameter sharing. This study proposes Block Recursive Transformers (BRT), which partition layers into contiguous blocks and recursively reuse each block before moving to the next. This intermediate topology enables local refinement within blocks while preserving depth-wise transitions, without adding routing modules, auxiliary states, or extra training objectives. Across decoder-only models up to 1.7B parameters, with additional encoder-decoder and encoder-only studies, BRT improves validation negative log-likelihood and downstream accuracy over static recursive sharing baselines. Ablations and representation analyses further show that intermediate block granularity better balances local refinement and depth-wise differentiation. Project website:…

  PDF
• arXiv cs.AIOct 18

  Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing

  Lei Ren, Haiteng Wang, Shixiang Li, Jing Zhang, Yuqing Wang +5

  Large language models (LLMs) are enabling agents to move beyond predefined workflows toward autonomous planning and execution, creating new opportunities for smart manufacturing. However, dynamic environments, complex physical constraints, and stringent reliability requirements hinder the direct deployment of general-purpose agents in smart manufacturing. This article presents a systematic overview of LLM-driven industrial agents. First, we analyze five key challenges and discuss the concept and core characteristics of industrial agents. We then establish a unified taxonomy covering application scenarios, embodiment forms, and five capability levels. Next, we propose a four-layer system architecture and detail its core modules and operational mechanisms for closed-loop task execution. Finally, we review representative applications across the industrial lifecycle and outline future research directions. This article provides a structured reference for the design, development, and application of industrial agents.

  PDF
• arXiv cs.CLOct 18

  When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding

  Yongchao Long, Chunrui Zheng, Yuxuan Zhou, Guangkun Nie, Tian-Chi Ma +8

  The throughput gains of speculative decoding depend on the trade-off between acceptance length and execution latency. We ask when additional acceptance is worth the cost of obtaining it. We establish a comparison protocol spanning training, inference, and evaluation, remeasuring released checkpoints and retraining six drafter recipes on shared target-generated data across ten benchmarks and two target models. Alignment changes the picture: gaps that appear large in published comparisons shrink substantially under shared training and inference conditions. This narrowing motivates two deeper questions: how is acceptance improved at different costs, and when do these gains improve throughput? We find that acceptance can be improved through nearly free objective and context changes or more expensive token-to-token conditioning. DCore illustrates the former route as a strong baseline with little additional measured drafting overhead. The payoff is conditional: task uncertainty and serving conditions affect acceptance returns, execution costs, and the preferred drafter and budget. These findings inform future drafter design and deployment choices.

  PDF
• arXiv cs.CVOct 18

  MultiAltitudeSR: Multi-Altitude Agricultural UAV Image Super-Resolution via Physical Ground Sampling Distance Conditioning

  Xintong Jiang, Yu Tian, Yixue Liu, Valerio Hoyos-Villegas, Viacheslav Adamchuk +1

  Unmanned aerial vehicles (UAVs) enable high-throughput platforms for crop monitoring but face a fundamental trade-off between flight altitude and image spatial resolution. Many existing super-resolution (SR) methods for UAV imagery rely on oversimplified synthetic degradation models and are restricted to fixed integer upsampling scales, limiting their ability to handle real-world degradations and varying flight altitudes. This study proposes MultiAltitudeSR, a framework that conditions feature modulation and reconstruction on source and target ground sampling distances (GSDs). MultiAltitudeSR trained jointly on real UAV images at altitudes of 10 to 70 m above ground level supports all 21 source-to-target altitude pairs without pair-specific fine-tuning, covering scale factors ranging from 1.18$\times$ to 6.03$\times$. The framework can be extended to additional source-target GSD combinations by incorporating corresponding image pairs into training. On the 20-to-10 m pair, the model achieved competitive perceptual performance compared with pair-specific baselines, with LPIPS of 0.2236, DISTS of 0.2431, and NIQE of 8.9020. Experiments using the same architecture demonstrated the…

  PDF
• arXiv cs.LGOct 18

  Certified Sparse Attention via Perturbed Retrieval

  Runguo Li

  Sparse attention speeds up long-context decoding by reading few keys of the KV cache, but existing methods do not control the error of a query, and on real KV caches their errors have heavy tails. We show that perturbing the score of every key with an independent Exp(1) variable turns threshold retrieval into sampling keys with probability proportional to their attention weights. Lowering the threshold along a geometric grid gives nested samples, a Horvitz--Thompson estimate of the output at every level, and confidence bounds that hold simultaneously over all levels, so each head stops at the first level whose certificate meets the target error $\varepsilon$. With fresh perturbations at every decoding step, each certificate fails with probability at most $δ$ during generation. At a suitable threshold, the estimator reads $O(\varepsilon^{-2}\log(1/δ))$ values regardless of the context length, and no adaptive method reads fewer, up to constants. A 4-bit scan with deterministic bounds, shared across a grouped-query-attention group, generates the candidates exactly but reads every key. On three LLMs and ten settings at 16K--128K tokens, no certificate is violated, and at equal keys…

  PDF
• arXiv cs.CLOct 18

  The World as Viewed by 136 Countries: An Open, Curated, Annotated, and Multilingual Dataset of 118 Million State Media Articles

  Bryan Li, Samar Haider, Grace Kim, Fiona Luo, Jinqi Luo +4

  State media outlets often project their governments' narratives to target both domestic and foreign audiences. Because this content is plentiful and free to access, it appears widely in the web corpora that large language models (LLMs) are trained on and that retrieval systems draw from. However, the prevalence of state media in these corpora and its potential influence on LLM outputs remain largely unexplored. In this paper, we introduce WorldStateMedia, an open dataset of 118 million state media articles from 136 countries in 114 languages. We extract these articles from existing pretraining corpora and annotate each outlet with level of state control from State Media Monitor. Using WorldStateMedia to audit these corpora, we find that, in English web crawls, the share of state media pages from editorially controlled (vs. independent) outlets rose from 39% in 2013 to 93% in 2025. In several low-resource languages, state media make up a substantial share of all web data, such as 17.8% for Uyghur and 7.8% for Belarusian. To characterize the differing narratives of news outlets, we compare Russian and Ukrainian state media in English and in their native languages, revealing…

  PDF
• arXiv cs.AIOct 18

  CorrectRTL: Boost RTL Generation Quality Through Automated Self-Correction with Instruction Decomposition

  Jing Wang, Shang Liu, Hangan Zhou, Wenji Fang, Yuchao Wu +2

  Large language models (LLMs) have shown strong promise in specification-to-RTL generation. Among the explorations, the self-correction paradigm has significantly advanced LLM-based RTL generation. However, two challenges limit further progress. Existing benchmarks are saturated by advanced LLMs, leaving little room to evaluate the agentic self-correction framework. The monolithic self-correction paradigm rewrites the entire design at once, where LLMs are susceptible to error confusion and corruption of originally correct code. To address the benchmark challenge, we contribute ScaleBench, a more challenging benchmark of 200 complex RTL designs. To address the challenge in methodology, we propose CorrectRTL, an agentic framework that realizes a new decompose-then-correct paradigm, in which the LLM agent explicitly decouples scaffold construction from detailed implementation. CorrectRTL contributes three core techniques: (1)~\emph{Structure-oriented decomposition}, (2)~\emph{Snippet-based RAG}, and (3)~\emph{SVA-based self-correction}. On ScaleBench, CorrectRTL improves Pass@1 from 20.5% to 49.0% (+28.5%). On VerilogEval, CorrectRTL achieves up to 96.1% Pass@1, demonstrating…

  PDF
• arXiv cs.CLOct 18

  A Measurement Perspective on Benchmarking LLM-Generated Text Detectors using Item Response Theory

  Yanbin Zhao, Zhipeng Chen, Guangsheng Bao, Guandong Zhang, Yan Li

  Benchmarking large language model (LLM)-generated text detectors commonly relies on aggregate detector-level metrics such as accuracy, F1 score, and AUC. Although useful for summarizing overall performance, these metrics provide limited insight into how benchmark composition shapes detector comparisons or which texts distinguish detectors with different response profiles. We propose a measurement-based benchmarking framework for jointly characterizing benchmark heterogeneity and detector behavior using multidimensional item response theory (IRT). By treating benchmark texts as measurement items and detectors as respondents, the framework estimates text-level discrimination and difficulty-location parameters alongside multidimensional detector abilities. We apply the framework to a benchmark of 32K human-written and machine-generated texts across four domains, evaluated by 14 detectors. The estimated IRT item-parameter space reveals distinct but overlapping human-machine distributions, with substantial variation across domains and text lengths. The human-machine label shows the strongest multivariate association with this space, while domain and text length further contribute to…

  PDF
• arXiv cs.CLOct 18

  Rubrics Carry the Standard: Shapley Attribution for Checklist-Based LLM Judges

  Saeid Asgari, Rui Ying, Sara Malvar, Rakshanda Agarwal, Bruce Sun +3

  Checklist rubrics applied by large language model (LLM) judges have become a standard instrument for evaluating open-ended outputs and for rewarding them during training. Two assumptions surround this practice: that leniency or strictness is a property of the judge model, and that a rubric can be improved by asking a model to review it. We test both in a controlled grading task with planted flaws and on two human-labeled datasets, SummEdits and RAGTruth. Holding the judge and the outputs fixed, rubric content moves the pass rate of correct outputs from 2% to 100%, whereas changing the judge model or the rendering of the same checks moves it by a few points. Model self-review then drifts the rubric toward the reviser's own standard: it adds requirements the task never stated and deletes checks that human labels had taught, with three reviser models and on all three datasets. To measure and control this, we show that under all-must-pass aggregation the Shapley value of each check has an exact closed form, which yields per-check catch credit, false-fail blame and unique catches in linear time. Attribution shows that self-review deletes the checks that do unique work and keeps the…

  PDF
• arXiv cs.LGOct 18

  PRECOCIAL: Pretraining with Code Curriculums via Iterative Search for Accelerated Learning

  Edward Gu, Ali Payani, Kevin Ellis

  Fully synthetic pretraining data generated by symbolic programs can bootstrap downstream training on naturalistic tasks, such as language modeling, but the generating programs have so far been designed by hand. We introduce PRECOCIAL, a method for automatically optimizing programs that generate synthetic pretraining data. Starting from an initial generator program, an LLM iteratively rewrites the program, and each rewrite is scored by pretraining a randomly-initialized transformer on its data and fine-tuning it on the downstream task. Because every score requires training, PRECOCIAL keeps a single network for the entire search, continuing its pretraining for each accepted program instead of training a new network per candidate, making it significantly more efficient. On four language and code datasets, at a fixed fine-tuning budget, optimized programs reach lower perplexity than hand-designed curricula, published procedural generators, random program mutation and the program the LLM writes in the first iteration of the search, and reach the same perplexity as the hand-designed curricula with 9-33% fewer fine-tuning steps. PRECOCIAL also ends with lower perplexity than FunSearch…

  PDF
• arXiv cs.AIOct 18

  Towards Human-AI Complementarity for AI Safety

  Sander Lanbo Shi, Miranda Anna Christ, Eric Modesitt, Andrew Louis, Konrad Cheng +18

  Safely overseeing AI is increasingly challenging for the humans doing it, as they must evaluate longer and more complex outputs with every new model generation. To mitigate this challenge, we could leverage complementarity: where humans and models make different mistakes, combining their judgements could yield an oversight signal stronger than either produces alone. We study this opportunity in realistic, safety-relevant settings, contributing the largest known suite of such tasks (3,957 instances across 8 datasets and 6 domains) as well as a platform and data pipeline for measuring human, AI, and human-AI performance on matched items. We collected 35,613 judgements from 416 human raters, finding a considerable opportunity for a complementarity effect. We also found that with the assistance methods we tested, human raters corrected the AI's errors less often, even when overall human accuracy rose, and the hybridisation methods we tested added little over the better single source on average. While complementarity is an important and feasible engineering target for safe oversight, achieving it remains an open challenge for future work.

  PDF
• arXiv cs.CVOct 18

  Visual Sufficiency Landscapes: Understanding Query-Conditioned Reliability in Visual Token Pruning

  Zhenghan Li, Kexin Sun, Wei Zheng, Peng Hu, Xiao Wei +1

  Different visual token pruning strategies retain different subsets while maintaining similar task performance. This motivates a combinatorial question: how many visual subsets can preserve model behavior, and how does their abundance depend on the query? We introduce visual sufficiency landscapes to characterize this abundance. At a fixed layer and budget, visual sufficiency probability is the fraction of uniformly sampled subsets that jointly preserve the dense model's answer, reference-answer likelihood, and output distribution. Independent sampling replicates separate input variation from estimation noise. Across Qwen2.5-VL-7B, InternVL2-8B, and LLaVA-v1.5-7B, differences between inputs on GQA and TextVQA exceed replication error, and different questions about the same GQA image produce distinct landscapes. Sufficiency probability also improves failure prediction for full pruning methods. On LLaVA, adding this probability increases AUC by 0.1151 for FastV, 0.0683 for VisionZip, and 0.1401 for SparseVLM, while reducing log loss and Brier score. Several architecture-adapted configurations on the other two models reproduce these gains. Under controlled selection rules, predictors…

  PDF
• arXiv cs.CVOct 18

  Meta Inverse Prompting for Video Generative Models

  Yerin Jung, Jongheon Jeong

  Recent advances in video generative models have enabled flexible conditional generation and editing pipelines, such as text-to-video, image-to-video, and reference-guided synthesis. However, these workflows are inherently one-directional, mapping conditions to videos without providing a mechanism to invert this process. In complex media production settings, the ability to recover controllable textual conditions from a given video is highly desirable, yet remains underexplored. While inverse prompting has been studied for image generation, directly extending these approaches to video is challenging due to the need to capture temporal dynamics beyond static appearance, as well as the substantial computational cost of per-video optimization. In this work, we propose the first practical framework for efficient video inverse prompting. Specifically, we formulate inverse prompting as a meta-learning problem and introduce Meta Video Inverse Prompting (MVIP), which learns a meta-prompt optimized over temporal dimensions to enable fast and effective prompt inference. Our approach amortizes the inversion process, eliminating the need for costly iterative optimization at test time.…

  PDF
• arXiv cs.CLOct 18

  DeGMatch: Target-Aware Reasoning Data Selection via Deconfounded Gradient Matching

  Changho Lee, Janghoon Han, Rajdeep Mukherjee, Yeda Song, Lening Nick Cui +2

  Reasoning post-training on long trajectories has substantially improved the reasoning capabilities of large language models, but scaling such training to large datasets is increasingly expensive. We study target-aware reasoning data selection, where a small reference set specifies a target capability and guides the selection of training trajectories for specialization. We find that existing target-aware methods can exhibit limited target discrimination on long reasoning trajectories, while dominant population-level structure in candidate gradients can obscure finer target-dependent variation during gradient matching. To address these limitations, we introduce Deconfounded Gradient Matching (DeGMatch), which first constructs a target-relevance gate and then reranks candidates using model-specific gradients. DeGMatch centers gradients using the candidate-population mean and removes leading principal directions before target matching, reducing the influence of dominant population-level structure and improving target discrimination. Across mathematics, science, and code, DeGMatch outperforms strong heuristic, target-aware, and reasoning-specific data selection baselines, while…

  PDF
• arXiv cs.LGOct 18

  Label-Space Mismatch Distorts Cross-Cohort Evaluation in Breast Cancer Molecular Subtyping

  Suxing Liu, Byungwon Min, Zhijian Zheng, Jiahao Wang

  Cross-cohort evaluation of breast cancer subtype classifiers is unreliable when source and target cohorts use different annotation standards: METABRIC labels six classes, PAM50 defines five, and a claudin-low prediction cannot be correct under a five-class standard. A classifier transferred from 1,369 METABRIC patients (train n=958) to TCGA-BRCA (n=987) and GSE21653 (n=266) separates three evaluation operations routinely conflated in cross-site comparisons. (1) Label-space restriction - an evaluation-rule change, not a retraining gain - is the dominant correction (73.76%->79.74% on TCGA-BRCA; 63.16%->68.42% on GSE21653); (2) EM prior correction on the reconciled space is an optional calibration step (Brier fidelity up, macro F1 down; to 80.65% and 74.06%); and (3) the target label space is not recoverable from unlabelled predictions (EM retains prior 0.0751 on the absent class; calibrated detectors fail), so compliance must come from cohort documentation. The protocol exposes why internal validation overstates cross-cohort value: multimodal fusion gains do not transfer (no configuration beats mRNA alone, n=694; McNemar p=0.13-1.00), and the genomic panel adds nothing to…

  PDF