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.

• Federated learning50+31.6%
• Agents531+2.3%
• Quantum machine learning240.0%
• Character recognition OCR170.0%
• Sensing communication150.0%
• Frontier LLMs450−7.0%
• Voice AI103−11.2%
• Image segmentation184−11.5%

• arXiv cs.AIOct 18▲ 9

  StopLoss: Teaching Agents to Predict Failure and Stop Early

  Jiarong Liang, Xueguang Ma, Dongfu Jiang, Yuxuan Zhang, Ping Nie +1

  Coding agents keep working on runs that will fail verification, and asking a frontier model to watch for this is expensive in its own right. We introduce StopLoss, a small external monitor that learns failure recognition from completed trajectories and their verifier outcomes. The name is inspired by the stop-loss order in finance: StopLoss ends a run early when the run is likely to fail, which saves resources. Final outcomes label earlier local windows, so a fine-tuned language model can score the most recent tool steps in a single forward pass, and a threshold calibrated on successful runs turns that score into an abort decision without changing the executor. Trained on GPT-family SWE-rebench trajectories and evaluated on SWE-bench Verified and a SWE-bench Pro subset with GPT and Claude executors, StopLoss is compared against six general-purpose judges reading identical windows. Outcome supervision lifts failure prediction from near chance to a useful signal at the first check, at one to two orders of magnitude lower cost per check than any tested judge. This translates into savings: relative to completing every task, StopLoss lowers cost per retained solve by 4.5\% on Verified…

  CodePDF
• arXiv cs.GTOct 18

  Breaking the 1/3 Barrier for Approximate Nash Equilibria in Symmetric Bimatrix Games

  Ashkan Soleymani, Patrick Jaillet, Gabriele Farina

  We give the first unconditional family of polynomial-time algorithms that breaks the $1/3$ approximation barrier for symmetric bimatrix games. For every fixed $δ>0$, an algorithm in this family computes a symmetric $(1-1/\sqrt{2}+δ)$-approximate Nash equilibrium, improving on the previous best guarantee of $(1/3+δ)$ due to Kontogiannis and Spirakis [2011].

  PDF
• arXiv cs.LGOct 18

  FracTS: Hierarchical and Autoregressive Time Series Generation

  Jiayu Li, Umair Afzal, Zilong Zhao, Milad Abdollahzadeh, Uzair Javaid +1

  Time series are ubiquitous across different domains, and the growing use of synthetic data for privacy-preserving sharing, data augmentation, and stress testing makes time series generation increasingly important. Early generative approaches are predominantly autoregressive, which can suffer from low sample diversity, error accumulation, and difficulty modeling long-range dependencies. In this paper, we introduce FracTS, a hierarchical, coarse-to-fine autoregressive model for multivariate time series generation. Inspired by fractal generative modeling developed for images, FracTS adapts the paradigm from 2D to 1D sequences by learning a multi-scale representation that captures global trajectory structure at coarse scales and local dynamics at fine scales while following the autoregressive nature of time series. In contrast to unstructured images, time series are structured, allowing easy automated or designated temporal feature processing optimized for the model, and global (static) feature extraction describing the instances that generate the corresponding time series in the collection. We incorporate them in the generation process to further improve the generation quality. The…

  PDF
• arXiv cs.AIOct 18

  When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice

  Dean Ariel, Guy Laban

  Conversational large language models can respond with warmth and reassurance while failing to advance the user's stated goal. We conceptualize this failure as $\textbf{goal displacement}$, the substitution of persona-maintenance content for goal-relevant substance. To measure it, we introduce $\textbf{GDB}$ (Goal Displacement Benchmark), comprising 230 scenarios across nine domains and $4{,}134$ human-scored responses from 18 models. A $2 \times 2$ taxonomy crosses hard constraints with emotional distress, distinguishing failures to confront infeasible goals or combine empathy with practical guidance from reverse displacement, where unsolicited problem-solving replaces requested emotional support. A deletion-test rubric assesses whether substantive help remains after purely supportive sentences are removed. Independent raters achieve weighted $κ= 0.82$ against author scores for displacement severity. Trap displacement ranges from $0.0\%$ to $37.7\%$ and is strongly negatively correlated with Chatbot Arena Elo ($ρ= -0.706$, $n = 15$). Reverse displacement reaches $41.9\%$, including substantial rates in models with negligible trap displacement. A factorial probe supports a…

  PDF
• arXiv cs.LGOct 18

  ATEST: Adaptive Resource-Aware Test-Time Scaling for LLM Inference

  Mobina Kashaniyan, Ali Jannesari

  Test-time scaling (TTS) improves large language model (LLM) reasoning by sampling multiple answers, but fixed sampling budgets ignore both query difficulty and the changing energy cost of inference under GPU contention. We measure up to a 4.1-fold increase in energy for the same four-sample query as GPU load rises. We present ATEST, a resource-aware TTS framework that jointly considers the expected value of additional samples and their current GPU cost. ATEST-Online, its default mode, requires no offline calibration: it incrementally generates samples, estimates the stability of the plurality answer, monitors live GPU conditions, and learns step energy cost online to decide when to stop. ATEST-Calibrated instead selects a per-query budget using offline accuracy and cost models, favoring deployments with stable loads. We evaluate both modes on four reasoning and question-answering datasets using Phi-3-mini on an NVIDIA A100 under controlled varying load, and test transfer to an NVIDIA L40S and Qwen2.5-3B. Across the four A100 datasets, ATEST-Online answers every query without exceeding the energy budget, while achieving the highest or statistically tied accuracy and reducing…

  PDF
• arXiv cs.LGOct 18

  Transformers Learn Two Competing Sorting Algorithms, and Only One Length-Generalizes

  Khashayar Gatmiry, Nathan W. Henry, Chloe H. Su, Emmanuel Abbe, Samy Bengio +3

  We show that two-layer transformers trained to near-zero loss on a sorting task converge to one of two mechanistically distinct solution classes depending on their initialization. One solution class consists of solutions that do not use the second attention layer to sort, but also fail to length-generalize. The other, which uses both attention layers, length-generalizes perfectly, despite only being trained to sort sequences of a fixed length. By carefully choosing the weight initialization, we demonstrate that we can steer the model toward learning one solution or the other. We identify input types that are rare at the training length but increasingly common at longer sequence lengths as a source of this disparity in length-generalization, and find that layer-wise specialization of the second class of solutions allows them to handle these rare sequences more accurately. In the second class, we discover a mechanism by which the second layer attention can use the contextual information gathered by the first layer attention to reduce its search space. On the related task of finding the minimum of a sequence, we find a similar two solution-type phenomenon, but with the opposite…

  PDF
• arXiv cs.CVOct 18

  ReDT: Resolution-Decoupled Visual Geometry Transformer

  Abteen Arab, Guile Wu, Dongfeng Bai

  We introduce ReDT, a feed-forward visual geometry transformer designed to scale multi-view reconstruction to high-definition (HD) inputs. Existing visual geometry transformers are typically trained at fixed, standard definition (SD) resolutions and exhibit degraded reconstruction quality and poor computational scaling to high input resolutions. While recent efficient architectures reduce the complexity of inter-frame attention, expensive intra-frame and encoder attention remain largely unaddressed, making HD reconstruction impractical with existing architectures. ReDT addresses both limitations with a resolution-aware architecture designed to scale to high-resolution inputs. The key idea of ReDT is to first map each view to a fixed-size set of basis tokens, compute correspondences in this compact constant-size basis space, and then project the outputs back to the original resolution for dense prediction. By decoupling the internal representation from input resolution during attention, ReDT substantially reduces the computational cost of high-resolution 3D reconstruction and improves model performance at all resolutions. Extensive experiments on multiple datasets spanning SD to…

  PDF
• arXiv cs.AIOct 18

  Bud ContextCompact 2.0: Context Compaction for Agent Success and Accuracy with Small Language Models and Constrained Context Windows

  Jithin VG, Ditto PS

  Agents that work for many turns outgrow the context window of the model that serves them, and on small language models (SLMs) and constrained inference systems that window is small. Context compaction replaces older turns with a summary so a session can continue, but it is lossy, costs a model call, and can help or hurt depending on when it runs. We describe Bud ContextCompact 2.0, the compaction built into the Bud agent runtime, and evaluate it in two settings. On recall questions over recorded agent sessions, compaction to a 16K budget raised a 1.2B-parameter model's accuracy to 0.335, from 0.247 with truncation and 0.176 with its full 32K history (p < 0.001), and raised a 9B model from 0.515 (truncation) to 0.577 (p = 0.04). On 100 SWE-bench Verified tasks run end to end by a 27B reasoning model on a 49K-token window (556 graded sessions), compaction raised the resolve rate on long sessions from 41% to 53% (+12.3 points, 95% CI +1.6 to +23.0, McNemar p = 0.043), left short sessions unchanged, and used 13% fewer tokens per solved task at equal total cost. The main failure without compaction was not the history overflowing but a reasoning turn exhausting the room the history…

  PDF
• arXiv cs.HCOct 18

  When Interpretations Persist: Downstream Influence in Gaze-Aware Assistants

  Mingcong Ding, Chenyan Zhang, Zhuojiang Cai, Dongyang Guo, Babette Bühler +1

  AI assistants may carry forward not only observations but also interpretations of what a person is doing or may do next across time. Once retained, these interpretations become context for later predictions and system-triggered outputs. We study whether this representation step changes later behavior in gaze-aware streaming assistance. Holding retrieved events, their order, and the target input fixed, we find that Free-form Interpretation amplifies historical influence in both directions: correct histories produce more helpful changes and wrong histories more harmful changes. Unsupported and broader interpretations about activity or future behavior are associated with greater harmful influence. Evidence-Bounded Interpretation preserves distinctions between observation, inference, uncertainty, and temporal scope, reducing unsupported and overcertain content and lowering wrong-source harmful influence while retaining most helpful influence. The same effect structure appears with a second model. These findings identify persistent interpretation as a consequential design choice for history-aware human-AI systems.

  PDF
• arXiv cs.LGOct 18

  Dynamics-Aligned Representation Learning under Induced Partial Observability

  SM Mazharul Islam, Manfred Huber

  Model-based reinforcement learning (MBRL) has enabled sample-efficient learning of continuous control policies from high-dimensional observations through learned latent dynamics models. These models are typically trained with observation reconstruction objectives, which provide strong supervision but can bias representations toward visual fidelity leading to an undertrained prior and unreliable long-horizon predictions. We propose a stochastic gating mechanism that induces controlled partial observability during training by sampling a spatial binary mask from a Beta--Bernoulli random field and applying it to the raw observation. The gate probability is resampled at each time step, exposing the encoder to conditions ranging from near-total occlusion to near-full visibility. Integration of our method requires minimal architectural changes from existing dynamics models: the gated observation and the binary mask are channel-wise concatenated and passed to the encoder as a single augmented input, with no modifications to the broader training pipeline. We evaluate the proposed approach on a set of pixel-based continuous control tasks selected from the DeepMind Control Suite. Using…

  PDF
• arXiv cs.LGOct 18

  KPI-Aware Multimodal Anomaly Detection for 5G and Open RAN Telemetry

  Chiman Salavati, Liang Wu, Kelly Wan, Mayank Darbari, Liangjie Hong

  Reliable anomaly detection is a deployment bottleneck for 5G/Open RAN observability and emerging self-optimizing 6G systems, where hundreds of heterogeneous KPIs, severe class imbalance, and strict alert budgets make purely numerical scores brittle. We present KAC, a deployment-oriented KPI-aware multimodal anomaly-detection framework that uses KPI-level residual-text alignment to turn compact operator-style summaries into a learnable feedback signal over full-KPI temporal evidence. This gives the detector broad numerical coverage like modern time-series models, while retaining the sparse KPI-specific reasoning that makes operator feedback sustainable in a future operator-facing workflow. Across public telecom telemetry, enterprise-scale Open RAN observability data, and a Nokia benchmark built from real 5G RAN production packet traces with realism-hardened injected anomalies, KAC achieves strong threshold-based detection performance while remaining competitive on threshold-free ranking metrics. On TelecomTS, at a fixed 2.5 percent false-positive-rate operating point, KAC achieves the highest recall among the evaluated residual-based methods while maintaining comparable precision;…

  PDF
• arXiv cs.CLOct 18

  Where Are Language-Specific Features Represented in Multilingual LLMs? Everywhere

  Mikaela Martins, Jonathan Dunn

  Previous work has argued that multilingual LLMs encode language-specific features most strongly in their initial and final layers, implying that intermediate layers support language-agnostic representations. This paper reconsiders this finding by performing four different experiments: three that undertake a fine-grained analysis of representations of Portuguese and Spanish, two closely related languages, and one large-scale language identification experiment that covers over 200 languages. The results of these experiments challenge the strict separation between language-specific and language-agnostic layers in multilingual LLMs, using Llama 3.2 1B as a test case. By analyzing and manipulating contextual sentence embeddings, we demonstrate that language identity remains strongly recoverable throughout the model rather than being restricted to initial and final layers. Moreover, we find that the model tends to classify ambiguous strings as closer to Spanish than to Portuguese, revealing a skew in model behavior that differs from human judgments.

  PDF
• arXiv cs.CVOct 18

  From Seeing to Reporting: A Theory of Reliable Visual Set Generation in Vision-Language Models

  Junzhe Shi, Yuan Gan, Shida Jiang

  Vision-language models (VLMs) are asked to report what they see: to count objects, box them, parse a screen or pick a click target (GUI grounding). We argue that reporting is part of the visual task, not merely its formatting. In a dense scene with 173 shapes, GPT-6.1 lists 173 records that match every shape, yet the counts it states in the same response sum to 188. From Seeing to Reporting (FSR) is a theory of visual reporting and a set of inference-time procedures that improve the reports of frozen VLMs. It models reporting as a chain from responses to decoded records, constructed sets and task answers, linked by task-compatible matching. The chain gives exact relations for deleting records, averaging their coordinates and switching readouts, and it splits the error of one answer chosen among several calls into missing candidates, lost representatives and wrong choices. These relations guide procedures for counting, detection, document layout, screen parsing and GUI grounding that use the task specification and a shipped configuration, without requiring labels from the target task. On 50 dense synthetic scenes, a one-call reporting-and-decoding protocol cuts per-type count…

  PDF
• arXiv cs.LGOct 18

  Steered Not Stirred: Effective Reward Tilting using Surrogate Reward Mixing

  Alec Sargood, Olivia Gallup, Georg Maierhofer, Noam Ghenassia, Paul Duckworth +2

  Continuous-time generative models, from diffusion models, flow matching, and now flow maps, owe their practical value to high-fidelity generation and steerability. In many applications, a ground-truth latent ``oracle'' reward $R^*$ is unavailable or expensive to evaluate, e.g., human judgments or experimental measurements. Although the oracle reward is not directly observable, it can often be approximated through multiple cheaper surrogates that, individually, provide incomplete characterizations but collectively reveal substantial information about the downstream task. In this paper, we present a method for composing such surrogates to steer a pretrained model toward the distribution tilted by an unavailable $R^*$. Given a small feedback set of oracle rankings or numerical rewards, we introduce Mixing And Reward Tilting for INference-time Improvement (MARTINI), which learns a surrogate composition for plug-and-play use with standard inference-time steering methods. Our theory characterizes surrogate information limits and relates population recovery error to ideal-target KL at small tilt strength. For preferences, the bound additionally accounts for an irreducible mismatch…

  PDF
• arXiv cs.AIOct 18

  Formal Raising: Embedding Verifiable Ethical Properties into the Development of AI

  Rolf Drechsler, Christina Plump

  Alan Turing proposed constructing a ``child machine'' and educating it rather than directly programming an adult-like intelligent machine. Recent work on model raising revives this developmental view for Large Language Models by arguing that moral values should accompany capability acquisition from the beginning rather than be added only through post-hoc alignment. This paper proposes Formal Raising (FR): selected moral values are represented as explicit, machine-checkable properties that participate in development, evaluation, and action selection. We present a C-based reasoning framework in which candidate actions are evaluated against prioritized ethical properties. Conflicts are resolved w.r.t. a given order, strict rules are non-defeasible, and underdetermination is reported explicitly. Exceptions are not encoded as special cases but emerge from the comparison of alternatives. We provide examples that cover conflicts involving life, truthfulness, harm, privacy, autonomy, and strict rules. We outline a property layer inspired by a Property Specification Language (PSL) for state and temporal requirements and discuss its integration into a raising process.

  PDF
• arXiv cs.AIOct 18

  Assessing the AI Readiness of Construction Datasets: A Multidimensional Operational Framework

  Xiaoyu Hou, Bo Xiao, Abdolmajid Erfani, Ronghua Xu, Yu Cai

  The rapid growth of artificial intelligence (AI) applications in construction has increased the demand for datasets suitable for reliable model development, evaluation, and reuse. However, construction datasets vary widely in documentation, quality, governance, and evaluation support, and consistent criteria for assessing AI readiness remain limited. This study develops a Construction Dataset AI Readiness Framework with 30 attributes across four dimensions: Metadata Completeness, Data Quality and Representativeness, Data Governance and Accessibility, and AI Utility. The framework uses attribute-specific scoring, applicability screening, and automated and manual verification. It was evaluated using 21 publicly available datasets across seven data-type groups. Overall readiness scores ranged from 0.720 to 0.964, with a mean of 0.879. Hybrid verification achieved 90.5% agreement between automated suggestions and manually verified scores. The framework supports consistent assessment of heterogeneous construction datasets and identification of readiness gaps.

  PDF
• arXiv cs.CLOct 18

  Self-Distillation for Supervised Fine-Tuning

  Wenxuan Zhu, Bang An, Shuming Liu, Wenqing Cui, Tianqi Xu +4

  Supervised fine-tuning treats the expert demonstration or gold response as a one-hot target, suppressing valid alternative continuations that the model would otherwise assign probability to. We propose Gold-Conditioned Distillation (GCD), a method that turns expert demonstrations into model-native supervision. GCD uses one model as both teacher and student: the teacher conditions on a prompt containing the gold response in context, the student conditions on the original prompt as at inference, and the student is trained to minimize the forward KL divergence to the teacher's next-token distribution at each gold response token. This lets the model use its prior knowledge to teach itself the new task: correctness is anchored by the gold response, while the soft target preserves plausible alternatives. Across various training tasks on Qwen and Llama models, GCD improves new-task accuracy over SFT and generally reduces degradation on general benchmarks.

  PDF
• arXiv cs.AIOct 18

  From Proposal to Execution: Modeling Interaction Semantics in Shared Autonomy

  Shashank Shekhar, Laurent Jeanpierre, Abdel-Illah Mouaddib

  In many human-AI systems, candidate actions are not executed directly but are first evaluated by another decision-making entity under a potentially different objective or decision model. Standard decision-theoretic frameworks do not require this interaction to be represented explicitly, as they define transition dynamics directly over state-action pairs, allowing evaluation to be absorbed within the transition model. We introduce a semantics-aware decision framework in which a candidate action is proposed, evaluated under an interaction context, and then resolved into an executed outcome. We formalize this through a joint action language and an interpretation function that maps each joint action and context to a semantic outcome. Transition and reward dynamics are induced through these semantic outcomes, thereby introducing an explicit representational layer for interaction semantics. Semantic outcomes provide explicit units for organizing interaction principles, which can be instantiated through application-specific evaluation mechanisms and reused across distinct interaction instances. This provides a structured interface for specifying context-dependent evaluation separately…

  PDF
• arXiv cs.LGOct 18

  Probabilistic Limit Order Book Forecasting with Conditional Diffusion Models

  Junyu Chen, Franklin Liu, Moshu Xu, Lijian Yang

  Modeling limit order book (LOB) dynamics is central to market forecasting and execution-strategy evaluation. While diffusion models achieve strong empirical performance, existing LOB snapshot models typically lack a learned recurrent encoder and formal statistical guarantees. We introduce LOBGrad, a conditional DDPM framework for probabilistic LOB forecasting that combines an autoregressive RNN encoder with a diffusion-based generator. In particular, we establish an excess-risk oracle inequality for the one-step DDPM noise-prediction objective under exponential mixing and regularity assumptions. We further show that, under contractive dynamics, the dependence on the conditioning-window length can be reduced to a dependence on the latent-state dimension. Experiments on BTC/USDT, GOOGL, and META show that LOBGrad improves on its encoder-free diffusion ablation across all reported queue metrics and obtains competitive results against other baselines. It also reproduces the key stylized facts of LOB microstructure, and yields reasonably calibrated queue-based predictive intervals. A stylized downstream task illustrates the potential value of the generated forecasts.

  PDF
• arXiv cs.CVOct 18

  GroundedVDR: Grounding Video-to-Web Evidence Dependencies in Video Deep Research

  Xiyuan Liang, Yu Wang, Zuhao Yang, Ziting Wang, Duo Li +5

  Video large multimodal models have improved at identifying cross-frame visual evidence and conducting open-web retrieval, as reflected in recent video deep research (VDR) benchmarks. However, existing VDR benchmarks primarily evaluate tool-use trajectories and final responses without verifying whether a model actually uses the temporal video information or the retrieved web evidence. To fill this gap, we introduce \method{}, an evidence-grounded benchmark with three features. First, it combines human review with restricted-access probing across multiple models to exclude questions answerable from parametric knowledge or a single information source. Second, each question carries structured video-to-web evidence annotations that link the relevant video segments to their supporting web evidence. Third, its evaluation protocol separately scores video grounding, web evidence grounding, and final-answer correctness. Across eight multimodal agent systems, the best reaches 76.0\% answer accuracy, yet none recovers the complete required web evidence for more than 8\% of questions. Our benchmark is publicly available at \url{https://huggingface.co/datasets/hh721/vdr_temp}.

  PDF