Research

• Lack of holistic evaluation for multimodal video understanding1 paper raises it · 1 addresses it

  Existing benchmarks only cover partial dimensions, limiting systematic diagnosis of models' capabilities across temporal, spatial, and reasoning tasks.

  • OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understandingraises · addresses
• Closed systems for generalist computer-use agents1 paper raises it · 1 addresses it

  Frontier implementations are largely closed, hindering systematic study and community-driven improvements in agent design.

  • OpenGCUA: Toward a Fully Open Stack for Generalist Computer Useraises · addresses
• Structural limitations in decision-making models1 paper raises it · 1 addresses it

  Current models often fail to handle null outcomes, permutation invariance, scalability with candidate sets, and reusable computation for recurring alternatives.

  • Jeva: System One Models from First Principlesraises · addresses
• Inefficient context management for long-horizon agents1 paper raises it · 1 addresses it

  Agents repeatedly process interaction histories instead of organizing context around reusable progress, leading to inefficiency and reduced performance.

  • Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agentsraises · addresses
• Inadequate evaluation for real-world AI delivery tasks1 paper raises it · 1 addresses it

  Existing benchmarks focus on well-specified tasks, while real-world delivery requires handling ambiguity, live systems, and unstated constraints.

  • FDE-Gym: The Last Mile of AI Deliveryraises · addresses

Named by an AI from these papers' abstracts.

• Sensing communication16+23.1%
• Federated learning40+14.3%
• Agents483−4.2%
• Frontier LLMs417−11.5%
• Forecasting time75−16.7%
• Learning verifiable rewards164−17.6%
• Inference & serving244−18.9%
• Quantum machine learning23−20.7%

• arXiv cs.LGOct 19

  Two hidden layer suffice: the caterpillar net

  Jakob Paul Zimmermann

  Every continuous piecewise linear (CPWL) function is a finite signed sum of maxima of affine functions, making maximum representation a central problem in the study of the expressiveness of ReLU networks. A now-disproved conjecture predicted logarithmic depth for maxima. Inspired by the proof by Brunck et al. (2026) that two hidden layers suffice for general CPWL functions, we give the Caterpillar Net, a nonrecursive construction for the maximum of $N$ inputs with two hidden layers of widths $O(N^2)$ and $2^{O(N\log N)}$. The construction has a direct geometric interpretation.

  PDF
• arXiv cs.LGOct 19

  On Data Scaling in Tabular ML: More Data, Better Generalization?

  Ivan Rubachev, Nikita Lazarev, Artem Babenko

  Recent work in tabular machine learning has emphasized the importance of diverse and realistic evaluation settings. The niche of large-scale (1M+) data, however, remains under-explored. To study training-data scaling, we assemble eight real-world tabular datasets with up to around ten million training examples, retaining the natural distribution shifts of the tasks and using random-split evaluation as a control. We find that GBDTs and MLP-based models show broadly similar scaling trends, with gains from both additional training data and algorithmic improvements. Tabular foundation models show more varied scaling behavior, with recent versions benefiting more consistently from larger contexts even under distribution shift. However, scaling training data under distribution shift introduces new challenges: in-distribution and out-of-distribution performance mostly improve together at smaller scales but can diverge at larger scales. We examine this through MLP capacity sweeps and comparisons of the validation distributions used for tuning and early stopping in MLPs and GBDTs. We also compare common practices of using validation data, contrasting its use for model selection in MLP…

  PDF
• arXiv cs.AIOct 19

  SOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One Models

  Ruizhi Qian, Lei Shi, Tianyu Hu, Bo Yan, Song Wang +1

  Reasoning models often run into problems without noticing them, even when symptoms are visible in their own text. In humans, metacognition separates monitoring from control: fast, intuitive signals keep watch while slow, deliberate reasoning unfolds and help decide whether to continue, change course, or stop. System One (S1) decision models, such as Jev, are a natural candidate for this role: they return a calibrated probability for a natural-language question about a text in one fast call, yet they are used only as gates before reasoning. We introduce SOMA (System One Metacognitive Awareness), in which an S1 model continuously monitors a System Two (S2) reasoning model and intervenes when needed. SOMA has three layers: a scenario layer states each objective in natural language with predefined actions, an awareness layer lets S1 judge whether the described behavior appears, and a control layer accumulates these judgments, first reminds S2, and takes over only if the behavior persists. Sharing one S1 model and one controller across tasks, without training, SOMA addresses two different failures on two reasoning models: on overthinking, it cuts reasoning tokens by up to 36\% while…

  PDF
• arXiv cs.LGOct 19

  Training with ML-labeled Data via Stochastic First- and Zeroth-Order Optimization

  Maria-Eleni Sfyraki, Jun-Kun Wang

  Training a machine learning (ML) model is an optimization process that typically requires a set of examples with ground-truth labels beforehand. Obtaining these ground truths usually requires laborious human effort and can be costly. The scalability of human labeling becomes a concern when there are a large number of data points that need to be labeled. To address this practical issue, we consider an optimization setting where a subset of samples has ground-truth labels, while the remaining data points were labeled by an ML predictor, which could potentially assign incorrect labels to those points. We propose both first-order and zeroth-order stochastic optimization methods for training on datasets consisting of a mix of true-labeled and ML-labeled samples. We further conduct comprehensive empirical studies from training a linear regression model to fine-tuning a large language model (LLM) to showcase the effectiveness of the proposed algorithms for training with ML-labeled data.

  PDF
• arXiv stat.MLOct 19

  Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order Books

  Skander Lejmi

  A market maker provides liquidity by quoting prices to buy and sell an asset, earning the spread while managing inventory risk. We study market makers trained with multi-agent reinforcement learning on prediction markets, specifically Polymarket, whose thin order books pose distinct challenges. Three challenges underpin this research: adverse selection may cause a policy trained on real data to stop quoting; the consequences of a quote can arrive many steps after the action; and prediction-market L2 data does not identify individual orders needed for simulation. We address these challenges by reconstructing order-level LOBSTER-format data from Polymarket and training agents in JaxMARL-HFT on 417 real markets. We enrich the baseline market maker's observation space with the book and recent flow, redesign its actions and inventory controls, and propose a cooperative multi-agent decomposition into a quoter and a risk manager trained using recurrent Independent Proximal Policy Optimisation (IPPO) with RNN policies. We investigate reward shaping, particularly reward blending and post-fill markout, to mitigate credit-assignment difficulties between the agents. Our redesigned…

  PDF
• arXiv cs.AIOct 19

  LG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences

  Lu Sun, Xiangyi Zhang, Xiangyang Zhu, Kaiyuan Ji, Zijian Chen +4

  Traditional evaluation benchmarks reduce inherently interconnected scientific knowledge in life sciences into flat lists of questions, disregarding the underlying topological structure of the knowledge. We introduce, the first graph-structured benchmark for life sciences, featuring over 10,000 high-quality multiple-choice questions across medicine, biology, and chemistry. Our approach constructs a weighted evaluation graph using bidirectional matching and semantic similarity algorithms, where nodes represent questions and edge weights capture their semantic relationships. Leveraging this graph topology, we design two novel evaluation metrics. The Global Coherence Score (GCS) measures a model's consistency within semantically related neighborhoods, while Knowledge Balance Score (KBS) analyzes how model errors are distributed across the graph to reveal conceptual blind spots. LG-Bench facilitates fine-grained comparison of LLMs by surfacing differences in conceptual coherence and patterns of knowledge organization across models. Our framework shifts the evaluation paradigm from flat accuracy metrics to structure-aware analysis, offering a new lens for diagnosing and improving LLM…

  PDF
• arXiv cs.CLOct 19

  RESIN: Multi-Chain Reasoning with Entity-Structured Indexing

  Xuanyu Meng, Jash Rajesh Parekh, Jiawei Han

  Multi-chain reasoning is a challenging task not only because the multi-chain evidence is dispersed, but also because different parts of reasoning may require distinct, interacting chains of support. Flat retrieval can flood a model with loosely related text, whereas early selection of a single reasoning path can discard evidence that becomes useful only after other facts are considered. We introduce RESIN (Reasoning with Entity Structured Indexing), which uses structure to locate evidence while keeping the original source as the basis for reasoning. RESIN decomposes a question into focused one-hop needs, retrieves a small set of source-grounded units for each hop, and places only this relevant evidence in a compact reasoning buffer. The buffer preserves alternative supports until final composition, making intermediate decisions explicit without forcing a brittle path. On the full HolisQA benchmark, RESIN achieves 82.92 context recall and 76.70 answer relevancy over all questions, with higher reported CR and AR across five domains and higher F1 in four domains than the published baselines. Ablations show that both typed evidence diversity and hop-wise decomposition are essential,…

  PDF
• arXiv cs.CROct 19

  Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams

  Nardine Basta, Robin Carpentier, Benjamin Zi Hao Zhao, Dali Kaafar

  Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermeasures impose no resource cost on perpetrators. Strategic scam-baiting, in which automated agents engage scammers to deplete their operational capacity, offers a proactive alternative but requires dynamic strategy adaptation that static systems cannot provide. We introduce a game-theoretic framework enabling LLMs to learn effective counter-strategies through in-context experience without fine-tuning. The framework models scammer-baiter interactions as a two-player game with empirically grounded strategies and utility functions, using Nash equilibrium as a formal benchmark for evaluating learned behaviour. Across 300 simulated dialogues and three LLM architectures, adaptive strategy selection achieves 28.9-79.7% closer alignment to Nash equilibrium than non-adaptive baselines. The code and an annotated dataset of 300 dialogues with turn-level strategy labels and utility scores are released at https://github.com/nardinebasta/GameofPhones_/ .

  PDF
• arXiv cs.CVOct 19

  V-JEPA Hand: Simple, Accurate and Fast 3D Hand and Camera Trajectory Recovery from Egocentric Videos

  Ruicheng Li, Qixiu Li, Yu Deng, Sicheng Xu, Jiaolong Yang +1

  Egocentric video supports diverse applications, including robot learning, augmented reality, and human activity understanding. Recovering metric 3D hand trajectories from such video requires estimating both hand motion and camera egomotion to express the hands in a consistent reference frame. Many existing pipelines recover hand and camera motion in separate stages, combining hand detection, hand reconstruction, camera tracking, and trajectory refinement. We present V-JEPA Hand, a simple feed-forward video model that jointly reconstructs bilateral hand motion and camera motion from egocentric clips. It uses a self-supervised V-JEPA 2.1 encoder to extract spatio-temporal features from full-frame video and a query-based predictor to decode these features into per-frame hand poses, hand presence, and camera motion. We use the predicted camera motion to express the hand trajectories in a common world frame. The model accepts known focal lengths or predicts them when unavailable. It reconstructs each clip in a single forward pass. We train both components end to end in a single stage on a mixture of diverse pseudo-labelled videos and high-precision 3D annotations. A single model…

  PDF
• arXiv cs.LGOct 19

  Topological Sheaves of Irreducibility: A Theoretical Framework for Multi-Agent Task Obstructions

  Steven Motta, Davide Mambelli, Alessandro Rozza

  Multi-agent systems can differ under identical agents and communication budgets when they support different forms of joint interaction. We introduce Topological Sheaves of Irreducibility (TSI), a sheaf-theoretic framework separating task-level compatibility obstructions from system capability. A task is represented by an interaction complex $K$ and a capacity sheaf $\mathcal{F}$; nonzero $H^n(K;\mathcal{F})$ defines a structural signature, while registered interventions test capability. For cocycle data, cochain realization is solvable exactly when the represented cohomology class vanishes. Examples show that the signature is sheaf-relative, and the degree-1 reduction yields cycle-space witnesses and observation requirements. We evaluate two finite one-round models. Across 15,625 degree-1 inputs, an all-agent additive primitive solves decision and repair exactly; the optimal pairwise system reaches 88.80% on decision, one input above the 88.79% majority-class baseline, and 26.63% on repair. On a degree-2 tetrahedral-boundary task over 531,441 inputs, the same-2-skeleton system retains all four three-agent primitives yet matches the pairwise-only optimum throughout the registered…

  PDF
• arXiv cs.CLOct 19

  Monsoon: Scalable Spontaneous Speech Collection for Low-Resource ASR in 50 Languages

  Shobhit Banga, Manas Dhir, Aaditya Pareek, Amritansh Walecha, Bhaskar Singh +6

  For most languages, automatic speech recognition (ASR) is limited less by model architecture than by a lack of accurately transcribed spontaneous speech. We present Monsoon, a framework for collecting such data at scale. It elicits unscripted conversations between paired contributors, screens recordings with automated classifiers, corrects transcripts over five levels of human review, and selects segments for lexical and acoustic coverage. It has collected speech in 50 languages; we analyse seven 3,500-hour corpora. At equal volume, its quality stages reduce semantic word error rate (WER) by 10-39% relative to a conventional protocol. Compared with an architecture-matched baseline trained on public corpora, Whisper fine-tuned on Monsoon performs comparably on the baseline's own test sets and reduces semantic WER by 20-44 points on conversational benchmarks. The gains transfer to a second architecture and grow with data volume. We release the framework, its quality-control models, and the fine-tuned models.

  PDF
• arXiv cs.LGOct 19▲ 25

  HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

  Zhuoshi Pan, ZhiYuan Feng, Yukuo Cen, Honglin Lin, Junru Lu +4

  Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with higher execution costs. We introduce HarnessPro, a label-free method for evolving harnesses to improve task performance while reducing execution cost. In this setting, candidate harnesses are evaluated using LLM-generated tests without access to ground-truth solutions or official tests. Specialized agents diagnose execution trajectories, plan updates with different performance-cost priorities, and implement them as candidate harnesses. Rather than returning a single harness, HarnessPro uses normalized weighted squared-distance selection to provide cost-focused (lite), balanced (medium), and performance-focused (heavy) harnesses for different deployment budgets. Selected harnesses enter the next iteration, where execution feedback guides further updates. Our experiments cover Terminal-Bench 2, SWE-Bench Pro, and ProgramBench, using GPT-5.5 with Codex and GLM-5.2 with Claude Code. Across these benchmarks using GPT-5.5 with Codex, the heavy mode of HarnessPro achieves an average pass-rate…

  Code
• arXiv cs.LGOct 19

  Simulation Priors for Rapid Adaptation in Model-Based RL for Autonomous Racing

  Adrian Remonda, Jiajun Xi, Nicklas Hansen, Marcus Greiff, Thomas Lew +3

  Reinforcement learning enables learning high-performance control policies, but its reliance on extensive interaction limits deployment on physical systems where data collection is costly, and failures are unsafe. We introduce Prior-Informed Adaptation (PIA), an offline-to-online model-based RL framework that uses structured simulation priors for rapid adaptation. PIA pretrains a world model on heterogeneous low- and high-fidelity simulated trajectories, then adapts it with limited target-domain interaction using uncertainty-regularized planning. Rather than requiring an accurate simulator for policy transfer, PIA treats simulated trajectories as biased priors whose residual mismatch is corrected during online adaptation. We evaluate PIA in autonomous racing using high-fidelity simulation and on a real full-size autonomous race car. In simulation, PIA adapts faster across track and surface shifts than strong baselines, achieving lower lap times and fewer failures. On hardware, PIA achieves reliable few-shot adaptation with less than one hour of on-vehicle interaction.

  PDF
• arXiv cs.CLOct 19

  TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning

  Liana Patel, Rishabh Ranjan, Ion Stoica, Matei Zaharia, Carlos Guestrin

  Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters. On the other hand, language models process all input tokens through each model layer, resulting in significant processing costs for long-context inputs. We introduce TokenGate, a small, drop-in component that extends existing trained models to enable end-to-end learnable token pruning over long-context inputs for fast and memory-efficient prefill. To enable end-to-end learning despite the non-differentiable top-K operator for token pruning, we introduce token-gated attention, a mechanism inspired by Mixture-of-Experts that re-weights attention logits using token importance scores. Across diverse tasks, TokenGate achieves $1.4$-$11.3\times$ faster time-to-first token (TTFT) and $1.5$-$3.4\times$ lower peak memory at no accuracy degradation for prefill in transformers. Compared to the best-performing prior methods for token-pruning, TokenGate gives up to $6.4\times$ faster prefill and $2\times$ lower peak memory. TokenGate natively extends both standard transformers (e.g., Qwen3) and hybrid-attention models (e.g., Qwen3.5) with simple lightweight…

  PDF
• arXiv cs.CVOct 19

  Beyond Omni: A Unified MLLM for Embodied Sensory Understanding

  Shiyun Xiong, Dongming Wu, Peiwen Sun, Bokang Yang, Jiaxu Wang +3

  Recent embodied systems increasingly build on multimodal large language models (MLLMs) for their pretrained understanding and reasoning capabilities, but their perception of the physical world remains largely limited to basic modalities such as vision and audio. However, broadening MLLMs to more diverse sensory modalities from the physical environment is challenging: their representations are often weakly connected to the MLLM and vary substantially in structure and statistics, while their interpretation still requires shared high-level understanding and reasoning. We therefore propose Unisense, a unified embodied MLLM framework that supports diverse physical sensory modalities within a shared multimodal architecture. Unisense follows a two-stage training process: (i) aligning sensory representations with language to establish a language-accessible interface; and (ii) tuning modality-specific experts within the shared LLM to provide specialized processing for different sensory modalities. To support broad sensory learning, we curate Unisense-1M, a large-scale embodied sensory training corpus comprising 1M samples across 8 sensory modalities. We further evaluate Unisense on 12…

  PDF
• arXiv cs.LGOct 19

  Trajectory Replay: Continuous-Time Mixture Transport for Lifelong Generative Models

  Alessandro Palma, Charles Jones, Tristan Cinquin, Fabian J. Theis, Frederik Wenkel

  Adapting pre-trained continuous-time generative models to sequentially incoming data without forgetting earlier tasks is a central challenge in lifelong learning. A leading strategy, generative replay, uses a generative model trained on historical tasks to augment its own continual update with synthetic samples from experience. However, it requires full trajectory simulations at every training step, which accumulate discretization errors and can degrade the replayed historical distribution. Here, we propose trajectory replay, which bypasses sample generation by training an updated velocity field to match both a frozen historical velocity along its trajectories and the incoming task's velocity field, weighted by a stability-plasticity coefficient. Through the lens of continuous-time transport, we show the resulting optimum averages the two task velocities by their respective densities and generates the mixture of their probability paths. Combined with mean velocity distillation, trajectory replay accesses historical trajectories using only a few network evaluations per continual update. Empirically, it outperforms generative replay and distillation baselines on class-incremental…

  PDF
• arXiv math.OCOct 19

  Gradient descent reaches arbitrary accuracy in a fixed number of large steps on multiclass logistic regression

  Andreea-Alexandra Musat, Nicolas Boumal

  We show that gradient descent (GD) with step size $η$ can achieve $\varepsilon$ optimality gap on the multiclass logistic regression loss in a number of iterations $T$ that is independent of $\varepsilon$. To do so, the step size $η$ must be chosen large enough as a function of $\varepsilon$ (and properties of the linearly separable dataset), while $T$ is a constant that only depends on the data. The relevant properties of the data include the number of points and their margin (for $T$), and one additional quantity (for $η$) that turns out to be necessary in dimension $d \geq 3$. The proofs build on the known fact that, as $η\to \infty$, suitably rescaled GD becomes the perceptron algorithm, and the latter finds a perfect classifier in $T$ iterations. A similar claim was shown for two classes in dimension $d = 2$ using other proof techniques. This result adds to previous works that showed GD on the logistic regression loss can be accelerated by taking large step sizes. Those provoke a wild, oscillatory initial phase, followed by a stable phase. We provide results of this (qualitatively different) nature, too.

  PDF
• arXiv cs.LGOct 19

  recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language Models

  Saurav Jha, Qianli Liao, Robert Vernon, Sarath Chandar, Quentin Fournier

  Protein language models (pLMs) are powerful tools for protein annotation and mutation-effect prediction, but progress has largely depended on scaling model size and data, making them expensive and prone to memorization. Test-time scaling offers a complementary path, but methods developed for autoregressive LLMs do not transfer directly: masked encoders lack a generation loop, and amino acids do not verbalize in a reasoning language. Instead, we adapt recursive pretraining to masked pLMs, where a weight-tied Transformer core refines residue-aligned hidden states over an adjustable number of cycles. We instantiate this recipe as recAMPLIFY, a pLM with 155M unique parameters trained on the same 2T tokens as AMPLIFY-350M. Despite 56% fewer parameters, it improves CASP contact recovery and three out of four supervised tasks, notably raising fold accuracy by 22.5%. Because optimal depth for recAMPLIFY varies across tasks and assays, we then introduce Gated Mixture Recurrence (GMR), a framework that decodes each protein from a probability-weighted mixture of hidden states visited during recursion. GMR employs a learned residual gate at scalar, low-rank, or per-dimension resolution to…

  PDF
• arXiv math.NAOct 19

  Polar Switch: Fast Muon Orthogonalization with Polynomial Circuits

  Zhehang Du, Weijie Su

  Muon, a 2024-born optimizer for language models, differs from the 2015-born spectral gradient descent mainly in its fast, GPU-friendly Newton--Schulz polynomial for orthogonalizing the gradient matrix. Accordingly, a line of research proposes faster polynomial iterations for gradient orthogonalization, such as Polar Express and Gram Newton--Schulz, both built on quintic polynomials. In this paper, we introduce Polar Switch, a new approach to polynomial gradient orthogonalization. Using simple polynomial circuits, Polar Switch reaches a given high polynomial degree at a lower FLOP cost than quintic iterations. We define a circuit as a short sequence of symmetric matrix products on a few square buffers, and circuits with $k$ products form a restricted family of odd polynomials of degree up to $2^{k+1}+1$. We choose the sequence of products in each circuit, their coefficients, and how the circuits are composed by numerically minimizing a worst-case bound on the polar approximation error. This minimization is subject to a FLOP budget that accounts for symmetric matrix multiplication kernels and a rounding constraint for numerical stability in half precision. Our two recommended Polar…

  PDF
• arXiv cs.CVOct 19

  CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image Editing

  Yaqi Cai, Zuan Gao, Mengting Chen, Wei Li, Bo Zheng

  Reinforcement learning for instruction-guided image editing requires reward models that provide reliable, accurate, and efficient feedback. Direct scalar prediction compresses multidimensional editing preferences, whereas generative evaluators can expose their judgment through explicit reasoning. However, broad scoring criteria do not specify all instance-dependent editing and preservation constraints, and generating long reasoning trajectories is costly for online optimization. We introduce CheckDistill, a pointwise reward modeling framework that internalizes instruction-adaptive checklists. We decompose each editing condition into atomic, independently verifiable requirements and construct four-dimensional scoring labels together with structured verification evidence. After supervised score initialization, a privileged teacher conditions on checklists, item-level judgments, and dimension-level rationales to supervise the student's own scoring trajectories. A reliability-weighted on-policy self-distillation objective adjusts supervision at score tokens according to agreement between the teacher's expected scores and reference labels, while retaining candidate probability weights…

  PDF