Research

• Compositional coverage and decision grounding in trajectory supervision1 paper raises it · 1 addresses it

  Current tool-use trajectories often lack multi-step dependencies and justified actions, limiting effective agent learning.

  • Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agentsraises · addresses
• Benchmarking agent harness reliability and failure attribution1 paper raises it · 1 addresses it

  Existing benchmarks focus on model capabilities, neglecting the evaluation of agent harnesses and their reliability.

  • Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
• Compositionality of RAG pipeline components1 paper raises it · 1 addresses it

  Isolated gains in RAG components do not necessarily compose, and optimizing one metric can hurt another.

  • Retrieval Augmented Generation Compositionalityraises · addresses
• Token collapse in graph soft prompting1 paper raises it · 0 address it

  Graph-specific tokens in textual graph soft prompting become indistinguishable, failing to convey graph content.

  • On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
• Label-free monitoring in self-supervised learning1 paper raises it · 0 address it

  Standard signals like loss and feature statistics fail to detect encoder degradation in self-supervised training.

  • Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learningraises

Named by an AI from these papers' abstracts.

• arXiv cs.CVOct 9

  Knowing Whether, Not Just Where: Anchor-Probing Distillation for Open-Set Remote Sensing Visual Grounding

  Zhihao Chang, Lei Zhai, Shuyuan Yang, Zhixi Feng

  Open-set visual grounding in remote sensing requires models to determine not only where a queried object is located, but also whether the image provides sufficient evidence for the query at all. Existing closed-set grounding models, however, tend to return plausible boxes even for absent objects, blurring localization confidence with genuine Visual Support. We introduce AnchorProbe-Distill (APD), a teacher-student framework that recasts open-set grounding as Visual Support learning. APD builds on the insight that supported queries should induce coherent spatial anchors, whereas unsupported or mismatched queries tend to produce unstable or misleading localization patterns. APD-T therefore uses the Original Query as a Reference Anchor to interpret query perturbations: Semantic-Preserving Queries retain the annotated target, Near-Category Ambiguous Queries are resolved according to whether they form a reliable alternative anchor or collapse onto the Reference Anchor, and Far-Category Counterfactual Queries provide rejection supervision. This reference-aware reasoning is distilled into APD-S, enabling unified localization and rejection from a single image--query pair. Experiments…

  PDF

  Summarize this
• arXiv cs.AIOct 9

  MAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution Failures

  Loan Bernat, Matthieu Grard, Ariane Herbulot, Florent Lamiraux

  Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. Existing benchmarks investigate dynamic task execution and embodied multi-agent coordination, but provide limited evaluation of their intersection. We introduce MAGMA-Bench, an architecture-agnostic benchmark for persistent task reasoning in dynamic multi-robot environments. MAGMA-Bench evaluates agents across increasing task horizons and controlled online perturbations, including execution failures, task interruptions, and mission updates, with scenarios requiring coordination across robots with heterogeneous capabilities. It uses a structured skill-level interface to separate task-level reasoning from perception and low-level control. We evaluate locally deployable open-weight planners, multi-agent state-tracking strategies, and frontier models. Even the strongest evaluated models fail on a substantial fraction of clean episodes, and their success rates decrease further under online perturbations. Supervised adaptation greatly improves a small model, but performance remains substantially lower on longer and multi-robot missions.…

  PDF

  Summarize this
• arXiv cs.CVOct 9▲ 298

  S-Space: Exploring Spatial Workspace in Multimodal Language Models

  Zhiyuan Shi, Xiang Li, Xingzhuo Guo, Shangchen Miao, Weiliang Chen +6

  Multimodal language models (MLLMs) exhibit promising spatial reasoning capabilities, yet the internal mechanisms supporting them remain poorly understood. We uncover S-Space, a linear representation subspace in which object-token representations encode continuous coordinates along horizontal, vertical, and distance axes. Although we identify these axes by differentiating spatial-answer scores with respect to object-token activations, S-Space is intrinsic rather than induced by specific data or prompts, remaining readable under non-spatial questions. We show that S-Space functions as an internal spatial workspace of MLLMs. Perception encodes object locations into it, forming spatial representations that can be directly read out to support accurate spatial judgments. Internal reasoning transforms it for changing viewpoints. Verbal responses selectively access it, evidenced by causal interventions that alter spatial judgments while largely preserving non-spatial responses. Case studies further show that S-Space assigns locations to unseen entities and the observer, and connects physical directions with abstract linguistic meanings, suggesting both the capabilities and limitations of…

  Code
• arXiv cs.LGOct 9

  Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models

  Ran Tian, Courtney Paquette

  Intermittent ``spikes'' in loss, during the pre-training of Large Language Models (LLMs), remains a mysterious phenomenon both theoretically and empirically. In this paper, we show that simple quadratic models with heavy-tailed, power-law distributed inputs can replicate these spikes. We introduce a theoretical framework and simulation algorithm to model per-layer training dynamics of Deep Neural Networks (DNNs), using such quadratic models. In a case study on an Adam hyperparameter configuration (where $β_2$ is set close to $1$) known to induce spikes in Transformer LMs, our simulation successfully predicts bumps indicating spiky behavior from a given checkpoint. Furthermore, we derive an appropriate $β_2$ schedule from observed metrics, which empirically improves performance.

  PDF

  Summarize this
• arXiv cs.ROOct 9

  Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics

  Peiyan Tu, Cong Wang, Hanxin Zhu, Xin Jin, Zhibo Chen

  Action-conditioned world models offer a promising foundation for generalist robotic intelligence by predicting the consequences of actions. However, existing robotic datasets provide limited coverage of the diverse interaction dynamics required for generalizable world modeling. Large-scale egocentric human videos offer complementary interaction experience, yet the embodiment gap between human hands and robotic manipulators hinders effective cross-embodiment learning. Meanwhile, the predominance of successful demonstrations leaves failure dynamics substantially underrepresented, limiting the ability of world models to anticipate unsuccessful executions. To address these limitations, we introduce HF-WM, an action-conditioned world model that combines Human interaction learning with Failure-aware post-training. To bridge the embodiment gap, we develop a dual-branch framework that couples video generation with auxiliary pointflow prediction, using stabilized pointflow as a unified motion representation across human and robot interactions while suppressing egocentric camera motion. To improve failure modeling, we further perform Group Relative Policy Optimization (GRPO) post-training…

  PDF

  Summarize this
• arXiv cs.AIOct 9▲ 243

  Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation

  Shi-Yu Tian, Yong Liu, Ximan Liu, Tianrui Zhu, Sule Bai +8

  Multi-teacher on-policy distillation (MOPD) extends on-policy distillation (OPD) by routing domain-specific data to specialized teachers, integrating their capabilities through dense token-level supervision on student-generated trajectories. However, domain routing only distinguishes the supervision sources for different domains; updates from all domains still act on shared parameters. When teachers differ substantially in response style and domain expertise, supervision that is effective in isolation may still lead to persistent gradient conflicts and capability degradation during joint optimization. To address this challenge, we propose Cross-Teacher Guarding for MOPD (Road MOPD), which introduces non-routed teachers as auxiliary cross-domain critics on the same student trajectories and coordinates multi-teacher supervision through token-level credit assignment and gradient updates. Specifically, cross-teacher-guided credit assignment uses teacher agreement to strengthen token-level corrections jointly supported by the teachers and attenuate conflicting signals; preventive multi-teacher gradient projection uses auxiliary gradients from the same trajectories to constrain…

  PDF

  Summarize this
• arXiv cs.AIOct 9

  Causal Effect Identifiability in Causal Abstractions: A Strict Hierarchy of Criteria

  Clément Yvernes, Marianne Clausel, Emilie Devijver, Eric Gaussier

  Identifying causal effects from observational data typically requires a fully specified causal graph, an assumption that is often unrealistic in complex or high-dimensional settings. Causal abstractions address this limitation by retaining only partial causal information, thereby defining equivalence classes of compatible causal graphs. In this paper, we study causal effect identifiability directly at the level of these graph collections, rather than at the level of individual causal diagrams. We formalize several notions of identifiability in this setting and organize them into a hierarchy that clarifies their relationships and differences. In particular, we establish that a causal effect may be identified over a collection of graphs without admitting a single causal derivation that holds uniformly across all compatible graphs. These results help reveal gaps and clarify ambiguities in the existing literature.

  PDF

  Summarize this
• arXiv stat.MLOct 9

  A Stochastic Analysis Perspective on Diffusion Models

  Stanislas Strasman

  Generative modelling involves two complementary tasks: learning a probabilistic approximation of an unknown data distribution from observations, and designing a tractable mechanism for sampling from this approximation. We present a stochastic-analysis perspective on score-based generative models, connecting ideas from classical sampling theory, score estimation, and diffusion time reversal. We first explain how score functions link Langevin sampling with score matching, and how Gaussian smoothing leads to denoising score matching and multiscale sampling methods. We then emphasize the distinction between dynamics preserving a fixed distribution and dynamics transporting a prescribed family of marginals. This motivates a path-space treatment of diffusion time reversal. Finally, we connect the ideal reverse diffusion with practical generative algorithms.

  PDF

  Summarize this
• arXiv math.DSOct 9

  Asymptotic Analysis of Discrete-Time Self-Attention Dynamics in Transformers

  Claudio Altafini

  In machine learning, a self-attention dynamics describes the attention mechanism of transformers, and is obtained treating the layer index of a transformer as time index. Even though naturally discrete-time, this dynamical system is most often studied in continuous-time. Scope of this paper is to provide a thorough investigation of the discrete-time version of the self-attention dynamics: a complete classification of its equilibria is given, and their stability properties are studied, in both the single-head and the multihead case. We show that in both cases the main attractor of the dynamics is a consensus equilibrium aligned with the principal eigenvector of the value matrix (in the single-head case, a corresponding matrix of weights in the multihead case), even though other locally asymptotically stable bipartite equilibria can be show to exist at least in the single-head situation. The behavior is confirmed by looking at the learned weight matrices of a real transformer.

  PDF

  Summarize this
• arXiv cs.ROOct 9

  RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors

  David Ahmedt-Aristizabal, Abdelwahed Khamis, Mohammad Ali Armin, Lars Petersson

  Runtime failure monitors for robot policies are typically evaluated by how accurately they distinguish failed from successful executions. Yet an accurate alarm may arrive too late for recovery, while an unnecessary intervention may disrupt an execution that would otherwise succeed. We introduce RESCUE, a counterfactual framework for evaluating whether a monitor's alarms enable useful interventions. By restoring simulator and policy states at execution checkpoints, RESCUE compares alternative actions, identifies the latest checkpoint satisfying a specified recovery criterion, and evaluates whether acting on alarms reduces expected task-completion cost. We evaluate RESCUE with OpenVLA-OFT and $π_{0.5}$ over LIBERO-Spatial and LIBERO-Plus using 128,340 counterfactual branches. Recoverability depends on the state--intervention pair rather than on robot state alone: at $τ=0.5$, 14 of 66 OpenVLA-OFT/LIBERO-Plus failures contain a recoverable checkpoint under continuation, compared with 34 of 66 under continuation or scripted recovery, while recovery reduces recoverability in other conditions. On the primary strong-policy conditions, favourable detection scores do not establish lower…

  PDF

  Summarize this
• arXiv cs.AIOct 9

  Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis

  Hamza Shafiq, Jialu Tang, Ting Dang, Jun Hu, Aaqib Saeed

  Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRISM (Population-Retrieved Inference for Structured Multimodal Prognosis), a multimodal language model that combines per-feature numerical tokenization, recency-weighted aggregation of longitudinal ECGs, and a dual-modality population memory bank. Retrieval operates in representation space: the model receives mean-pooled embeddings of similar training-cohort encounters, while no individual retrieved record enters the prompt. On the 1,443-task MDS-ED benchmark, PRISM achieves AUROCs of 86.2% for diagnosis, 93.1% for deterioration, 91.8% for ICU admission, and 92.8% for mortality. These results use a 96-hour pre-arrival window unavailable to reported baselines. With benchmark-window inputs only, PRISM reaches 0.8895 AUROC, compared with 0.8937 for UniPACT and 0.8889 for MDS-ED. A matched-input compact fusion model using the same five evidence streams and frozen encoders reaches 0.7652 AUROC, versus 0.9092 for PRISM. Replacing numerical EHR encoding with text serialization reduces AUROC by 3.66 points; removing pre-arrival history…

  PDF

  Summarize this
• arXiv cs.LGOct 9

  FedPCD: Priority-Constrained Federated Aggregation

  Yousef Irshaid, Dara Varam, Mohamed I. AlHajri

  Federated learning (FL) seeks to optimize a shared global model from decentralized client data. While effective for average performance, this process can produce unfair performance across clients, particularly under statistically heterogeneous data distributions. Existing fairness-aware and multi-objective FL methods address this through client re-weighting, gradient correction, or common-descent formulations, but often change the global optimization direction or treat client objectives symmetrically. We propose FedPCD, a priority-constrained federated optimization framework that separates the global optimization objective from client protection. FedPCD preserves the conventional federated aggregate as the primary objective, while allowing only the minimum correction necessary to meet client performance constraints. Across heterogeneous FL benchmarks, FedPCD consistently outperforms state-of-the-art baselines, achieving the highest global accuracy across all configurations and leading worst-10% client accuracy in nearly all. FedPCD further preserves competitive trade-offs between global accuracy and client performance variability. Beyond this trade-off, FedPCD demonstrates faster…

  PDF

  Summarize this
• arXiv cs.LGOct 9

  Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning

  Oriol Corcoll, Qiyao Wei, Ciarán Mark Gilligan-Lee

  Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after a decision. Standard RL propagates reward according to temporal proximity rather than explicit relevance, attenuating the signal assigned to distant but important actions and creating a source of sample inefficiency. We introduce Explanatory World Models (EWM), an attribution framework that uses explanations to identify the earlier events that plausibly contributed to a realized outcome. We instantiate EWM with a frontier language model and use its explanations as learning signals using a conservative hierarchical operator that recursively redistributes reward while preserving the undiscounted episode return. To investigate what constitutes a useful explanation, we operationalize three complementary variants inspired by Halpern's actual causation, Lombrozo's explanatory simplicity, and Deutsch's hard-to-vary explanations. We evaluate EWM on two controlled long-horizon RL benchmarks, a public sequential-recommendation benchmark, and an industry-scale generative recommender. On Crafter and WordCraft, EWM substantially outperforms PPO…

  PDF

  Summarize this
• arXiv cs.CVOct 9

  SplatQ: Interaction-Aware Pruning of 3D Gaussian Splatting via Quadratic Selection

  Hongbin Ye, Haixu Liu, Shenwei Kang, Wenxiu Wei, Tinglan Wang +11

  Existing 3D Gaussian Splatting (3DGS) pruning methods primarily rely on global Top-K selection based on independent importance scores, lacking regional budget control and ignoring joint deletion effects. Consequently, they cannot ensure balanced reconstruction quality across a scene. We propose SplatQ, a combinatorial pruning algorithm that coordinates regional budget allocation and joint Gaussian selection under a fixed budget. SplatQ partitions Gaussians by spatial proximity and appearance similarity into size-limited blocks, decomposing global selection into subproblems of a specific size. It then smooths importance-based block retention quotas to prevent excessive budget concentration. Finally, it constructs a quadratic approximation of joint deletion effects using the responses of representative pixel colors to changes in Gaussian opacity. Individual responses, pairwise interactions, and quota penalties are incorporated into a quadratic unconstrained binary optimization (QUBO) objective, solved using simulated annealing (SA) or a coherent Ising machine (CIM) to jointly select Gaussians. Experiments on 5 benchmarks demonstrate that SplatQ outperforms state-of-the-art pruning…

  PDF

  Summarize this
• arXiv cs.CVOct 9

  Stride: Scale-Aware Multi-Agent Evolutionary Refinement for Infographic Generation

  Yan Zhou, Yang Yang

  Infographic generation challenges text-to-image models because a single image must satisfy numerous visual, textual, and semantic constraints. Iterative agentic refinement with a multimodal verifier is a natural remedy, but existing methods face a scale mismatch: local edits cannot correct global composition errors, while full regeneration may destroy already-correct regions. We introduce Stride, a constraint-grounded multi-agent framework that treats refinement over any frozen generator as a history-aware evolution strategy. Stride separates constraint evaluation - whether each requirement is satisfied - from visual grounding - where and how it is violated. It then routes global revisions to a composer subagent and local corrections to a retoucher subagent. Each subagent conducts internal planning and generates multiple candidates, while Stride accepts a candidate only when it improves the verifier score, reducing regression across iterations. Because stochastic generators and imperfect verifiers make any single step unreliable, it is this combination of scale-aware routing, per-step redundancy, and monotonic acceptance that yields stable improvement across iterations. With…

  PDF

  Summarize this
• arXiv cs.AIOct 9

  Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits

  Changye Li, Zijian Zhang, Muheng Li, Yiduo Pang, Tingjun Wu +10

  Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnesses that manage tools, skills, and accumulated experience. However, we find that as single-session execution lengthens, the agent's reasoning intensity declines alongside slowing progress, summarized as long-horizon deceleration, and the benefits of these custom harnesses vanish as the underlying model improves, summarized as harness staleness. These findings suggest that their benefits may not persist across versions, which motivates a workflow-level approach in which agents build on one another's work across sessions. We model these alternating agent sessions as a context-reset semi-Markov decision process (CR-SMDP) and establish sufficient conditions for alternation to exceed single-agent reference limits, derive an explicit experiment-budget bound, and characterize when session caps preserve this advantage. Guided by this analysis, we introduce Humanize MLE Agents (HMA), which alternates two agents on a shared workspace, limits each session to at most k experiments and resets the context between sessions, without additional…

  PDF

  Summarize this
• arXiv cs.CVOct 9

  Neural Block-wise Auto-exposure for Single-Shot High Dynamic Range Imaging

  Zhengguo Li, Chaobing Zheng, Wei Wang

  Block-wise varying exposures are effective for cap- turing appearance of a real-world high dynamic range (HDR) scene via a single-shot. However, brightness order reversal (BOR) artifacts, blocking artifacts and loss of details in highlight/shadow regions are possible issues for block-wise varying exposures. In this paper, a novel neural block-wise auto-exposure algorithm is proposed to address the issues. The proposed algorithm maps a temporary image and its exposure time to the exposure times of all non-overlapping 16 X 16 blocks. The temporary image can be either an sRGB or a raw image. Although the sRGB image is widely adopted in existing auto-exposure algorithms, exposure times of blocks in the highlight and shadow regions might not be accurately learned due to the limited radiance measurement capability of the sRGB image. This paper thus also explores the feasibility of temporary image as a raw image. Due to the better radiance measurement capability of the raw image, the exposure times of blocks are learned more accurately, and more details in the highlight/shadow regions of the real-world HDR scene are captured by the resultant HDR imaging system. Experiment results…

  PDF

  Summarize this
• arXiv cs.CLOct 9

  Proactive Agentic Orchestration

  Xueyang Feng, Chaozhuo Li, Xiaohe Bo, Jiakai Tang, Chenxi Li +2

  Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of large language model agents. However, existing orchestration methods face two limitations: in execution, current methods fix sub-agents' goals and harnesses at creation time, limiting their adaptability to dynamic real-world environments; in optimization, sparse and delayed feedback constrains effective learning of the orchestration policy. To address these limitations, we introduce POrchestra, an on-the-fly proactive agentic orchestration framework. It allows sub-agents to proactively communicate with the orchestrator at any logical point to request harness adjustments while maintaining continuity of local execution. This mechanism not only enables sub-agents to adapt seamlessly to dynamic environments but also naturally inspires On-Policy Orchestration Distillation (OPOD) based on hindsight feedback. OPOD attributes sub-agents' proactive revision requests back to preceding orchestration decisions to derive targeted improvement signals, and leverages these signals as process supervision alongside the final reward to optimize the…

  PDF

  Summarize this
• arXiv cs.AIOct 9▲ 9

  Branching On-Policy Distillation

  Dongyang Chen, Shudong Liu, Shubo Li, Duoxun Tang, Jinwei Liang +2

  On-policy distillation (OPD) provides teacher supervision on student-generated trajectories, but a single trajectory realizes only one continuation at each decision, limiting supervision coverage under a finite sampling budget. We propose BranchOPD (Branching On-Policy Distillation), which selects informative decision points using student uncertainty and teacher-student disagreement, resamples student-policy continuations from shared prefixes, and applies token-level teacher supervision to both main trajectories and branches. BranchOPD operates at token-level decisions in mathematics and within-turn decisions in agent tasks. Shared-prefix reuse reduces student-generated token costs by approximately 19% on ALFWorld and 31% on WebShop relative to seven independent trajectories. We also introduce protocol-boundary repair (PBR), which uses targeted supervision under protocol constraints to mitigate repetition and wasted generation. BranchOPD outperforms Vanilla OPD and Multi-Rollout OPD (n=7) across all evaluated benchmarks, with gains over Vanilla OPD of 18.55 percentage points in mean mathematics accuracy over 16 sampled answers (avg@16) and 13.8 points in mean ALFWorld ID/OOD…

  PDF

  Summarize this
• arXiv math.OCOct 9

  A Scalable Learned Iterative Solver for Nonlinear MPC via Temporal Decomposition

  Lukas Lüken, Sergio Lucia

  Nonlinear model predictive control (NMPC) can be applied to large nonlinear systems with complex objectives while enforcing constraints, but the cost of solving the underlying optimization problems limits real-time application for systems with fast dynamics or many states. Neural networks can reduce this online cost by approximating the control law, but may violate constraints and typically require many precomputed optimizer solutions for training. The learning-based iterative solver for constrained optimization (LISCO) instead learns to predict primal-dual steps toward satisfaction of the Karush-Kuhn-Tucker (KKT) conditions through self-supervised training without precomputed solutions, but its dense, monolithic architecture grows with the prediction horizon. We remove this horizon dependence by exploiting the temporal structure of the problem in the solver architecture, which makes the network size independent of the horizon while leaving the training loss and the solver iteration unchanged. A closed-loop resampling strategy further aligns the training distribution with closed-loop operation at no additional sampling cost. On an economic NMPC benchmark of a CSTR cascade, the…

  PDF

  Summarize this

• Anomaly detectors27+80.0%
• Channel state information18+63.6%
• AI tutors16+45.5%
• Multimodal emotion9+28.6%
• Character recognition OCR12+20.0%
• Physics informed neural148−6.3%
• Machine learned interatomic44−10.2%
• Medical image segmentation165−11.3%