Artificial Intelligence · Cross-listed from cs.LG
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina et al. (+3 more)
LLM
agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-only rewards provide too sparse guidance, failing to inform the model about the goodness of intermediate actions. Dense supervision methods aim to solve this problem by scoring intermediate steps, from intrinsic confidence to self-
distillation and
embedding similarities. However, it is common practice to evaluate them by measuring the downstream performance of a training pipeline that integrates them. This is expensive, conflates supervision quality with training engineering confounders, and renders different methodological families requiring distinct training setups incomparable. As a result, dense supervision methods are rarely benchmarked on common ground. We introduce QVal, a training-free testbed for directly evaluating dense supervision signals. Given a state-action pair, QVal measures how well a method's score is Q-aligned: whether it orders actions according to the Q-values of a strong reference-policy. This lets us compare signals before any training run and separate signal quality from other engineering choices. We instantiate QVal as QVal-v1.0, benchmarking 21 dense supervision methods across four diverse environments and seven methodological families, with over 1.2K evaluation experiments across six open-weight model backbones. We find that simple prompting baselines consistently outperform recent dense supervision methods from the literature, and that performance clusters strongly by family. These findings hold across model sizes, environments, and observation modalities. QVal is designed to be easily extensible to new environments and methods, enabling researchers to iterate on dense supervision methods before any training run.
Read the full abstract ▾
All authors Sergio Hernández-Gutiérrez, Matteo Merler, Ilze Amanda Auzina, Joschka Strüber, Ameya Prabhu, Matthias Bethge
Artificial Intelligence · Cross-listed from cs.CL
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona et al. (+2 more)
Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowledge boundaries, and misrepresent their internal uncertainty–undermining trustworthiness and reliability. Since monitoring task performance and adapting behavior accordingly are central to metacognition, we posit that models capable of accurately judging their own performance are better positioned to improve it. We operationalize this idea via two novel mechanisms: reinforcement learning with metacognitive feedback (RLMF), a paradigm to refine completion rankings during preference optimization based on the quality of a model's self-judgments of performance, and metacognitive data selection, which uses similar self-judgments to identify high-value training examples, outperforming naive active learning. We apply these innovations to the problem of faithful calibration (FC), a task that is itself fundamentally metacognitive: the goal is to align expressed with intrinsic uncertainty, difficult even for frontier LLMs. We adopt a two-stage, decoupled approach, first using these methods to calibrate the faithfulness of models' self-reported confidence scores, then mapping to natural, context-adaptable linguistic uncertainty via targeted output editing. Extensive experiments show RLMF achieves generalizable, state-of-the-art FC on diverse tasks while preserving accuracy. Further, RLMF surpasses standard RL by up to 63% while enhancing models' ability to assess and express their own capability limits. This positions RLMF as a promising paradigm to enhance LLM metacognition toward improved abilities and
alignment, and suggests metacognitive performance as an effective RL signal to overcome limits of prior intrinsic feedback methods.
Read the full abstract ▾
All authors Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona, Idan Szpektor, Arman Cohan
Artificial Intelligence · Cross-listed from cs.CL
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Yuqing Yang, Qi Zhu, Zhen Han et al. (+5 more)
While large
language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of intermediate
reasoning steps. Yet prior studies have only offered limited, small-scale analyses. In this work, we present the first systematic evaluation of tabular data referencing errors across different models and tasks. Our results show that DREs occur across all tested models (1.7B to 20B parameters). Furthermore, we demonstrate that incorporating data referencing as a critic significantly improves answer accuracy up to 12.0%, through critic-based filtering and rejection sampling. Finally, we trained a lightweight 4B-parameter critic model that achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-distribution DREs, and effectively assists inference for larger models.
Read the full abstract ▾
All authors Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala
Artificial Intelligence · Cross-listed from cs.RO
Freeform Preference Learning for Robotic Manipulation
Marcel Torne, Anubha Mahajan, Abhijnya Bhat et al. (+1 more)
Reward design remains a central bottleneck for autonomous
robot policy improvement, especially in long-horizon manipulation tasks where sparse success labels provide too little signal and binary preferences collapse many competing notions of quality into one ambiguous signal. We introduce Freeform Preference Learning (FPL), a method for learning
robot policies from freeform human preferences. Rather than asking annotators which of two trajectories is better overall, FPL lets them define natural-
language preference axes, such as speed, safety, quality of placement, or carefulness, and provide pairwise preferences along each axis. These annotations are used to learn a
language-conditioned reward model that maps a trajectory and preference label to an axis-specific reward. We use this model to train a reward-conditioned policy that optimizes across the multiple human-specified dimensions. Across four real-world and two simulated long-horizon manipulation tasks, FPL improves over sparse-reward and binary-preference methods by 38 percentage points. Beyond improved performance, FPL learns dense progress signals without explicit subtask
segmentation, shows compositionality of behavior not present in the data, and allows users to steer the policy towards different behaviors at test time without retraining. Blog post with
videos available at https://freeform-pl.github.io/fpl.website/
Read the full abstract ▾
All authors Marcel Torne, Anubha Mahajan, Abhijnya Bhat, Chelsea Finn
Artificial Intelligence · Cross-listed from cs.LG
AdaJEPA: An Adaptive Latent World Model
Ying Wang, Oumayma Bounou, Yann LeCun et al. (+1 more)
Latent world models enable planning from high-dimensional observations by predicting future states in a compact latent space. However, these models are typically kept frozen at test time: when their predictions become inaccurate, planning can fail, especially under test-time distribution shift. To address this, we propose AdaJEPA, an adaptive latent world model that performs test-time adaptation within the closed loop of model predictive control (MPC). After training, AdaJEPA plans and executes the first action chunk, uses the observed next-state transition as a self-supervised adaptation signal, and replans with the updated model. This closed-loop update continuously recalibrates the world model without additional expert demonstrations. Across a range of goal-reaching tasks, AdaJEPA substantially improves planning success with as few as one gradient step per MPC replanning step.
Read the full abstract ▾
All authors Ying Wang, Oumayma Bounou, Yann LeCun, Mengye Ren
Artificial Intelligence · Cross-listed from cs.CV
FLORA: A deep learning approach to predict forest attributes from heterogeneous LiDAR data
Emilie Vautier, Clément Mallet and Cédric Vega
Forest attributes are essential for national-scale resource monitoring. Airborne
LiDAR metrics are among the auxiliary variables most strongly correlated with forest attributes used in National Forest Inventory (NFI) estimates. However, producing wall-to-wall predictions remains challenging when
LiDAR data are acquired under heterogeneous conditions. As national
LiDAR programs expand across Europe, variability in sensors, flight parameters, seasons, and scan angles limits the robustness of existing models, which are often calibrated for local conditions. We present FLORA (Forest
LiDAR Octree Regression with Auxiliary Data), a deep learning framework that predicts six forest attributes: dominant height, total volume, deciduous volume, coniferous volume, basal area, and stem density from heterogeneous
LiDAR point clouds. FLORA combines an octree-based backbone with ecological and spatiotemporal auxiliary variables through a late-fusion gating mechanism. Models are trained and evaluated on 32,052 National Forest Inventory plots across mainland France using data from the French
LiDAR HD program. A single model trained on both leaf-on and leaf-off acquisitions outperforms season-specific models and improves cross-season robustness. Auxiliary variables provide modest overall gains but contribute more strongly to species-specific volume prediction. FLORA achieves an rRMSE of about 12.3% (R2 = 0.88) for dominant height and 39% (R2 = 0.74) for total volume, providing a robust baseline for large-scale forest attribute estimation from heterogeneous national
LiDAR programs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
Yuanda Xu, Zhengze Zhou, Hejian Sang et al. (+6 more)
Agentic reinforcement learning requires assigning credit to environment-facing actions such as searches, clicks, edits,
navigation commands, and object interactions. Standard GRPO uses the final verifier outcome as a uniform advantage over all action
tokens. This outcome signal is useful but structurally incomplete: it punishes useful exploration in failed rollouts and reinforces redundant or regressive actions in successful rollouts. We propose TRIAGE, a role-typed credit assignment framework that adds a semantic role axis to outcome credit. A structured judge classifies each segment as decisive progress, useful exploration, no-progress infrastructure, or regression, and a fixed role-conditioned rule maps these labels to bounded segment-level process rewards. This keeps verifier outcomes as the source of optimization direction while correcting the two main blind spots of outcome-only credit. We further show that the Bayes-optimal role-measurable correction is the L2 projection of the per-segment advantage residual onto the role variable, and that TRIAGE's fixed role constants approximate this projection, reducing advantage estimation error whenever the judge is reliable; we connect this to lower-variance policy gradients. Across ALFWorld, Search-QA, and WebShop, TRIAGE improves success rates over GRPO for two policy models and outperforms both a scalar judge-derived process reward and an outcome-supervised shared-backbone value baseline. Ablations show that the gain comes from role typing rather than merely adding dense rewards: reliable detection of regression inside successful trajectories is the dominant contributor, while exploration credit provides a consistent secondary gain; on completed ALFWorld and WebShop rollouts, TRIAGE also reduces environment-facing turns by an additional $10.4\%$ and $14.8\%$ relative to GRPO.
Read the full abstract ▾
All authors Yuanda Xu, Zhengze Zhou, Hejian Sang, Xiaomin Li, Jiaxin Zhang, Xinchen Du, Sen Na, Zhipeng Wang, Alborz Geramifard
Artificial Intelligence
AxDafny: Agentic Verified Code Generation in Dafny
Benjamin Breen, Austin Letson, Borja Requena Pozo et al. (+1 more)
We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification. We present AxDafny, a verifier-guided repair framework that iteratively generates implementations, invariants, assertions, and termination arguments. We also introduce LiveCodeBench-Pro-Dafny (LCB-Pro-Dafny), a
benchmark of 250 competition-style programming problems translated into Dafny with formal specifications and a verifier-based evaluation harness. On LCB-Pro-Dafny, AxDafny substantially improves verification success over baseline GPT-5.5 performance. On DafnyBench, AxDafny achieves 92.7% verification success, outperforming the strongest previously reported proof-hint baseline by 6.5 percentage points. Lastly, we show that verification success and runtime test performance measure different aspects of generated code.
Read the full abstract ▾
All authors Benjamin Breen, Austin Letson, Borja Requena Pozo, Leopoldo Sarra
Artificial Intelligence
PolicyGuard: From Organizational Policies to Neuro-SymbolicCompliance Review Engines
Sameer Malik, Ayush Singh and Amar Prakash Azad
Policy-grounded document review requires determining whether a target document complies with organization-specific policies, guidelines, or playbooks. While large
language models can assist with policy interpretation and document analysis, end-to-end prompting leaves the applied policy logic implicit, making compliance decisions difficult to inspect, update, and test. We present PolicyGuard, a neuro-symbolic framework for policy-grounded document compliance review. PolicyGuard converts organizational policy guidance into an executable review engine consisting of typed relational logic rules and atom-level extraction questions. During review, LLMs answer these local questions using retrieved document evidence, and a symbolic evaluator applies the formal rules to detect non-compliance. We instantiate and evaluate PolicyGuard on company-specific NDA compliance review, where contract clauses must be checked against organization-specific negotiation policies. By separating policy formalization, local document interpretation, and symbolic compliance evaluation, PolicyGuard makes document review more explicit, maintainable, and systematically testable.
Read the full abstract ▾
Artificial Intelligence
Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA
Ekaterina Alimaskina, Denis Shveykin, Gleb Molodtsov et al. (+3 more)
Language models are increasingly taught from synthetic question–answer (QA) supervision: a model generates questions about a document, answers them from the same text, and the resulting pairs are used to fine-tune, distill, or compress knowledge into another model. We show that this generation step is not neutral preprocessing. It is an implicit policy that both selects which evidence becomes training signal and decides how that evidence is answered, and it is fragile at both stages. When choosing what to ask, generators do not scan a document uniformly. Coverage saturates early and concentrates on salient spans, diverse
prompts converge on the same regions, and what looks question-worthy is driven by local presentation. As a result, salient artifacts such as poorly cleaned markup can hijack question generation across model families and scales. When answering, the model that produces the supervision tends to obey instruction-like passages embedded in the text. This compliance depends on the intent and surface form of the passage rather than its strictness, and is worst under task conflict, where larger models comply more often. These failure modes arise from choices made during QA generation, so they can be reduced without changing the training loop. Tying each question to a fixed target reduces biased selection, and filtering instruction-like spans before answering lowers mean injection compliance from $88\%$ to $13\%$ in our evaluation while retaining nearly all clean text.
Read the full abstract ▾
All authors Ekaterina Alimaskina, Denis Shveykin, Gleb Molodtsov, Igor Shalygin, Alexey Kadeishvili, Aleksandr Beznosikov
Artificial Intelligence · Cross-listed from cs.LG
Radial Suppression Accelerates Algorithmic Generalization: A Geometric Analysis of Delayed Generalization
Srijan Tiwari, Aditya Chauhan and Manjot Singh
Why do neural networks memorize algorithmic training data long before they generalize? We present a
geometric case study demonstrating that, on tasks where generalization requires discovering structured low-dimensional
circuits, the memorization-generalization delay is driven by radial inflation of hidden representations under cross-
entropy optimization. We formalize a radial-angular decomposition of activation-space dynamics and derive three testable propositions: (i) that penalizing radial inflation induces anisotropic, data-dependent weight regularization; (ii) that it suppresses radial gradient energy below the isotropic random baseline, forcing predominantly angular updates; and (iii) that it biases convergence toward flatter minima. To empirically validate these propositions, we study a single-hyperparameter norm penalty that softly constrains activations to a sqrt(d)-radius hypersphere. On modular arithmetic, this penalty accelerates grokking up to 6x across MLPs and
Transformers, and halves training steps for a 10M-parameter nanoGPT on 3-digit addition.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Anchored or Drifting: What Recursive Self-Generation Reveals About Training Data
Wojciech Łapacz and Stanisław Pawlak
Large generative models are known to memorize their training data, posing severe
privacy risks. Yet, current methods to detect training membership typically rely on the weak signals of a single forward pass. In this work, we find that training samples and unseen (held-out) data follow visibly different trajectories under recursive self-generation – repeatedly feeding a model's output back as its next input. Held-out samples drift: they lose the specifics of the original within a few steps. Training samples stay anchored, degrading far more slowly. We show that the membership signal this produces holds across model modalities, architectures and scales, spanning
language,
diffusion, and autoregressive
vision models. Furthermore, these recursive trajectories provide a signal that raises membership inference TPR at $1\%$ FPR for nearly every attack we evaluate, roughly doubling it on the weakest baselines and still improving the strongest, which shows that a model's behavior under recursion carries membership evidence that a single query does not.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.IR
GR2 Technical Report
Yufei Li, Zaiwei Zhang, Mingfu Liang et al. (+68 more)
Industrial recommendation systems serve billions of users through a multi-stage funnel –
retrieval, early-stage ranking, and re-ranking – where the final re-ranking step disproportionately shapes user engagement and downstream performance, particularly for carousel and grid display formats. Despite growing enthusiasm for Large
Language Models (LLMs) in recommendation, three gaps hinder industrial adoption: (1) most efforts target
retrieval and ranking, leaving re-ranking – the stage closest to the final user experience – largely underexplored; (2) LLMs are typically deployed zero-shot or via supervised fine-tuning, underutilizing the
reasoning capabilities unlocked by reinforcement learning (RL) on verifiable rewards; (3) deployed catalogs index billions of items with non-semantic identifiers that lie outside any base-LLM vocabulary. We present GR2 (Generative
Reasoning Re-Ranker), an end-to-end framework that combines (i) mid-training on semantic IDs produced by a tokenizer with >=99% uniqueness, (ii)
reasoning-trace distilled from a stronger teacher via targeted prompting and rejection sampling, and (iii) RL with verifiable rewards purpose-built for re-ranking. To make GR2 resource-viable, we further (iv) introduce a context compressor that amortizes training cost, On-Policy
Distillation (OPD) as a scalable alternative to SFT – which we find collapses at industrial scale – and
reasoning distillation for low-latency serving. GR2 delivers +18.7% R@1, +7.1% R@3, and +9.6% N@3 over legacy baselines on industrial-scale traffic. We further find that reward design is critical in re-ranking: LLMs often hack rewards by preserving the incoming order or exploiting position bias, motivating conditional verifiable rewards as essential industrial components.
Read the full abstract ▾
All authors Yufei Li, Zaiwei Zhang, Mingfu Liang, Kavosh Asadi, Jay Xu, Jimmy Kim, Chongyang Bai, Jieyi Zhang, Hongye Xie, Prachi Agrawal, Dian Yu, Tianyi Chen, Jean-Pascal Billaud, Garret Buell, Yongkang Zhu, Sachin Patil, Brooke Bian, Zhou Fang, Kevin Huang, Shiva Sudanagunta, Yuzhen Huang, Emma Lu, Chris O'Brien, Yang Song, Lihong Li, Jacob Tao, Zhicheng Zhu, Chao Li, Gaoxiang Liu, Neil Wu, Zhongyin Hu, Li Han, Loki Chen, Ming Lei, Greg Rehm, Siyuan Song, Tianwei Zhang, Li Li, Ketan Singh, Yavuz Yetim, Ilyas Atishev, Satendra Gera, Ashkan Sadeghi, Rachel Yan, Nikko Mizutani, Shuaiwen Wang, Song Yang, Zhijing Li, Jiang Liu, Mengying Sun, Fei Tian, Xiaohan Wei, Chonglin Sun, Shuo Gu, Parish Aggarwal, Senthil Manickavelu, Kaushik Rangadurai, Zhi Hua, Frank Shyu, Ruchit Sharma, Liyuan Li, Shike Mei, Wenlin Chen, Santanu Kolay, Ben Schulte, Deepak Chandra, Yang Song, Sandeep Pandey, Xi Liu, Hamed Firooz, Luke Simon
Artificial Intelligence · Cross-listed from cs.CV
LUNA: Learning Universal 3D Human Animation Beyond Skinning
Peng Li, Rawal Khirodkar, Junxuan Li et al. (+6 more)
Creating photorealistic, animatable 3D human avatars from
monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressivity and often introduce artifacts due to imperfect fitting. We propose LUNA, an LBS-free universal neural animation model that directly maps multiple 2D controls like images, keypoints, sketches, and unseen characters into 3D Gaussian deformations, bypassing explicit body fitting. At its core, a
transformer-based motion regressor disentangles global rigid motion from fine-grained local dynamics to capture both coherent movement and subtle non-rigid effects. To resolve the inherent ambiguity of 2D-to-3D lifting while scaling beyond fitted
datasets, we introduce hybrid supervision that distills soft structural priors from an LBS teacher and a loss that supports training on both limited fitted data and large in-the-wild unlabeled
videos. Extensive experiments show LUNA achieves competitive visual fidelity compared to LBS-based approaches, while delivering realistic human motion and zero-shot cross-identity generalization across diverse driving modalities. To the best of our knowledge, LUNA is the first end-to-end 3D animatable model that supports implicit 2D driving.
Read the full abstract ▾
All authors Peng Li, Rawal Khirodkar, Junxuan Li, Yuan Dong, Chen Cao, Yuan Liu, Wenhan Luo, Yike Guo, Shunsuke Saito
Artificial Intelligence · Cross-listed from cs.CL
DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching
Meng Chen, Anya Ji, Tsung-Han Wu et al. (+4 more)
Agents are increasingly capable of automating software tasks, but can they teach humans how to use software themselves? We introduce DigitalCoach, a
multimodal dataset of 72 human expert-novice computer use coaching sessions consisting of 22,752 dialogue turns grounded in 28.1 hours of screen and input event recordings across five software applications. We use DigitalCoach to evaluate whether state-of-the-art models can teach humans how to use computers. Automated evaluation shows that models differ from humans in how they coach: models provide more direct instructions, but fewer explanations, error diagnoses, and knowledge-check questions. When we fix the coaching method, models produce utterances similar to human references yet poorly grounded in visual context. Interactive evaluation confirms that model coaches cause learners to passively follow instructions without deeper engagement and fall short in visual grounding. DigitalCoach lays a foundation for collaborative and proactive computer use coaching
agents. Data and code are available at https://project-digital-coach.vercel.app.
Read the full abstract ▾
All authors Meng Chen, Anya Ji, Tsung-Han Wu, Tobias Maringgele, David M. Chan, Alane Suhr, Amy Pavel
Artificial Intelligence
TreeAgent: A Generalizable Multi-Agent Framework for Automated Bias Labeling in Forestry via Compiled Expert Rules and Vision-Language Models
Shiyi Chen, Nicholas Saban, Collin Hargreaves et al. (+1 more)
Human-labeled data are widely used as reference annotations in ML, despite known variability across annotators in many expert-driven domains. In addition, expert annotation is slow, inconsistent, and remains a major bottleneck for scaling tasks like tree height bias classification in forestry remote sensing. We propose a multi-
agent system (MAS) that orchestrates expert decision trees with
Vision-
Language Models (VLMs), treating the decision tree as a structural prior while VLMs perform localized semantic perception at individual nodes, with multi-
agent voting to mitigate VLM stochasticity. We formalize a Decoupled Declarative Decision (D3) Framework that enables zero-modification generalization across diverse expert-defined decision structures. On a tree bias classification testbed, our framework outperforms supervised ML baselines and reduces the amount of expert labeling effort required. These results suggest that agentic orchestration of VLMs with expert priors can reproduce expert-defined labeling procedures at substantially lower annotation cost while maintaining interpretability.
Read the full abstract ▾
All authors Shiyi Chen, Nicholas Saban, Collin Hargreaves, Huiqi Wang
Artificial Intelligence · Cross-listed from cs.MA
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
Qingyun Liu, Jiwen Zhang, Jingyi Hu et al. (+2 more)
Recent
multimodal large
language models (MLLMs) have strong potential as
embodied agents, but their ability to collaborate in visually grounded environments remains underexplored. To address this gap, we introduce MECoBench, a
multimodal embodied cooperation
benchmark with an evaluation platform spanning diverse real-world tasks, two cooperation structures, and three collaboration modes. Through extensive experiments across various MLLMs, we summarize three key findings: (i) Collaboration generally improves
embodied task completion, but its benefits depend on balancing collaborative gains against coordination complexity. (ii) Communication is essential to collaboration gains, while the best collaboration mode depends on team size and model capability. (iii) Moreover, collaboration improves robustness under noisy priors and exploration conditions. Generally, MECoBench provides a systematic testbed for understanding the mechanisms and limits of
multimodal embodied collaboration. Code and
dataset are available at https://github.com/q-i-n-g/MECoBench.
Read the full abstract ▾
All authors Qingyun Liu, Jiwen Zhang, Jingyi Hu, Siyuan Wang, Zhongyu Wei
Artificial Intelligence · Cross-listed from cs.RO
LeCropFollow: Latent Space Planning for Navigation in Unstructured Crop Fields
Felipe Tommaselli, Francisco Affonso, Arthur Pompeu et al. (+4 more)
Unstructured navigational features, such as irregular planting or discontinuities, remain the primary failure mode for under-canopy agricultural
robots. Existing
geometric approaches often fail in these scenarios because they compress high-dimensional visual data into deterministic spatial references, effectively discarding the uncertainty and semantic context required to navigate ambiguous terrain. To address this, we present LeCropFollow, a visual
navigation framework that bypasses explicit
geometric modeling in favor of a learned latent representation. By integrating a self-supervised semantic heatmap extractor with TD-MPC2, a Model-Based Reinforcement Learning (MBRL) planner, our system optimizes trajectories directly within a latent
manifold. The framework operates over the uncompressed heatmap signal, preserving the semantic context that
geometric reductions discard. We demonstrate that this representational shift enables zero-shot transfer from simplified simulation to the physical world without fine-tuning. Extensive field experiments in late-stage corn fields show that LeCropFollow matches state-of-the-art baselines in unstructured rows but significantly outperforms them in plantation gaps, achieving a 2.4x reduction in semantic failures compared to keypoint-based methods. These results suggest that latent planning offers a robust alternative to
geometric estimation for operations in heterogeneous agricultural environments. Code, models, and data available: https://felipe-tommaselli.github.io/lecropfollow .
Read the full abstract ▾
All authors Felipe Tommaselli, Francisco Affonso, Arthur Pompeu, Gianluca Capezzuto, Arun Narenthiran Sivakumar, Girish Chowdhary, Marcelo Becker
Artificial Intelligence · Cross-listed from cs.RO
MVP-Nav: Multi-layer Value Map Planner Navigator
Wenyuan Xie, Shaokai Wu, Yijin Zhou et al. (+7 more)
Zero-shot Object Goal
Navigation (ZSON) with RGB-only perception poses a fundamental challenge for
embodied agents, as the absence of explicit depth information introduces severe physical uncertainty and semantic-physical misalignment. Existing approaches either rely on high-level semantic
reasoning without
geometric grounding or learn end-to-end policies that lack explicit physical constraints, often resulting in semantically plausible but physically unsafe behaviors. In this paper, we propose MVP-Nav, a physical-aware RGB-only
navigation framework that aligns perception, planning, and control with the real 3D world. MVP-Nav reconstructs explicit physical occupancy from
monocular observations by leveraging 3D foundation models to project 2D semantic instances into 3D oriented bounding boxes, forming a global spatial semantic representation. To unify high-level semantic
reasoning and low-level physical constraints, we introduce a Multi-layer Value Map (MVM) that integrates semantic priorities and reconstructed geometry into a shared cost space, enabling physically grounded
geometric planning. Extensive experiments on zero-shot object
navigation benchmarks demonstrate that MVP-Nav significantly outperforms existing depth-free methods, achieving state-of-the-art performance and validating that structured physical priors can effectively compensate for the absence of active depth sensors.
Read the full abstract ▾
All authors Wenyuan Xie, Shaokai Wu, Yijin Zhou, Yanbiao Ji, Guodong Zhang, Bayram Bayramli, Qiuchang Li, Xunchu Zhou, Yue Ding, Hongtao Lu
Artificial Intelligence · Cross-listed from cs.CV
Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference
Zhaoyang Luo, Runmin Dong, Miao Yang et al. (+4 more)
Multimodal large
language models (MLLMs) increasingly process long visual-
token sequences, increasing the overall inference computation. Existing acceleration methods usually remove visual
tokens or skip visual-
token updates in entire layers, but these coarse strategies may discard fine-grained evidence or suppress useful operators together with redundant ones. In this paper, we study visual-
token computation from an answer-observable perspective and find that late visual-
token updates can remain large while having little effect on answer-
token representations. Motivated by this answer-silent redundancy, we decompose each
Transformer layer into
attention and FFN operators and show that useful visual computation is often operator-dominant and layer-dependent. We propose an operator-level visual-
token skipping framework that preserves the full visual-
token sequence while selectively bypassing redundant
attention, FFN, or both. Experiments across three MLLM architectures and 10 VQA
benchmarks show that our method achieves strong efficiency-accuracy trade-offs, reducing 33.7% TFLOPs on Qwen3-VL while retaining 99.5% of the vanilla model performance.
Read the full abstract ▾
All authors Zhaoyang Luo, Runmin Dong, Miao Yang, Fan Wei, Yushan Lai, Bin Luo, Haohuan Fu
Artificial Intelligence · Cross-listed from cs.LO
Better Understanding, Understanding Better
Yu Wei
"Any fool can know; the point is to understand." A well-known remark often attributed to Einstein captures a widely shared intuition: understanding is more than merely knowing. Yet epistemic logic has paid relatively little
attention to understanding, despite its central role in contemporary epistemology, philosophy of science, and recent debates about AI. A recurring theme in the philosophical literature is that, unlike knowledge, understanding comes in degrees: one may understand something more or less well, and one's understanding may be better than another's. We introduce a comparative epistemic logic of understanding with level-indexed understanding modalities and a comparative connective for saying that one
agent understands why a proposition better than another
agent does. Semantically, we enrich multi-
agent epistemic models with
agent-indexed graded explanation structures and a justification-style term
algebra. This yields a unified framework for representing minimal, ordinary, more demanding, and ideal understanding, together with comparisons between
agents with respect to the same formula at issue. We distinguish a finitary bounded-level calculus from an infinitary full-
language companion system. We establish soundness and strong completeness, and show that each fixed finite-level fragment is decidable.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LO
Modal CEGAR-tableaux with RECAR and resolution-based SAT-shortcuts
Rajeev Goré and Cormac Kikkert
We investigate two approaches for extending CEGAR-tableaux with SAT-shortcuts using a previously known approach called RECAR but also a totally new approach using the modal resolution
theorem prover KSP as an oracle. Our experiments using our C++ implementation CEGARBox++ of CEGAR-tableaux show that: (1) CEGARBox++ with RECAR SAT-shortcuts is not competitive (2) CEGARBox++ using KSP to provide SAT-shortcuts is superior to both CEGARBox++ and KSP, particularly on large satisfiable problems. As far as we know, this is the first effective integration of SAT, tableaux and resolution methods for modal satisfiability which performs better than its parts.
Read the full abstract ▾
Artificial Intelligence
Harnessing Textual Refusal Directions for Multimodal Safety
Moreno D'Incà, Nicu Sebe and Massimiliano Mancini
Safety in
Multimodal Large
Language Models (MLLMs) depends on unsafe
multimodal data for post-training
alignment or activation steering. However, such data is hard to collect, must be gathered anew for each modality, and its collection and distribution raise ethical and legal concerns. In this work, we relax this constraint and investigate whether textual refusal directions, extracted directly from the LLM backbone, generalize across modalities (i.e., image,
video). Preliminary findings confirm this ability, though effectiveness is conditioned by layer selection, steering strength, and cross-modal
alignment, with the latter causing safe
multimodal inputs to be spuriously steered toward refusal. Building on this, we introduce Modality-Agnostic Refusal Steering (MARS), a lightweight training-free approach that injects
multimodal safety without the need for
multimodal safety data. MARS corrects modality misalignment via activation centering, adaptively scales steering strength within a geometrically defined trust region, and selects the optimal intervention layer, operating at the first generated
token. Evaluated on five SOTA MLLMs across safety, utility, and
video jailbreak, MARS achieves consistent safety gains while preserving utility up to over-refusal. MARS reveals that safety-relevant structure is shared across modalities and that textual refusal directions are a powerful and underexplored foundation for
multimodal alignment.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LO
Belief Contraction in Dynamic Epistemic Logic
Gaia Belardinelli and Snow Zhang
Dynamic epistemic logic represents belief change via model transformations induced by epistemic events. Its standard formulation (Baltag, Moss, Solecki, 1998) provides a natural account of belief expansion through the elimination of possibilities, but it cannot model belief contraction about factual propositions. A classic response enriches Kripke models with plausibility orderings, representing contraction as an update that promotes certain possibilities over others. We show that this approach has expressive limitations. In particular, the approach cannot model belief that violates positive introspection and contraction dynamics in response to a hedged public announcement that phi might be false. Motivated by these considerations, we introduce a mechanism for belief contraction defined directly on standard Kripke models, without any constraints on the doxastic accessibility relation. We show that it satisfies some of the standard properties of belief contraction but not others, study the conditions under which contraction may be unsuccessful, and provide a sound and complete axiomatization of the logic via reduction axioms. We also define a more general dynamic logic that is an extension of standard DEL and accommodates belief contractions due to events such as private or semi-private announcements, and provide a complete and sound axiomatization of the general logic.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models
Lang Cao, Renhong Chen, Luyi Li et al. (+3 more)
Vision-
Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting
language instructions, visual observations, and continuous control. However, most existing policies remain limited by behavior cloning or supervised fine-tuning (SFT) from fixed demonstrations, which provides limited opportunity to improve from the policy's own failures. In this paper, we present Z-1, a reinforcement learning (RL) post-training framework for flow-based VLA models. Built on top of $\pi_{0.5}$, Z-1 uses only publicly released RoboCasa demonstrations for SFT and then applies a task-wise Group Relative Policy Optimization (GRPO) strategy across $24$ standard RoboCasa tasks. To improve the efficiency and stability of online optimization, Z-1 combines shared-prefix rollout construction, tree-structured trajectory branching, completion-aware reward calibration, and selective joint training of VLM and Action Expert. Across all $24$ RoboCasa tasks, Z-1 achieves an average success rate of $80.6\%$, improving over its SFT initialization by $13.2\%$ points and outperforms the published sota models. These results show that systematic GRPO post-training can substantially improve flow-based VLA policies without additional private demonstrations.
Read the full abstract ▾
All authors Lang Cao, Renhong Chen, Luyi Li, Peng Wang, Mofan Peng, Yitong Li
Artificial Intelligence · Cross-listed from cs.RO
Bridging Local Observation and Global Simulation in Closed-Loop Traffic Modeling
Ziyan Wang, Tan Xiang, Peng Chen et al. (+1 more)
A local-to-global context mismatch arises when autoregressive traffic simulators trained on ego-centric driving logs are deployed in globally observable closed-loop environments. In such logs, the ego vehicle has rich local observations, while surrounding
agents are only partially observed due to perception limits and occlusions. As a result, simulators may learn incomplete context–action mappings that remain hidden in log-based training but emerge during closed-loop rollouts, leading to unrealistic behaviors such as abnormal stops, unsafe interactions, and rule violations. We propose CRAFT, a Contextual pReference
Alignment Framework for Traffic Simulation, to mitigate this mismatch via self-supervised failure discovery and preference-guided test-time
alignment. CRAFT treats the base simulator as a globally observable sandbox, generating diverse what-if rollouts from logged initial states to expose context-induced failures. These failures are grounded with human-aligned driving priors and converted into preference supervision for training a Contextual Preference Evaluator (CPE). At inference time, CPE acts as a plug-in
alignment module that scores candidate actions under complete scene context and reweights autoregressive decoding toward globally coherent behaviors. CRAFT mitigates this local-to-global contextual bias, reducing collisions by 31.2% and traffic violations by 33.2% without retraining the base simulator.
Read the full abstract ▾
All authors Ziyan Wang, Tan Xiang, Peng Chen, Xintao Yan
Artificial Intelligence · Cross-listed from cs.CV
Real-Time Source-Free Object Detection
Sairam VCR, Varun Gopal, Poornima Jain et al. (+2 more)
Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and
memory constraints, yet existing source-free object detection (SFOD) methods rely on heavyweight architectures that prioritize accuracy alone. We show this trade-off is unnecessary: building on YOLOv10, an NMS-free dual-head detector, we achieve state-of-the-art adaptation accuracy while being faster and more compact. We observe that directly applying vanilla mean-teacher self-training to dual-head detectors leads to suboptimal adaptation performance due to two key factors. First, simple pseudo-label generation strategies, such as using a single head or directly combining high-confidence predictions from both heads, yield suboptimal supervision under domain-shift. We propose DHF (Dual-Head Pseudo-Label Fusion) which selectively admits one-to-one (O2O) and one-to-many (O2M) head predictions, preserving precision and recovering missed objects. Second, we observe domain-shift collapses multi-scale feature discriminability. We propose the use of our MARD (Multi-scale Adaptive Representation Diversification) loss which mitigates this by enforcing detection-aware variance and covariance constraints on multi-scale feature maps. Both modules are training-time only, leaving inference unchanged. Across domain-shift
benchmarks, our method, RT-SFOD yields 1.4 to 3.5% mAP gains, 1.3$\times$ higher throughput, with $\sim$2$\times$ fewer parameters than prior state-of-the-art SFOD methods, thus advancing the Pareto frontier of the speed-accuracy-model size trade-off. We report main results with YOLOv10, and demonstrate generalizability with additional YOLO- and DETR-based dual-head detectors. Code is available here: https://github.com/Sairam13001/RT-SFOD/
Read the full abstract ▾
All authors Sairam VCR, Varun Gopal, Poornima Jain, Vineeth N Balasubramanian, Muhammad Haris Khan
Artificial Intelligence
An Agentic AI Framework to Accelerate Scientific Discovery in Plant Phenotyping
Renan Souza, Daniel Rosendo, Kelsey Carter et al. (+6 more)
High-throughput plant phenotyping now generates image derived
datasets far faster than scientists can analyze them. At Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory (APPL), automated stations image hundreds of plants daily across multiple remote sensing modalities; yet, trait extraction and interpretation remain manual, expert-bound, and strictly post-hoc, making analysis, not acquisition, the binding constraint on discovery. We present an end-to-end agentic AI framework that turns the facility from a data factory into an interactive autonomous, discovery platform, where scientists partner with AI
agents to accelerate time to insight. A conversational Co-Scientist
Agent translates a scientist's natural-
language question into a structured analysis plan, and a headless Compute
Agent dispatches
Vision Transformer segmentation and trait extraction on the Frontier exascale supercomputer. The two
agents run in separate security and resource domains and communicate over a secure,
token-authenticated streaming channel, a design that accounts for the federation, data-movement, and provenance realities cloud-native agentic frameworks ignore, ensuring end-to-end provenance is captured for every interaction. The framework turns a days- to weeks-long analysis process into an interactive loop where
agents reason over results, recommend next analyses, and respond to follow-up questions in seconds.
Read the full abstract ▾
All authors Renan Souza, Daniel Rosendo, Kelsey Carter, John Lagergren, Frédéric Suter, Shelaine L. Curd, Gerald A. Tuskan, Rafael Ferreira da Silva, David Weston
Artificial Intelligence · Cross-listed from cs.CV
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
Junha Jung, Minbyul Jeong, Suhyeon Lim et al. (+5 more)
Recent
multimodal large
language models have shown great promise in clinical image
reasoning, but existing post-training pipelines remain predominantly outcome-centric, relying on final answer correctness or sequence-level preferences. This suffers from sparse credit assignment, making it difficult to optimize the
reasoning process essential for clinical applications. Our analysis reveals that cascading errors from early-stage
reasoning failures are a leading cause of incorrect predictions in medical visual question answering (VQA)
benchmarks. Motivated by this, we propose Medical
Reasoning-aware Policy Optimization (MRPO), an RL
algorithm that incorporates step-wise process rewards. When the final answer is incorrect, MRPO assigns exponentially larger penalties to
tokens in earlier invalid
reasoning steps, breaking failure cascades without compromising successful paths. Across four
multimodal LLM backbones, MRPO consistently outperforms standard GRPO and a recent RL baseline, and on Qwen3-VL-8B-Thinking even surpasses substantially larger medical MLLMs such as HuatuoGPT-
Vision-34B by 4.59 points. Moreover, MRPO reduces early-stage
reasoning failures from 58.6% to 13.4%, showing that targeted mitigation of cascading failures improves both
reasoning quality and final answer accuracy. Our code is available at https://github.com/dmis-lab/MRPO
Read the full abstract ▾
All authors Junha Jung, Minbyul Jeong, Suhyeon Lim, Sungwook Jung, Jaehoon Yun, Taeyun Roh, Mujeen Sung, Jaewoo Kang
Artificial Intelligence
Adaptive Cluster-First Route-Second Decomposition for Industrial-Scale Vehicle Routing
Oguzhan Karaahmetoglu and Hyong Kim
Large-scale capacitated vehicle routing problems (CVRPs) are commonly addressed using cluster-first route-second (CFRS) approaches that split a routing instance into smaller, computationally tractable subproblems. Existing splitting methods typically rely on fixed partitioning rules, predefined optimization objectives, or learned policies, which may perform inconsistently across instances exhibiting different spatial, demand, and operational characteristics. In this work, we propose an adaptive CFRS system that formulates a decomposition procedure as an iterative decision-making process. Motivated by the recent success of large
language models (LLMs) in
reasoning and tool selection, the system employs an LLM as a high-level decision maker that analyzes the evolving decomposition state and selectively applies further clustering, balancing, and refinement operators. The proposed
algorithm jointly partitions customers and vehicles, enabling capacity-aware clustering while adapting partitioning decisions to the characteristics of each problem. We evaluate the approach on synthetic and
benchmark-derived CVRP instances containing up to 500,000 customers. Experimental results demonstrate competitive performance on
benchmark-scale instances while exhibiting improved scalability and robust routing quality on substantially larger problems. These results highlight the potential of adaptive, LLM-guided decision support as a practical approach for industrial-scale vehicle routing and large-scale logistics planning.
Read the full abstract ▾