Artificial Intelligence · Cross-listed from cs.LG
Learning Graph Energies for Finite-Time Generation
Amartya Banerjee, Xingyu Xu, Caroline Moosmüller et al. (+1 more)
Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at
equilibrium need not yield accurate samples when the sampler stops after a fixed number of steps. We introduce finite-horizon energy learning, which adapts the acceptance energy of a Metropolis–Hastings sampler to the distribution it returns after a prescribed number of steps, with initialization, proposals, and annealing schedule held fixed. For graph generation, a frozen pretrained model supplies initialization and proposals, and a learned energy governs acceptance. A training-only discriminator scores completed samples, and coupled continuations of the accepted and rejected branches of a proposal give an acceptance-gradient
estimator that is unbiased for a fixed discriminator under stated conditions, without equilibrated negative samples or differentiation through discrete states. Generation uses the learned energy in the original single-trajectory sampler, without discriminator evaluations or reranking. On twelve pairwise binary targets with exactly evaluated terminal laws, learned energies have lower median terminal total variation than the
equilibrium-correct energy in every tested short-horizon setting, and than its numerically tuned scalar multiple in most settings. On MOSES, a learned two-coefficient combination of pretrained Graph Energy Matching (GEM) potentials lowers FCD by 3.7–10.5% relative to scale-calibrated GEM at matched sampling steps, with validity gains at the shortest budget and a sub-point validity trade-off at higher budgets.
Read the full abstract ▾
All authors Amartya Banerjee, Xingyu Xu, Caroline Moosmüller, Harlin Lee
Artificial Intelligence · Cross-listed from cs.CL
Does Machine Translation Retain Media Bias?
Silvia V. Gargova, Tim Menzner and Jochen L. Leidner
Within the most recent two decades, machine translation (MT) has been advanced from a research area to a mature, deployed technology for prose text and most
language pairs. However,
language has different dimensions of meaning, and the alluded progress has primarily been demonstrated for propositional meaning. In this small exploratory study, we investigate whether one type of affective meaning, namely different types of linguistically expressed media bias, are retained under automatic translation for two
language pairs, English and German as the source
languages, and Bulgarian as the target
language. We evaluate four state-of-the-art translation methods to answer the question whether and to what degree a loss of non-neutral
language (specifically, 27 types of media bias) can occur as a result of applying MT. Our empirical findings are consistent with the claim that MT does not fully retain existing news bias of its input source text, but also may add extra bias of its own. To the best of our knowledge, this is the first experimental study of MT media bias retention.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
MUCO: A Mani-Unit-Structured Manipulation Framework for Compositional Long-Horizon Robot Tasks
Xiangyi Wei, Hanzhe Yao, Jingwen Shang et al. (+3 more)
Learning and executing long-horizon
robot manipulation as complete task trajectories raises data-collection costs, lim?its capability reuse, and causes local failures to cascade into later task stages. We introduce manipulation units (MUs) as reusable operations, each defined by a local goal, an initi?ation condition, and observable success and failure criteria. MUs are learned and verified individually. During execution, consecutive MUs remain coupled through shared environ?ment dynamics. We formulate MU-Structured Manipulation (MUSM) and realize it through MU-Centric Orchestration (MUCO). Given
language and
vision, MUCO constructs an MU sequence, matches each MU to compatible policy models in a frozen capability registry, and dispatches the model with the highest calibrated success rate. Visual verification checks MU outcomes against success and failure criteria and governs transitions, enabling retry or fallback to another model from the current state without re-executing verified MUs. Canonical keys enable checkpoint reuse for equivalent MUs across tasks without new demonstrations or updates. We evaluate MUCO on RLBench, RoboTwin 2.0, and five real-world tasks. MUCO achieves higher complete-task success and verified progress, stronger failure containment, and lower error propagation than baselines. Results demonstrate cross-task MU reuse and het?erogeneous policy composition without joint training, shared backbones, or common action representations.
Read the full abstract ▾
All authors Xiangyi Wei, Hanzhe Yao, Jingwen Shang, Zhenhong Wu, Yang Li, Changbo Wang
Artificial Intelligence
Sparse Transformer: a Controlled Testbed for Mechanistic Interpretability
Anton Korznikov, Alexey Dontsov and Elena Tutubalina
Mechanistic interpretability aims to decompose neural network computations into human-understandable features, yet progress is limited by the absence of ground-truth units to evaluate against. We address this with a Sparse
Transformer (ST): a 5-layer
language model trained on TinyStories whose wide, TopK-sparse MLP forces
neuron specialization. We show that ST
neurons are highly interpretable: they outperform a loss-matched dense
transformer by 43% on AutoInterp, and
circuits of a median of 12
neurons suffice to reproduce individual model predictions. This testbed allows us to directly compare feature learning methods: Transcoder, which approximates the MLP input-output mapping, recovers ST's
neuron vectors with 52.6% higher cosine similarity than Sparse Autoencoder, which only reconstructs outputs. Furthermore, the ST enables a controlled study of polysemanticity: distilling its sparse MLP into a dense counterpart reveals how compression leads to feature superposition. These results show how a known reference basis sharpens evaluation and understanding, a role we hope the ST can serve for the field.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters
Taha Sabir, Alberto Montero Molina, Thinh Quang Ly et al. (+3 more)
Adapting a single
vision-
language model to medical image parsing requires training choices that reflect the demands of each task. We study task-specific adaptation with Qwen3.5-9B for
FLARE 2026 Task 3, covering six task families and seven imaging modalities. Our system couples a shared, frozen 4-bit backbone with LoRA adapters selected from the input question. We customize adapter ranks and
prompts, rebalance rare classification targets, and supplement regression training with dermatology classification examples. On the fixed internal holdout, the task-specific adapters achieve a
dataset-macro balanced accuracy of 0.7791 for classification, a
dataset-macro micro-F1 of 0.6286 for multi-label classification, a counting mean absolute error (MAE) of 11.73, a
dataset-macro detection F1 of 0.8914, a
dataset-macro regression MAE of 9.78, and a report-generation CRIMSON score of 0.8204. On the organizer's 1,703-example hidden-validation set, the submitted system achieves 0.8496 classification balanced accuracy, 0.5338 sample-averaged multi-label F1, and 14.5950 regression MAE. The final 30.1 GB container averages 3.1 seconds per case, including model loading, and produces identical outputs across repeated verification runs. The benefits vary across tasks, supporting the use of task-specific adapter configurations and image budgets within a shared medical
vision-
language model. Code is available at https://github.com/TahaSabir0/
FLARE26-Hexapus.
Read the full abstract ▾
All authors Taha Sabir, Alberto Montero Molina, Thinh Quang Ly, Veronika Dmitrenko, Mohammad Yaqub, Tausifa Jan Saleem
Artificial Intelligence
How GUI Agents Fail: GraceBench for Execution Stability Diagnosis
Ridong Zhang, Shuxian Liang, Chaoqun Wan et al. (+2 more)
As GUI
agents are increasingly deployed for mobile task automation, their reliability depends not only on final task outcomes, but also on whether they reach these outcomes through stable interaction trajectories. In automation workflows, unnecessary actions, detours, and execution errors can add noise to collected data, introduce irreversible side effects, or undermine trust, even when the
agent eventually completes the task. It is therefore important to systematically diagnose the execution stability, including whether an
agent deviates from a feasible path, enters a loop, becomes stagnant, or recovers from unstable actions. Existing
benchmarks, however, primarily assess final task success or a small set of intermediate milestones, leaving step-level execution behavior unclear. To bridge this gap, we introduce GraceBench, an online evaluation framework that represents the reachable interaction space of mobile applications as UI Transition Graphs (UTGs), providing a structural reference for step-level execution diagnosis. To support reliable
alignment between dynamic UI observations and graph states, GraceBench uses
video-grounded trajectory evaluation over this graph-aligned representation, assessing process stability beyond final success with metrics such as deviation rate, loop burden rate, and recovery ability. GraceBench contains 169 tasks spanning 10 applications and constructs 10 UTGs with 2,909 canonical GUI states and 3,116 observed transitions. Across 3,718 trajectories, GraceBench shows that outcome scores hide execution instability: GPT-5.6 Sol achieves the highest success rate (SR) but the lowest recovery ability, 51.24% of successful runs still contain a deviation or loop, and trajectories with the same success rate (SR) and completion rate (CR) can differ substantially in recovery behavior. Code and data will be released on https://iaie-physicalai.github.io/GraceBench.
Read the full abstract ▾
All authors Ridong Zhang, Shuxian Liang, Chaoqun Wan, Zhen Huang, Xian-Sheng Hua
Artificial Intelligence · Cross-listed from cs.LG
Universal Sample-Based Embeddings of Higher-Order Objects
Radovan Haluška, Christopher Solinas, Nathan R. Sturtevant et al. (+2 more)
Neural networks operate naturally on finite-dimensional vectors, yet many problems require
reasoning about higher-order objects such as distributions, functions, and graphs. Such objects capture relationships within a ground set and rarely admit an explicit compact representation. Moreover, we typically want a compact representation not of a single higher-order object but of an entire family of such objects, including members unseen during training. While a few approaches exist for particular object types, none is designed to work across object types. We propose a unified framework that represents any higher-order object as a fixed-size
embedding vector learned over a family of such objects. An encoder maps an object, seen only through a finite set of samples, to an
embedding, and a domain-specific decoder supplies the training signal by modeling the object conditioned on that
embedding. Since the encoder works only from samples, one architecture serves different object types. Because the decoder is a model already suited to single instances of the object type, the framework inherits that model's native operations and inductive biases. We instantiate the framework on distributions, functions, and graphs. In each case we show that a single trained model represents an entire family and generalizes to members unseen during training. Furthermore, we demonstrate the downstream utility of these
embeddings: interpolating distributions in
embedding space, solving differential equations in
embedding space, and predicting unseen edges from a graph's
embedding.
Read the full abstract ▾
All authors Radovan Haluška, Christopher Solinas, Nathan R. Sturtevant, Martin Schmid, Michael Bowling
Artificial Intelligence · Cross-listed from eess.SP
DeepPV-MRF: End-to-End Partial-Volume Fraction Estimation from MR Fingerprinting Time Series
Tianyi Ding, Yang Gao, Zhuang Xiong et al. (+4 more)
Background: Estimating subvoxel tissue fractions from
magnetic resonance fingerprinting (MRF) is challenging. Conventional dictionary matching and segmentation pipelines can propagate errors from intermediate parametric maps into tissue fraction estimates. Purpose: We introduce DeepPV-MRF, a deep learning framework that directly estimates voxel-wise tissue fractions from raw MRF signals. Methods: A cascaded spatial-temporal network was trained on subject-derived Bloch simulations with radial k-space undersampling. The network combines temporal encoding and spatial U-Net refinement to estimate cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM) fractions without intermediate T1/T2 maps. We compared DeepPV-MRF with partial-volume dictionary matching (PV-DM) and pseudoinverse estimation (PV-Pinv) using simulated and in vivo data. Results: DeepPV-MRF outperformed both methods across acquisition settings. In single-shot simulations, CSF/WM/GM mean absolute errors were 0.0418/0.0744/0.0757, versus 0.1281/0.2443/0.2958 for PV-DM and 0.2021/0.2793/0.2630 for PV-Pinv. Corresponding structural similarity values were 0.960/0.916/0.922. In vivo results showed sharper anatomical boundaries and smoother tissue transitions, while cross-shot analysis indicated improved consistency across volunteers. Conclusions: DeepPV-MRF enables accurate and efficient direct tissue fraction estimation from MRF signals, particularly with limited shots. Further validation is needed before clinical deployment.
Read the full abstract ▾
All authors Tianyi Ding, Yang Gao, Zhuang Xiong, Feng Liu, Martijn A. Cloos, Jin Jin, Hongfu Sun
Artificial Intelligence · Cross-listed from cs.CL
Frustratingly Easy Majority Voting Using Length Conditioning
Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu et al. (+4 more)
Majority Voting (MV) is a simple and widely used strategy which improves the
reasoning accuracy of Large
Language Models (LLMs) by allocating additional inference-time computation. Specifically, in MV multiple Chain-of-Thoughts (CoTs) are independently sampled and the most frequent final answer is selected. In this work, we propose Length-Conditioned Majority Voting (LCMV), a Test-Time Training approach which improves MV leveraging an empirical observation that has recently been established in several studies: longer CoTs tend to be associated with a lower probability of correctness. We formulate this inductive bias as a length-conditioned prior probability, which is modeled by a simple logistic function. Moreover, we adapt this prior at test time using only unlabeled testing data and without fine-tuning the LLM. Finally, the adapted prior is used to weight the vote of each sampled answer. Extensive experiments across multiple LLMs and
reasoning benchmarks show that LCMV consistently improves over both standard MV and existing length-based and confidence-based aggregation strategies, while retaining the simplicity and model-agnostic nature of MV. Our code is available at: https://github.com/aimagelab/LCMV.
Read the full abstract ▾
All authors Fiorenzo Parascandolo, Enver Sangineto, Xiaoyi Yu, Wenhui Tan, Jipei He, Ruihua Song, Rita Cucchiara
Artificial Intelligence · Cross-listed from cs.LG
Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference
Amartya Banerjee, Harlin Lee and Caroline Moosmüller
Population dynamics are often observed only as unpaired snapshots, which leave the
evolution between measurements underdetermined. Second-order regularization can constrain it, but a penalty on the accelerations of sampled particles is a prior on joint particle paths, and different particle representations of the same marginal curve can have different acceleration costs. We therefore introduce Neural Wasserstein Splines (NWSP), a sample-based method that learns a continuous population curve under a Wasserstein smoothness prior. A neural network maps latent variables to the control points of a cubic spline in time, so samples at any time come from the spline basis without numerical integration. We project the generator's velocity onto gradients of a finite dictionary of scalar potentials and differentiate this measure-dependent projection in time, obtaining a finite-dimensional surrogate for the intrinsic Wasserstein acceleration, trained jointly with distributional fit losses. For a fixed dictionary and ridge parameter, we prove that the population penalty depends only on the marginal curve and bound its sensitivity to moment-estimation errors. Learned potentials (NWSP-N) sharpen acceleration estimates. On various synthetic and single-
cell benchmarks, NWSP is highly competitive with transport and flow-based methods, ranking in the top two in 11 of 16 settings. The penalty improves on an unregularized spline in 13 of 16 settings and, while competitive with a particle-acceleration penalty, adds provable representation invariance.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning
Mingyeong Kim, Gyusang Cho, Juho Lee et al. (+1 more)
Sampling multiple chain-of-thought rationales from a
language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, making repeated autoregressive generation costly. Continuous latent
reasoning offers a compact alternative, but point-valued methods condition repeated answer sampling on a single rationale, which can limit exploration of diverse paths and answer coverage. We thus propose rationale distribution
distillation (RDD), training a conditional flow over fixed-length latent sequences by distilling from multiple textual
reasoning paths. Furthermore, we expand the
distillation targets through within-query mixup, interpolating between complete latent rationales for the same query. The flow nonautoregressively generates the entire latent sequence, and a frozen
language model autoregressively decodes answers from sampled rationale contexts. Empirically, the resulting distributional reasoner achieves higher answer coverage than the evaluated point-valued latent
reasoning baselines, particularly on advanced mathematical tasks.
Read the full abstract ▾
All authors Mingyeong Kim, Gyusang Cho, Juho Lee, Giung Nam
Artificial Intelligence
Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards
Tianyu Liu, Davide Belli, Bence Major et al. (+2 more)
Training LLM
agents on long-horizon interactive tasks with reinforcement learning typically relies on human-annotated tasks and reliable verification, both expensive to construct for stateful environments. Self-play offers an alternative, but must generate achievable, compositional tasks and provide feedback beyond binary outcomes. We propose Explorer-Zero, a self-play framework that jointly generates tasks and fine-grained, verifiable rewards through environment interaction. A learned proposer explores the environment, constructs tasks, and records intermediate and final states as verification targets. These checkpoints reward partial completion, while alternating proposer–solver training adapts the generated curriculum. We show theoretically that subtask rewards reduce collapse among unsuccessful rollouts when they complete different numbers of subtasks. Without human-annotated training tasks, Explorer-Zero outperforms the evaluated self-play baselines across ALFWorld, ScienceWorld, and AppWorld; on AppWorld, our 30B
agent reaches 59.67% task success, approaching 62.65% for RL on human-annotated tasks. Further analyses support task-relevant composition and benefits on complex tasks, while self-play initialization improves subsequent human-data RL across all three
benchmarks.
Read the full abstract ▾
All authors Tianyu Liu, Davide Belli, Bence Major, Arash Behboodi, Tribhuvanesh Orekondy
Artificial Intelligence
Euler: Towards Human-Centered Multi-Agent Mathematical Discovery
Qiuyu Chen, Qi Wang, Liang Xu et al. (+3 more)
Mathematical research drives scientific discovery, and recent advances in AI for mathematics have shown that
language-model
agents can solve challenging problems and develop substantial mathematical proofs. Yet much of today's AI-for-mathematics work centers on obtaining a final answer. This emphasis leaves the exploration behind a result difficult for researchers to understand, while long-running investigations face fragmented context and the risk of unsupported claims propagating across
reasoning steps. We present Euler, a human-centered mathematical research system built around a shared, structured representation of the research process. Euler organizes mathematical statements, assumptions, proof dependencies, alternative approaches, failed attempts, and verification evidence into connected research graphs. This representation allows researchers to trace how results are developed and supplies
agents with persistent, task-relevant knowledge for planning, collaboration, and verification across sessions. Researchers can also select a graph node linked to a saved team state, revisit the
agents' earlier
reasoning, and explore alternative directions through continued interaction. We illustrate Euler's capabilities through three mathematical research case studies and describe the implemented system and its software validation.
Read the full abstract ▾
All authors Qiuyu Chen, Qi Wang, Liang Xu, Xin Jin, Baao Xie, Wenjun Zeng
Artificial Intelligence · Cross-listed from cs.CR
Lost in the Fallback: How Reliably Do Typed Decision Models Use Fallback Options?
Yuanbo Xie, Mingli Zhu, Tianyun Liu et al. (+3 more)
Typed decision models (TDMs) are increasingly used in applications such as request routing and model selection, making reliable decisions critical to system performance. Fallback options accommodate categories outside regular choices, enabling deferral to human experts or more capable models. While recent works have examined
adversarial vulnerabilities in TDMs, their ability to follow fallback rules in non-
adversarial settings remains underexplored. We introduce the Paired Fallback Robustness (PFR) Test to evaluate two aspects of fallback reliability: whether models correctly switch between regular and fallback options, and whether they make consistent decisions under logically equivalent definitions of the same rule. We evaluate open-source decision models on three
benchmarks, with controlled comparisons across architectures and parameter counts. We find that correct recognition does not reliably transfer to correct fallback options, and errors persist even when the correct category is explicitly supplied.Moreover, logically equivalent formulations of the same fallback rule can also produce substantial disagreement in model decisions. These findings reveal a crucial reliability gap in current TDMs: fallback mechanisms designed to improve reliability can instead introduce errors. It highlights faithful execution of fallback rules and consistency under equivalent definitions as essential requirements for reliable typed decision-making.
Read the full abstract ▾
All authors Yuanbo Xie, Mingli Zhu, Tianyun Liu, Yingjie Zhang, Haixiao Xiong, Tingwen Liu
Artificial Intelligence · Cross-listed from cs.CV
DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
Boyuan Sun, Deshui Miao, Wenzhao Gao et al. (+8 more)
We propose DeltaStreamer, a novel agentic framework for streaming
video understanding inspired by how humans observe, remember, and investigate. Streaming
video understanding requires a system to retain evidence before knowing which details future queries will need. Existing approaches often obscure event transitions and omit relevant details when compressing
video history, and cannot recover missing visual evidence. DeltaStreamer addresses these limitations by combining change-aware
memory with query-driven planning and targeted evidence gathering with replay. Before a query arrives, it continuously observes the stream and explicitly records visual changes in structured
memory, preserving how events unfold rather than only what is present. When a query arrives, a query-driven planner identifies the required evidence and guides
memory retrieval and targeted replay. By revisiting historical frames, the
agent can recover visual details omitted during observation and ground its answer in evidence beyond the retained descriptions. This connects continuous observation with active investigation tailored to each question. Experiments on OVO-Bench and StreamingBench demonstrate improvements over representative streaming
video understanding methods, with overall scores of 66.07% and 59.53%, respectively. Project page: https://bbbbchan.github.io/DeltaStreamer/
Read the full abstract ▾
All authors Boyuan Sun, Deshui Miao, Wenzhao Gao, Shaoyong Jia, Shaohui Jiao, Chi Liu, Yan Shu, Derek Li, Bryan Dai, Shengsheng Qian, Qibin Hou
Artificial Intelligence · Cross-listed from cs.LG
Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon
Sifan Yang, Hongyi Tao, Dingzhi Yu et al. (+5 more)
Memory-efficient subspace optimization has emerged as a practical approach to reducing the
memory cost of LLM training while preserving optimization performance. Previous
algorithms typically rely on the leading singular subspace of
stochastic gradients, yet the gradient noise may dominate the subspace in later training stages and can prevent convergence. To overcome this limitation, we adopt a residual correction framework, which maintains the optimizer states in the subspace and adds the orthogonal residual gradient to the parameter update. We first integrate this scheme into momentum SGD to develop SMRC, which attains an $O(T^{-1/4})$ convergence rate for a fixed orthonormal basis, matching that of full-space momentum SGD. Our analysis introduces a subspace virtual iterate to resolve the coupling between the momentum and the residual correction. Furthermore, we extend SMRC to a multi-stage variant which periodically recomputes bases to track the evolving dominant subspace and retains the same rate. Since each basis refresh breaks the consistency of the virtual iterates, we devise a boundary correction approach that aligns them across stages. Beyond momentum SGD, we incorporate our framework into
Muon and propose PMRC, which applies the
matrix sign to the projected momentum. Through a weighted momentum tracking analysis that accounts for the residual gradient, we establish an $O(T^{-1/4})$ convergence rate for PMRC, which matches the rate of full-space
Muon. We also design a multi-stage PMRC with periodically refreshed bases, which maintains a convergence rate of the same order. Extensive experimental results confirm the effectiveness and efficiency of our
algorithms.
Read the full abstract ▾
All authors Sifan Yang, Hongyi Tao, Dingzhi Yu, Haomin Bai, Wei Jiang, Silin Gao, Pi Bu, Lijun Zhang
Artificial Intelligence
LAGO: Language Agents with Reusable Growing Options
Yuran Wu, Mengkang Hu, Qionglin Qiu et al. (+5 more)
Long-horizon tasks expose a weakness of monolithic tool-use loops: one
agent must decompose, execute, and verify a task within a single trajectory. We introduce LAGO, which treats specialized
language agents as reusable temporally extended options. A meta-
agent retrieves options from a persistent library or spawns new ones, dispatches sub-tasks, verifies results, and admits successful novel options. The library grows across tasks without updating model weights. On 500 SWE-bench Verified tasks, frozen Qwen3.5-35B-A3B in both roles resolves 58.6% under single-attempt evaluation with the official Docker evaluator. On a fixed 150-task subset, we re-run mini-SWE-
agent, Terminus 2, and LAGO with the same policy, temperature, task IDs, and evaluator; their resolve rates are 49.3%, 57.3%, and 60.3%, respectively. Cross-model experiments provide evidence consistent with a role for decomposition quality. A 50-task component ablation finds four fewer resolved tasks without decomposition, two fewer with shuffled reused content, and six fewer without the library. These results support reusable
agent-options as a practical abstraction for task streams, while leaving component-level causality task- and model-dependent.
Read the full abstract ▾
All authors Yuran Wu, Mengkang Hu, Qionglin Qiu, Fanqing Meng, Qiguang Chen, Yuhang Zhou, Qiudan Zhang, Xu Wang
Artificial Intelligence
Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents
Md Farhan Ishmam and Kenneth Marino
Frontier web
agents using closed models have high inference and computational costs. Smaller open models can be an alternative, but to be performant, they require training supervision from a human or teacher model.
Token-level teacher
distillation is not an option for closed teachers as it needs access to the model's logits. The standard approach is to imitate teacher demonstrations offline, but it trains the student on states it has never visited, and in a style it does not write in. We introduce WebKD, where the teacher is the editor of the student's failures. Given a failed episode, the teacher finds the first point of mistake, and rewrites the student's
reasoning traces, harness states, and actions from that point onward. The editing reveals that the teacher's corrections can be more surprising to the student than the student's own text. WebKD instead aims to edit minimally. In the data space, the teacher writes each correction in the student's style. In the objective space, the
reasoning is weighted by its contribution to the action. A role-asymmetric KL anchor allows the corrected action to move freely while keeping the
reasoning near the student's prior. On the TimeWarp
benchmark, WebKD students gain about 5.5-10.7 pp over behavior cloning, outcome-reward RL, and teacher editing baselines. The performance transfers to unseen versions and to the live web in the OnlineMind2Web
benchmark. WebKD opens a new way of distilling black-box models to improve the capabilities of open-weight web
agents.
Read the full abstract ▾
Artificial Intelligence
ActionOPD: Distilling Decisions, Not Tokens
Huining Yuan, Xiangmin Yi, Zelai Xu et al. (+5 more)
Distilling capable
language-model
agents into smaller models requires aligning the student's behavior with the teacher's. This raises a fundamental question: at which states and at what granularity should this
alignment be performed? Offline imitation provides dense but
token-specific supervision and can suffer from state-distribution mismatch.
Token-level on-policy
distillation (OPD) addresses this mismatch but typically requires teacher
token probabilities and compatible tokenization. We argue that semantic actions provide a natural unit of supervision for
agent distillation. We introduce ActionOPD, an action-level on-policy
distillation method motivated by maximizing expected teacher-action likelihood at student-encountered states. At each such state, ActionOPD samples actions from both the student and a black-box teacher, rewarding student actions according to their semantic agreement with the sampled teacher actions. Through policy optimization, ActionOPD aligns the student's action-level behavior with the teacher's decisions without requiring reproduction of teacher-written
reasoning or access to teacher
token probabilities. Training Qwen3-4B and Qwen3-8B with two teachers on diverse, curated tool-use tasks yields average gains of 3.3-6.9 percentage points across four out-of-distribution
benchmarks. ActionOPD scales favorably with student size and teacher capability, without requiring the teacher and student to share a model family or tokenizer. On $\tau^2$-bench, ActionOPD achieves competitive performance against offline
distillation and
token-level OPD. We further explore Self-ActionOPD with a same-model teacher and privileged context. These results establish ActionOPD as a promising approach to
agent distillation.
Read the full abstract ▾
All authors Huining Yuan, Xiangmin Yi, Zelai Xu, Zixu Wang, Xinlei Chen, Xiao-Ping Zhang, Yu Wang, Chao Yu
Artificial Intelligence
One Monitor Does Not Fit All: Formalism-Agnostic Runtime Verification for Agentic AI
Angelo Ferrando
Agentic AI systems combine model decisions, mutable state, tool calls, and delegation to external
agents. Monitoring them requires observations from different execution boundaries, while prevention requires control before an operation produces its effect. We present AgenticRV, a runtime-verification architecture that separates these boundaries from the monitoring formalism. Adapters emit canonical events; each monitor receives its own projection and abstraction; and a decision policy uses normalised verdicts to select a reaction supported by the responsible adapter. We formalise when observations suffice, monitor replacement preserves decisions, and blocking prevents unsafe effects. We also distinguish rejected attempts from completed effects, avoiding the assumption that a blocked request must leave every monitor in a permanent violation state. The Python implementation supports LangGraph, MCP, and A2A. A controlled LangGraph experiment combines an external Reelay temporal monitor with a programmatic report monitor; ablations show why both are needed for the selected requirements. Differential checks and cross-adapter tests provide further integration evidence. An LLM-driven incident-response example illustrates the same enforcement path, while existing microbenchmarks isolate framework costs. The results support reuse of monitoring methods at explicit control boundaries, subject to the stated observation and deployment assumptions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting
Shengnan Guo, Jinjun Cheng, Xiaowei Mao et al. (+7 more)
Spatio-temporal forecasting is fundamental to many real-world systems, yet deployment environments are inherently varying: temporal distributions may evolve, spatial domains may change, and observation availability may shift from training conditions. Existing models are often tightly coupled to their training environments through node-specific representations, predefined spatial support sets, and reliance on consistently available observations, limiting generalization to changing environments. To this end, we propose VaryST, a compact spatio-temporal forecasting model trained from scratch that achieves strong generalization by dynamically constructing predictive context from available long-term observations. To accommodate temporal changes, VaryST derives node representations from long-term histories, capturing current behavior in the context of longer-term patterns. To adapt to spatial changes, it dynamically selects functionally relevant support nodes beyond predefined neighborhoods and integrates their information with recent and long-term target states and global context. To handle varying observation availability, VaryST selectively masks historical patches on which the model relies most during training, encouraging it to exploit alternative temporal and spatial dependencies for accurate forecasting when key observations become unavailable. Extensive experiments on six real-world
datasets against seventeen baselines show that VaryST achieves strong in-domain forecasting accuracy, substantially improves zero- and few-shot generalization under spatial and temporal changes, and remains robust to varying observation availability.
Read the full abstract ▾
All authors Shengnan Guo, Jinjun Cheng, Xiaowei Mao, Jianhao Zhang, Haochen Lv, Yang Jiang, YiHeng Huang, Yan Lin, Youfang Lin, Huaiyu Wan
Artificial Intelligence
ReproBAIT: Can coding agents build their own biological AI tools?
Shiv Muthupandiyan, Tolga H. Dur, Mac Walker et al. (+8 more)
Large
language models are increasingly competent at leveraging scientific knowledge and existing computational tools to execute complex workflows. At present, little information exists on their ability to reconstruct tools when given limited descriptions of such tools. We introduce an evaluation titled ReproBAIT (Reproducing Biological AI Tools), which measures the ability of coding
agents to design, implement, and train biological AI tools taken from published research across a range of information access conditions. The coding
agent is securely sandboxed without internet access and receives training data, a fixed time and compute budget, and limited information about the tool to replicate. We then score the reproduced biological AI tool based on its performance (tool-specific metrics) on held-out data. We evaluated a set of biological AI tools of varying complexities: ProteinMPNN, an inverse
protein folding tool, RFdiffusion3, an all-atom generative
diffusion tool, and a closed-source molecular design tool. We institute a methodology to check for memorisation, as the open source tools are likely to be included in models' pretraining corpus. Across a range of leading closed- and open-source coding
agents, we find substantial reproduction capability for some selected tools, though limited capability for a highly complex tool. We find moderate evidence consistent with memorisation, varying across coding
agents. These results suggest that tool developers need to be increasingly cautious when releasing information about the tools publicly; re-creation of the tool based on such information could undermine a tool's commercial value or invalidate dual-use managed access strategies.
Read the full abstract ▾
All authors Shiv Muthupandiyan, Tolga H. Dur, Mac Walker, Timo Flesch, Mahmoud Ghanem, Steph Suddell, Giles Harper-Donnelly, Sophie Rose, Jasper Götting, Coleman Breen, Jake Pencharz
Artificial Intelligence
Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning
Soyoung Oh, Nursulu Sagimbayeva, Nicholas Jennings et al. (+3 more)
In Theory-of-Mind (ToM)
reasoning, large
language models may correctly infer the
agent's mental state but fail to use that inference when predicting or judging the
agent's subsequent actions. In this work, we investigate whether explicitly connecting perception, belief, and action with rules improves ToM
reasoning. We generate concise if–then rules that express relations between perception to action and use Group Relative Policy Optimization (GRPO) to train Qwen2.5 and Llama3 models across four ToM
benchmarks. GRPO with rule generation outperforms prompting, supervised fine-tuning, and think
reasoning. Moreover, rules generated by larger models ($\geq$3B) provide transferable knowledge that improves downstream performance of GPT-4o-mini. These findings suggest that explicit rules help models bridge the
reasoning gap in ToM and support knowledge transfer across models.
Read the full abstract ▾
All authors Soyoung Oh, Nursulu Sagimbayeva, Nicholas Jennings, Paulina Hussein, Mehwish Alam, Vera Demberg
Artificial Intelligence · Cross-listed from cs.CV
StateCraft: Augmenting Video World Models with Abstract-State Reasoning
Lorenzo Venturoli, Nedko Savov, Xi Wang et al. (+2 more)
Video world models aim to simulate complex environments with realistic appearance and dynamics. Maintaining consistency over long interactions requires tracking past actions and understanding how those actions affect the environment.
Video world models can only generate partial observations of the entire world at a time. Remembering past observations alone may not be sufficient in every scenario, as they may no longer reflect the world after a sequence of actions. We introduce a paradigm that decouples a persistent, updatable abstract state from the visual state. The abstract state keeps track of the entities' changes as the world evolves, and is used to condition the visual state, which represents the current view. We propose StateCraft, a novel architecture that pairs a
language model with a
video diffusion model to evolve the dynamic world. We evaluate our approach on generative interfaces, which pose a substantial challenge because a single action may change parts of the state that are not currently visible. To support training and evaluation, we develop a data collection pipeline that produces informative, densely annotated trajectories at scale without human or
agent supervision, together with a
benchmark measuring generation quality,
memory, and controllability. On this
benchmark, our approach improves surpasses the state-of-the-art baselines. We demonstrate that StateCraft maintains high self-consistency and strong generation quality over long trajectories. Because the abstract state is explicit, it can be edited directly, and generation follows edits to states never observed in the data. Finally, a proof-of-concept 3D experiment, in which actions change the illumination of an unobserved room, shows that the paradigm can also be applied to spatial environments. Project page: https://insait-institute.github.io/StateCraft/.
Read the full abstract ▾
All authors Lorenzo Venturoli, Nedko Savov, Xi Wang, Marc Pollefeys, Luc Van Gool
Artificial Intelligence · Cross-listed from cs.MA
One Agent per Zone: Decentralised Active Inference under Partial Observability for Multi-Zone HVAC Control on Edge Hardware
Panagiotis Kasnesis, Lazaros Toumanidis, Christos Chatzigeorgiou et al. (+2 more)
Multi-zone HVAC control is a shared-resource problem: zones on a floor share one fan and cooling coil, so each zone's demand affects its neighbours and the building's peak power. One controller per zone scales well and isolates faults, but each controller then observes only its own zone, not the shared air loop. In this work, we present a decentralised controller that assigns each zone an independent active-inference
agent, which plans by minimising expected free energy and learns its zone dynamics online. The
agents exchange no messages, so none depends on peers or a coordinator; each accounts for the unobserved coupling through a latent disturbance and a congestion signal derived from the metered power of the other floors. Fifteen
agents are evaluated in EnergyPlus on a Sinergym office building against three rule-based controllers and three MADDPG fleets, one given the same floor meters. On five noisy weather years unseen during training, the fleet attains the lowest mean building peak (88.3 kW, 3 to 17 % below the baselines) and staggers the floor peaks better than any baseline, with a coincidence factor (building peak over the sum of the floor peaks) of 0.929 versus 0.936 to 0.994. Compared with a reactive rule at similar comfort (0.912 versus 0.916), it lowers the sum of monthly peaks, on which demand charges are billed, by 33 kW (4 %) in every year, at the cost of about 10 % more energy. It costs 9% less per year than the proactive rule (at lower comfort) and 1% less than the MADDPG fleet given the same floor meters, in every test year. The whole fleet runs on a single low-cost Raspberry Pi 5, closing the observation-to-action loop over MQTT in 442 ms at p95, far below the 15-minute control step.
Read the full abstract ▾
All authors Panagiotis Kasnesis, Lazaros Toumanidis, Christos Chatzigeorgiou, Amalia Contiero Syropoulou, Miguel De Prado
Artificial Intelligence · Cross-listed from cs.CV
LiFi: LiDAR Generation from Multi-View Images via Geometric and Semantic Collaborative Guidance
Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang et al. (+10 more)
Generating
LiDAR point clouds from multi-view camera images is a valuable task with applications in controllable data synthesis, cross-modal simulation and various perception tasks. However, most existing methods are not specifically designed for this task, and the quality of their generated
LiDAR remains limited. Moreover, these methods typically focus only on semantic cues in images or generate
LiDAR from a monocular camera image. In this work, we introduce LiFi (
LiDAR From images), a dedicated framework for generating visually and geometrically aligned
LiDAR scenes from multi-view camera images. LiFi guides the latent
diffusion process through two complementary branches: geometry and semantics. The geometry branch constructs scene features from images through a reverse sampling
algorithm and an uncertainty-aware
geometric encoder combined with DepthAnything3, whereas the semantic branch provides high-level semantic representations via a cross-view interaction module. We further introduce a dual-branch balanced classifier-free guidance (CFG) strategy, which enhances the model's conditional generation capability while preserving the independent learning and collaborative controllability of the two branches. Extensive experiments demonstrate that LiFi outperforms state-of-the-art methods in generating high-fidelity
LiDAR scenes. The code will be publicly available at: https://github.com/szzhou88/LiFi.
Read the full abstract ▾
All authors Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang, Qifeng Li, Junjie Li, Zirui Wang, Yukang Feng, Yu Hong, Shaofeng Zhang, Wenlong Liao, Tao He, Juyong Zhang, Junchi Yan
Artificial Intelligence
LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making
Jingyuan Li, Yujie Liu, Yijie Dai et al. (+18 more)
Laboratory experiments involve more than following predefined protocols; they require adaptive decision-making as the experimental state changes. Existing scientific
benchmarks rarely assess such evidence-based decisions in laboratory settings. Here we present LabOPBench, a
multimodal benchmark of 756 expert-authored, independently reviewed questions in organic synthesis and materials science. Each item pairs laboratory evidence with procedural context and an open-ended judgment, evaluated using a question-specific scoring rubric. Eight
multimodal models obtain overall normalized scores of 28.8-45.8%, leaving substantial room for improvement. On a controlled 100-question subset, the strongest models outperform undergraduate participants on average but remain below the average performance of PhD participants. Expert analysis of responses from the three leading models identifies Evidence Misreading and Evidence-Decision Conflict as the dominant error patterns. These results reveal that current models still struggle to turn
multimodal perception into reliable laboratory decision-making.
Read the full abstract ▾
All authors Jingyuan Li, Yujie Liu, Yijie Dai, Xiaoyu Yuan, Nian Ran, Huajie Niu, Ming Zhu, Shuwen Zhao, Chenxi Li, Fenghao Lu, Jiahao Li, Xinyu Gu, Zhe Liu, Long Xu, Wenlong Zhang, Bo Zhang, Lei Bai, Peiyu Zhang, Minting Pan, Weinan Zhang, Dongzhan Zhou
Artificial Intelligence · Cross-listed from cs.CL
PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making
Ziyang Ling, Shuyu Lu and Ziyi Chen
Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decision-making across medical specialties, a critical coordination failure that leads to adverse drug events and rehospitalizations. To address this coordination challenge, we introduce PRISMATIC, a multi-
agent architecture where specialized
agents, each representing a workflow role, collaboratively generate and refine treatment plans. Operating on a blackboard architecture, the system first structures patient information from clinical notes, then iteratively develops safe, rational, and interpretable drug regimens. The
agents' collaboration is governed by two novel adaptive coordination mechanisms: (1) Dynamic Self-Updating Weight Adjustment (DSWA), a long-term mechanism that adjusts the influence weights of
agents based on historical case outcomes, enabling the system to adapt and trust more reliable specialists over time. (2) Discrepancy Feedback Precise Calibration (DFPC), a short-term mechanism where
agents provide iterative feedback to resolve disagreements and eliminate prescription conflicts for the current patient. Experiments on patient records from the MIMIC-IV database show that PRISMATIC significantly reduces drug conflicts, improves prescription coverage, and enhances treatment consistency compared to strong LLM baselines. Our work demonstrates that structuring clinical co-treatment as a multi-
agent coordination problem offers a promising path toward safer and more coherent multidisease management.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs
Minghan Li and Guodong Zhou
Visible
reasoning traces of Chinese
reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets. We ask whether the linguistic register of
reasoning can be used to improve efficiency. We propose Wenyan Thinking, which emits intermediate
reasoning in Classical Chinese (wenyanwen) while retaining a short direct-answer output. Starting from modern-Chinese
reasoning traces, we rewrite only the
reasoning field into wenyan and fine-tune Qwen3-4B-Thinking-2507 on the rewritten supervision. To distinguish register shift from generic compression, we construct a compact modern-Chinese control using the same source data, teacher family, base model, and SFT recipe. Across budget-sensitive evaluations on MMLU-ProX-Lite-ZH, CEVAL, and AGIEval-CN, Wenyan Thinking substantially reduces
reasoning length and missing-answer rates under constrained decoding. Compact rewriting explains much of the efficiency gain, while wenyan consistently outperforms the compact modern-Chinese control on the primary
benchmark and remains competitive across the additional
benchmarks. These results identify linguistic register as a practical design axis for efficient visible
reasoning in Chinese LLMs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
ProtModernBERT: Compute-Efficient Protein Language Modeling
Alberto Martínez, Natalia Flechas Manrique, Llorenç Espinosa-Portalés et al. (+1 more)
Large
protein language models provide a powerful framework for learning sequence-function relationships and guiding experimental design. However, architectural improvements are underexplored, especially in low-compute regimes of relevance for resource-constrained research laboratories. We show that the training cost for encoder-only
transformer architectures can be reduced by leveraging modern architectural refinements, offering an encouraging performance / compute-efficiency trade-off. We introduce ProtModernBERT, a modernized BERT-style model pre-trained on amino acid sequences, and compare it with ProtBert, Amplify, and ESM2 across a set of supervised structural tasks -encompassing secondary structure prediction, disorder prediction, and subcellular localization- and ProteinGym's zero-shot functional
benchmark. We find that ProtModernBERT matches or closely tracks the performance of Amplify-120M and ProtBert with up to 80-90% reduction in pre-training FLOPs, and narrows the gap to ESM2 when controlling for pre-training. Our analysis using a cluster-based validation protocol for hyperparameter selection and randomly initialized models disentangles the contributions of architecture and data, showing that modern components provide stronger inductive biases that are more consequential than parameter count in low-compute regimes.
Read the full abstract ▾
All authors Alberto Martínez, Natalia Flechas Manrique, Llorenç Espinosa-Portalés, Luc Andrea