Artificial Intelligence · Cross-listed from cs.NI
DSWM: Decomposed Spatio-Temporal World Model for Demand-Driven UAV Base Station Repositioning
Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen et al. (+4 more)
Uncrewed aerial vehicle base stations (
UAV-BSs) are expected to cover traffic demand that shifts across space and time, yet most repositioning schemes either re-solve an optimization problem per slot or learn reactive policies without an explicit demand model. We cast demand-driven fleet repositioning as latent-space decision-time planning and propose DSWM, a decomposed spatio-temporal world model: an agentic controller that perceives the demand field through a rolling observation window, retains operational context in a latent recurrent state, reasons about candidate motions by imagined rollouts under an uncertainty penalty, and coordinates the fleet through replanned first actions. DSWM learns a recurrent state-space model shaped by an exponential-moving-average (EMA) based latent predictive objective with variance regularization. It attaches a differentiable service simulator that replays the association, probabilistic line-of-sight channel, and Shannon rate chain inside latent rollouts. Planning uses a cross-
entropy method whose imagined demand is anchored on the current observation window with mixing coefficient $\rho=0.95$. On a unified pipeline over three real
datasets (Milan CDR (call detail record), Shanghai Telecom, YJMob100K) and 14 methods including five reproduced IEEE baselines, DSWM attains weekday served ratios of 0.889, 0.908, and 0.898, ranking first among non-ablated configurations on every
dataset. On Milan it improves over the strongest non-learning baseline (Greedy, 0.780) by 0.109, a margin that comes from decision-time use of observations rather than prediction accuracy.
Read the full abstract ▾
All authors Shengjie Zhong, Zhongliang Zhao, Jingxuan Chen, Xianbin Cao, Xinmei Qiang, Dapeng O. Wu, Tony Q. S. Quek
Artificial Intelligence · Cross-listed from cs.CV
On-Policy Visual Evidence Distillation
Shaohang Wei, Feifan Song, Guangyue Peng et al. (+9 more)
Visual
agents solve problems by interleaving
reasoning with image operations, and on-policy
distillation (OPD) provides guidance from a strong teacher on student-generated interaction trajectories. However, image operations change the evidence available for subsequent
reasoning, so local errors in evidence acquisition (Acquire), reading (Read), or answer grounding (Ground) can propagate through the trajectory and lead to incorrect answers. Existing
multimodal OPD methods primarily construct or contrast auxiliary views of the original image to strengthen supervision, without explicitly modeling the connections between student actions, resulting observations, and subsequent
reasoning. This limits their ability to provide corrections tailored to different failure stages. We introduce Reflection on Visual Evidence (ReVuE), an on-policy
distillation method for visual
agents. ReVuE compares multiple student-generated trajectories for the same query, summarizes the observed visual evidence, and diagnoses the first failure across the Acquire, Read, and Ground stages. The resulting reflections provide training-time context for the teacher. We group and reweight
token-level
distillation losses according to how strongly these reflections affect the teacher's predictions. This design translates trajectory-level evidence diagnosis into targeted
token-level supervision, guiding students to improve their visual evidence acquisition and
reasoning. Across 11
benchmarks spanning the Qwen2.5-VL and InternVL3.5 model families, ReVuE outperforms all evaluated OPD baselines in weighted-average scores for perception, mathematical
reasoning, and general tasks. ReVuE also reduces redundancy in
reasoning and tool calls while improving tool-call accuracy and task accuracy. Code is available at https://github.com/sylvain-wei/ReVuE
Read the full abstract ▾
All authors Shaohang Wei, Feifan Song, Guangyue Peng, Wenhao Yu, Wei Li, Wen Luo, Yang Xu, Yufan Shen, Luke Mao, Yang Du, Asher Qin, Houfeng Wang
Artificial Intelligence
ARC-KV: Amortizing Anchor Search for Reconstruction-Based KV Cache Compaction
Zheyu Shen, Guanhua Wang, Dezhan Tu et al. (+5 more)
Long-context large
language model inference is bottlenecked by KV caches that grow linearly with sequence length. This burden is especially severe for long, reusable context prefixes, whose cache must serve many downstream queries. Reconstruction-based methods such as
Attention Matching achieve strong downstream task performance with compact KV caches. However, iterative anchor search dominates the compaction cost of OMP-based
Attention Matching. This motivates our selective amortization principle of learning a reusable anchor-selection policy across contexts while retaining context-specific reconstruction. In this work, we propose ARC-KV, a novel reconstruction-based KV cache compaction method that follows this principle. To this end, we first train a value-aware indexer to select real-key anchors in a single scoring pass. ARC-KV then applies convex-hull-constrained key merging and fits an
attention-mass bias and compact values against the full cache. At inference time, ARC-KV builds the compact cache once per context using the frozen indexer and reuses it for all subsequent queries. Extensive experiments demonstrate that ARC-KV outperforms reported compaction methods in most settings across QuALITY, RULER, and LongBench on Llama-3.1-8B-Instruct. In particular, at 10% KV retention on QuALITY, ARC-KV improves accuracy from 0.6409 to 0.6474 over
Attention Matching while reducing compaction time by a factor of 25.73, from 959.8 s to 37.3 s.
Read the full abstract ▾
All authors Zheyu Shen, Guanhua Wang, Dezhan Tu, Mengchi Zhang, Yanjia Li, Adnan Aziz, Chunqiang Tang, Ang Li
Artificial Intelligence
Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training
Chenliang Li, Neiwen Ling, Zijun Wei et al. (+1 more)
Fully asynchronous reinforcement learning (RL) improves resource utilization in large
language model post-training by overlapping rollout generation with policy optimization, but it also introduces policy lag as trajectories are generated and queued while the trainer continues to update. We study how this lag accumulates over a trajectory's lifetime and how it can be controlled without sacrificing the wall-clock benefits of asynchronous execution. We decompose trajectory staleness into Generation Staleness, accumulated before rollout completion, and Waiting Staleness, accumulated after a completed trajectory enters the pool. Motivated by this decomposition, we introduce PACE (Pool-Aware Control of Effective Staleness). PACE converts excess pool occupancy into an adaptive rejection budget and ranks completed trajectories using an effective-staleness score that combines Waiting Staleness with prefix-aware Generation Staleness. This avoids penalizing long or interrupted rollouts solely because they span multiple policy versions. In single-turn mathematical
reasoning, PACE improves the six-
benchmark average validation accuracy by 18.7% over unfiltered asynchronous RL at the same wall-clock budget and matches synchronous RL performance with 47.1% less GPU time. PACE also improves validation performance in multi-turn tool-integrated
reasoning, outperforming both synchronous and unfiltered asynchronous RL. Further experiments with the mixture-of-experts model and an alternative RL
algorithm support its applicability across model architectures and training
algorithms.
Read the full abstract ▾
All authors Chenliang Li, Neiwen Ling, Zijun Wei, Alfredo Garcia
Artificial Intelligence
The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents
Xueqi Li, Jingjie Ning and Yibo Kong
An executor can respond strongly to a change in a supplied plan's priority while showing a small change in the same information-selection probability when a default-aligned whole plan is removed. We call the risk of interpreting the latter as weak responsiveness to alternative priorities the default trap. We compare paired plans that prioritize different information targets with a shared no-plan reference. An accounting identity relates these distinct behavioral contrasts. Across 3,200 decision windows on 160 selected Retail, Airline, and AgentDojo tasks, switching priorities strongly redirects two models' choices, while the two plan-versus-default contrasts differ. In 2,160 additional windows, reversing account-list order shifts default target selection by 63.3-98.3 percentage points; priority-switching effects remain 96.7-100.0 points in either order. A separate 3,240-window component study finds strong control under single priority sentences, with effects of additional text varying by group and direction. Finally, 1,080 full-task episodes yield observed success differences of -19.4 to +8.3 points relative to no plan. All Retail and Airline success intervals include zero; AgentDojo results describe four fixed application worlds. These findings support joint reporting of priority responsiveness, presentation-dependent defaults, and task success and cost.
Read the full abstract ▾
Artificial Intelligence
Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models
Wenxiao Fan, Jingling Fu, Lichen Ma et al. (+6 more)
Post-training quantization (PTQ) lowers deployment cost for
multimodal large
language models, but calibration typically reconstructs fixed sequences with local objectives. This overlooks autoregressive feedback: a quantization-induced
token change redirects the prefix and changes future states. Yet on-policy coverage alone is insufficient because many decision mismatches barely affect future generation. We propose OnPTQ, an on-policy framework that calibrates on trajectories visited by the current quantized policy. On shared prefixes, OnPTQ identifies quantization-eroded boundaries, evaluates competing
tokens through short counterfactual rollouts, and combines current discrepancy with branch consequence into a Decision–Consequence risk. The risk prioritizes critical states, while context anchoring and trajectory refresh preserve
multimodal behavior and keep calibration aligned with the updated policy. We further derive a Decision–Consequence bound linking behavioral deviation to current policy discrepancy and action-conditioned future-value span. Across
vision–
language and omni-modal Qwen models under multiple low-bit settings, OnPTQ improves downstream performance and yields fewer correctness flips against the corresponding Dense/FP16 references, without changing the deployed inference graph.
Read the full abstract ▾
All authors Wenxiao Fan, Jingling Fu, Lichen Ma, Yu He, Luohang Liu, Jinbao Xue, Ke Zhang, Junshi Huang, Kan Li
Artificial Intelligence · Cross-listed from cs.LG
Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows
Junhyun Ha, Juho Lee and Byoungwoo Park
Diffusion and flow policies can model complex behaviors in offline reinforcement learning (RL). However, penalizing their KL divergence from the behavior policy can discourage actions having high critic values with low behavior density. Directly refining behavior proposals may be an alternative, yet Gaussian or deterministic editors limit expressiveness to represent multiple separated modes for the same proposal. In this work, we introduce Proposal-Conditioned Refinement Flows (PReFlow), a policy extraction method combining critic-based proposal selection with a conditional refinement flow. To optimize proposal selection and refinement together, we formulate a KL-regularized objective whose optimum induces a Gibbs policy over final actions under a Gaussian-smoothed behavior prior. The refinement flow can represent multiple high value modes, while a proposal-centered Gaussian reference regulates large action changes. This Gaussian reference further enables us to make use of simulation-free, closed form adjoint matching targets from sampled endpoints and critic gradients, yielding a single velocity regression loss without a backward adjoint solve. On 50 OGBench tasks, PReFlow achieves competitive offline performance and the highest aggregate score among the compared methods after online fine-tuning, reaching 91% after 500K environment steps.
Read the full abstract ▾
Artificial Intelligence
Geometry-Conditioned Fixed-Scaffold Encoders for Time-Warp Robust Sequence Retrieval
Cassandra Yang and Yufan Tang
Embedding-based
retrieval is attractive for long sequence collections because each item can be encoded once and searched by nearest-neighbor ranking. The difficulty is that the objects being indexed are often observed under a noncanonical clock: cardiac cycles stretch with rate,
speech changes with tempo, and sensor traces reach comparable states at different speeds. This paper studies a specific source of instability in patch-based encoders for this regime. If patch boundaries are chosen from signal geometry, then the tokenization can change under the same temporal deformation that the representation is expected to tolerate. We propose GeoPatch, a fixed-scaffold patch encoder that keeps
token support independent of geometry and uses slope,
curvature, acceleration, affine-residual, and confidence descriptors only as continuous conditioning variables. The design turns boundary variation into feature modulation: geometry can change the
embedding through a controlled pathway, but it cannot change the number, order, or support of local
tokens. We formalize this distinction through a mechanism-level stability analysis that separates boundary drift, affine timing variation, confidence-weighted geometry perturbation, and
retrieval-margin effects. The same local
tokens support global
embedding retrieval and late-interaction scoring, so the scoring rule can be matched to the evaluation protocol. Across ECG,
speech, and multivariate time-series
retrieval tasks, GeoPatch improves early-rank
retrieval under timing variation while exposing a clear trade-off between local surface matching and strict non-overlap
retrieval.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Spotter: Let the Embodied Model Lead, and the VLM Reflect for It
Long Li, Qichao Zhao, Yue Yang et al. (+6 more)
Current
embodied models do not respond to their own failures, although what just went wrong could inform a small adjustment on the next attempt, the kind of reflection behind the gains of thinking in
language models. We test whether they can repair a known error, which requires producing a correction and judging whether it is right. Stopped at a failure and allowed to retry, they seldom repair it through their own randomness or from a
language description of the error, and best-of-N selection cannot pick the successful candidate after a failure. We attribute this to training only on successful demonstrations and to inputs too narrow to show what went wrong, and conclude that reflection must come from a
vision-
language model (VLM), which takes in far more information, such as the episode history and text, and is more general. Prior VLM-led work has the VLM plan every step and invoke the
embodied model as a tool, placing the VLM on the critical path. We propose Spotter, which reverses the roles: the
embodied model leads and executes continuously, while the VLM runs in parallel, monitors through a lightweight local screener, intervenes only when an error is detected, reflects on and corrects it, and returns control. We run Spotter with Qwen and with GPT as the VLM, and both improve the
embodied models; with GPT, Spotter improves Cosmos Policy and $\pi_{0.5}$ by 5.6 and 7.5 percentage points on RoboCasa, and raises $\pi_{0.5}$ from 47.2% to 57.0% on the Hard setting of RoboTwin 2.0 and from 53% to 83% on a real
robot. Because the VLM steps in only when an error is confirmed, a successful episode with Qwen takes only 13 to 16 s longer than with the
embodied model alone and about 70% less time than with a VLM-led baseline using the same model. Our code is available at https://github.com/zqc3117/Spotter.
Read the full abstract ▾
All authors Long Li, Qichao Zhao, Yue Yang, Fan Xu, Zhe Wang, Alan Wee-Chung Liew, Chao Qu, Heng Tao Shen, Shirui Pan
Artificial Intelligence
CANTO: CAD-Native Transformer Operators for AI-Aided Engineering
Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn et al. (+8 more)
Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models. Evaluating design changes through numerical simulation requires meshing the continuous geometry, a computationally expensive and often brittle process that can require manual intervention and replaces the continuous representation with a discrete approximation. Most neural surrogates accelerate the simulation, but inherit this representation gap by relying on meshes, point clouds, voxels, or other sampled approximations of geometry. We introduce CANTO, a
transformer neural operator that maps directly from continuous CAD geometry to physical fields, without meshing the input geometry. We develop a theoretical framework for learning operators from
geometric manifolds to function spaces of physical fields, representing geometry through sequences of parametric patches. CANTO instantiates this framework by directly tokenizing non-uniform rational B-spline (NURBS) patches from their control points,
knot vectors, and weights, and predicts continuous surface and volume fields at arbitrary query locations. We evaluate CANTO on four automotive and aircraft aerodynamics industry
benchmarks: AhmedML, WindsorML, DrivAerML, and HiLiftAeroML. CANTO achieves state-of-the-art accuracy on most evaluated surface and volume prediction tasks, including a 19.8% reduction in surface-pressure relative $L_2$ error compared with AB-UPT on HiLiftAeroML. Differentiability with respect to CAD parameters further enables gradient-based inverse design of designs. On AhmedML, CANTO identifies designs with 4.4 to 20.4% lower drag than the best
dataset designs satisfying the same volume and lift constraints, with the improvements verified using the same CFD setup used to generate the original
dataset.
Read the full abstract ▾
All authors Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn, Ruben Ohana, Ira J. S. Shokar, Abouzar Ghasemi, Semih Akkurt, Rishikesh Ranade, Neil Ashton, Jan Kautz, Jean Kossaifi
Artificial Intelligence
UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval
Mengkun Liang, Haoran Qiang, Guannan Liu et al. (+1 more)
Large
language model (LLM)
agents reuse external
memory to guide new tasks, but effective
retrieval requires learning which
memory sets improve execution. Such learning relies on costly outcome feedback: ordinary
retrieval observes only executed sets, while evaluating alternatives requires additional rollouts. We introduce UpliftMem, which learns
memory retrieval from set-level execution uplift relative to the same executor without
memory. A theoretical analysis of how
retrieval preferences restrict feedback coverage motivates targeted probing of alternative
memory sets. Probe selection follows an expected value of sample information (EVSI) criterion, derived in closed form under a correlated Gaussian model, to allocate limited training rollouts according to their expected improvement in local
retrieval decisions. The shared scorer is trained with a frozen executor and selects
memory sets without test-time probes. Across ALFWorld, WebShop, and BigCodeBench, UpliftMem achieves the best success rates among evaluated baselines on the main evaluation sets. Controlled fixed-store and matched probe budget evaluations further demonstrate improved
memory-use decisions and more effective use of execution feedback.
Read the full abstract ▾
All authors Mengkun Liang, Haoran Qiang, Guannan Liu, Junjie Wu
Artificial Intelligence · Cross-listed from cs.CL
VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction
Yitong Han, Nankai Lin, Juan Luo et al. (+3 more)
Chinese Semantic Error Correction (CSEC) targets semantic errors in Chinese text, which are typically more subtle and complex than spelling and grammatical errors but remain relatively underexplored. Existing LLM-based approaches face two recurring obstacles in this task: over-correction, and unclear interaction between Chain-of-Thought (CoT)
reasoning and self-consistency decoding, such that the benefits brought by CoT cannot be reliably transferred to final corrections. We propose Vote-guided Advantage Allocation for CSEC (VAA-CSEC), a multi-stage framework that combines CoT
distillation, Supervised Fine-Tuning (SFT), Reinforcement Learning (RL) and self-consistency decoding. During RL, we design a task-specific reward function that directly aligned with the minimal-editing principle of CSEC. We further introduce Group-Level Relative Policy Optimization (GLPO), which reallocates GRPO advantages according to the margin between individual rollout rewards and the vote-aggregated group reward, aligning the RL training objective with the self-consistency objective used at inference time. Experiments on CSED-C and NaSGEC-Exam show that VAA-CSEC outperforms all LLM-based baselines on CSED-C with an F0.5 of 47.72%, achieves the highest recall of 42.15% among all methods, and establishes a new state of the art of 41.55% F0.5 on NaSGEC-Exam.
Read the full abstract ▾
All authors Yitong Han, Nankai Lin, Juan Luo, Hongyan Wu, Lianxi Wang, Shengyi Jiang
Artificial Intelligence
AI as a Compiler: Compiling Triton kernels without the Triton compiler
François Costa, Charly Castes, Thomas Bourgeat et al. (+1 more)
Compiler backends are expensive to build and maintain as programming models, workloads, and accelerators evolve. We investigate whether large
language models can replace the conventional optimizing and lowering pipeline, a process that we call AI lowering. We study AI lowering from Triton to NVIDIA PTX: an LLM
agent translates Triton kernels directly into PTX. We build an environment that evaluates candidate PTX, and an agentic harness in which an LLM translates Triton kernels into PTX. Across twelve common kernels on Ada, Hopper, and Blackwell GPUs and ten kernels from recent ML papers, AI lowering achieves 0.83x-3.34x the performance of autotuned Triton. The largest gains come from transformations that Triton's lowering pipeline does not perform, such as decoding packed binary weights directly into Tensor Core operands (3.34x on BitDelta), assigning each thread a complete softmax row in tensor
memory (1.37x on FlashAttention), and reusing overlapping convolution windows (up to 2.23x). These results rely on a robust evaluation harness with comprehensive verification support. We build on Volta, an existing PTX verifier, and substantially extend it to support modern GPU architectures by introducing support for Blackwell's tcgen05 Tensor Core interface. This requires modeling three architectural features: managed tensor
memory, descriptor-based operand layouts, and asynchronous execution coordinated through commits, waits,
memory barriers, and proxy fences. We discuss the challenges involved in formalizing them, as well as the current limitations. Our results suggest an emerging future in which AI compilers replace custom-written intermediate representations and checkers, reducing the time and engineering effort required to bring up software for new general-purpose and custom chips.
Read the full abstract ▾
All authors François Costa, Charly Castes, Thomas Bourgeat, Azalia Mirhoseini
Artificial Intelligence
Aperture: Merge-Consistent Rotary States for Compressed Tokens
Yuhao Du and Shunian Chen
Token compression combines content from several positions, yet rotary position
embeddings usually assign the merged
token one coordinate. We ask what positional information must survive later merges. Aperture stores
Fourier moments of the
token's weighted support at the model's rotary frequencies. We prove that these moments have minimal real dimension among continuous states sufficient for the selected expected rotary interactions. Represented mass makes updates additive;
attention normalisation remains a separate readout choice. Uniform intervals give a centre rotation times a sinc gain. We characterise when centres determine interval widths and construct matched examples where they do not. Numerical checks verify the weighted-support implementation. In trained temporal readers, compression transfer varies with gain calibration and feature placement. In a prespecified native
video question-answering comparison, stored support reaches $65.63\%$ accuracy versus $67.12\%$ for the deployed merging rule. These results separate exact positional preservation under compression from downstream benefit.
Read the full abstract ▾
Artificial Intelligence
Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D Scenes
Xiaokang Ye, Siddhant Hitesh Mantri, Zimeng Chen et al. (+6 more)
Frontier coding
agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely control scene state remains unclear. The generated 3D scene is a persistent, executable artifact: a convincing render can hide incorrect spatial relations, intersecting objects, or unintended modifications. We introduce Code4Scene, a
benchmark of 190 Unreal Engine cases built from human-assembled scenes that evaluates coding
agents on two complementary settings under a shared execution interface. Construction tests scene-level spatial
reasoning from open-ended
language specifications, where many realizations are valid; editing tests precise control of scene state, where the
agent must recover the target scene from reference images while preserving everything else. Rather than scoring code or rendered views, Code4Scene evaluates the generated engine-native scene for task fulfillment, artifact integrity, and static physical validity, with edits additionally compared against withheld ground truth. Across 14 coding-
agent configurations on the 95-case public set, construction and editing performance are strongly correlated but not interchangeable (Spearman $\rho = 0.78$): Claude Fable 5.1 leads construction, Gemini 3.8 Flash leads editing, and GPT-6 Astra narrowly leads overall. Spatial Composition is the weakest construction category for every
agent, while editing remains imprecise: the best Repair F1 is only 0.527, and 35.8% of edits that fully recover the target still introduce unintended changes elsewhere in the scene. These results expose a gap between plausible 3D generation and reliable spatial
reasoning and state control.
Read the full abstract ▾
All authors Xiaokang Ye, Siddhant Hitesh Mantri, Zimeng Chen, Edward Zhang, Zhaoxu Zheng, Yuanheng Li, Yizhao Chen, Tianyang Huang, Lianhui Qin
Artificial Intelligence · Cross-listed from cs.LG
Beyond Conditional Independence: Root Cause Analysis with Deep Causal Models
Md Musfiqur Rahman, Kenneth Lee, Ziwei Jiang et al. (+3 more)
Root cause analysis (RCA) is a critical problem in many real-world scenarios. RCA enables the identification of faulty or failing mechanisms in a system by comparing anomalous observations with corresponding reference (i.e., regular) observations. However, existing approaches rely either on heuristic methods or on conditional independence tests with a strong unconfoundedness assumption, and thus fail to exploit other complicated distributional constraints in the presence of latent variables. To relax these assumptions, we model the underlying system as a causal model and the anomalous system as a change in the structural functions of the same causal model. Specifically, to handle unobserved confounders, we establish an implicit connection between distributional constraint testing and root cause analysis. To adapt our approach to data generated from arbitrary causal models, we employ the deep causal model (DCM) framework, in which we design the causal model using neural networks. Finally, we illustrate how our method, RCA-DCM, can utilize different levels of partial graphical knowledge to perform RCA. We evaluate RCA-DCM against state-of-the-art baselines on simulated
datasets, a physics-based causal chamber and two micro-service applications. RCA-DCM improves top-1 accuracy over the strongest baseline on both Sock Shop (0.880 vs. 0.752) and Online Boutique (0.776 vs. 0.712), and when the true root cause in the causal chamber is unobserved and acts as a latent confounder, it recovers the exact root-cause set more often than any competing method (perfect recovery rate (PRR) 0.846 vs. 0.731).
Read the full abstract ▾
All authors Md Musfiqur Rahman, Kenneth Lee, Ziwei Jiang, Padmaja Jonnalagedda, Ruocheng Guo, Murat Kocaoglu
Artificial Intelligence
Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients
Aram Davtyan, Pablo Acuaviva, Sebastian Stapf et al. (+1 more)
Can a population of neural networks develop a useful division of labor without a shared gate or gradients between
agents? We study a setting where each network has its own weights, trains independently on the same heterogeneous data, and can ask another
agent for help through a forward pass. Unlike mixtures of experts, where a jointly trained gate assigns inputs to experts, specialization here must emerge without central control. We test this in a small scale proxy for predictive visual pretraining. Initially identical
agents are finetuned on an unlabeled mixture of six visual domains using masked prediction of frozen DINOv3 features. We measure specialization by asking whether the best
agent for an input aligns with its latent domain, and utilization by asking whether responsibility is distributed across
agents. We progressively remove central control, ending with DISCO (DIStributed COllaboration) where each
agent locally selects a helper, reads its internal state through a gradient free channel, and rewards its router only for the improvement that help provides. Specialization emerges and is useful. Randomly routed populations underperform a single generalist, while semantically routed populations outperform it, showing that specialization rather than population size drives the gain. Specialization persists without a central router, and gradient free communication lets nonexperts exploit emergent expertise. In DISCO, a random
agent helped by the expert matches the solo generalist, while experts surpass it, including on data outside the specialization mixture. Local routers select the emergent expert for 98% of inputs. These effects persist across population size, model capacity, data imbalance, and finetuning seeds, providing measurable evidence for the dynamics needed by decentralized predictive pretraining.
Read the full abstract ▾
All authors Aram Davtyan, Pablo Acuaviva, Sebastian Stapf, Paolo Favaro
Artificial Intelligence · Cross-listed from cs.CV
Dual-Mode Low-Rank Learner with Bridge-Prototype Ensemble for Vision-Language Class-Incremental Learning
Chiyuan He, Zihuan Qiu, Fanman Meng et al. (+5 more)
Benefiting from transferable visual-textual
alignment, CLIP has been widely adopted for class-incremental learning (CIL). However, existing learners either repeatedly update components shared across tasks, leading to knowledge overwriting, or overly isolate new-task updates, hindering the reuse of CLIP's transferable knowledge and limiting plasticity. Moreover, the text-based or bimodal classifier designs still fail to effectively integrate complementary information from the visual and textual modalities. To address these challenges, we introduce DuLBE, which couples dual-mode low-rank learning with a bridge-prototype ensemble classifier for exemplar-free CIL. DuLBE allocates two visual low-rank update modes according to the gradient demand and uses gradient routing to coordinate them: a compact and rewritable shared mode is selected from historically occupied visual directions to reuse transferable knowledge, while residual modes provide low-interference channels for task-specific variations. Building on the resulting stable inter-modal structure, we further construct geodesic bridges between visual prototypes and text
embeddings on the unit hypersphere, and ensemble reliable bridge prototypes to compensate for the modality-gap limitations of textual decision boundaries. Extensive experiments under multiple settings show that DuLBE achieves state-of-the-art CIL performance while retaining the high parameter efficiency of low-rank tuning.
Read the full abstract ▾
All authors Chiyuan He, Zihuan Qiu, Fanman Meng, Chao Wang, Liangjiang Chen, Linfeng Xu, Qingbo Wu, Hongliang Li
Artificial Intelligence · Cross-listed from cs.CV
NesTok: Nested Self-Aligned 1D Tokenizer for Autoregressive Image Generation
Jiawei Zhang, Shuhao Liu, Rong Huang et al. (+4 more)
One-dimensional (1D) variable-length visual tokenizers enable adaptive compression by varying the number of
tokens, allowing downstream autoregressive (AR) models to flexibly trade off generation quality against computational cost using a single tokenizer. However, existing approaches based on nested dropout often fail to fully exploit the representational capacity of the tokenizer, resulting in suboptimal performance in both image reconstruction and generation. In this work, we introduce NesTok, a nested self-
alignment framework tailored to dynamic visual tokenizers. NesTok introduces cross-length training, which jointly optimizes reconstruction across
token lengths while using the full-length sequence to guide shorter counterparts, enabling shorter
token sequences to approach the reconstruction quality of full-length sequences. On ImageNet, NesTok improves substantially over standard training and achieves an rFID score of 0.98. On downstream image generation, it achieves the state-of-the-art gFID score of 1.46 on ImageNet 256$\times$256 among existing variable-length autoregressive image generation methods. Code will be available at https://github.com/Jiawei804/NesTok.
Read the full abstract ▾
All authors Jiawei Zhang, Shuhao Liu, Rong Huang, Yuancheng Li, Zhihui Li, Xiaojun Chang, Changlin Li
Artificial Intelligence · Cross-listed from cs.LG
Group-Marginalized Self-Rewarding RL Drives Zero-Label Self-Evolving
Yiming Wang, Yikang Liu, Qingyuan Tian et al. (+4 more)
Self-rewarding reinforcement learning (RL) enables large
language models (LLMs) to self-evolve without human labels. Existing ensemble-based methods construct reward references from rollout groups and assign rewards accordingly. However, a response's reward representation also depends on its randomly sampled group context, i.e., the other responses in its group. Using only one group-context realization may miss desired reward signals and provide unreliable guidance for policy optimization. To address this issue, we propose Group-Marginalized Advantage Estimation (GMAE), which aggregates reward realizations across possible contexts into a response-level distribution and estimates expected advantages. Experiments across eight
benchmarks and four base models demonstrate strong performance and cross-domain generalization. GMAE also exhibits stable learning, low extra cost, and good applicability across training
datasets and RL backbones.
Read the full abstract ▾
All authors Yiming Wang, Yikang Liu, Qingyuan Tian, Xingyu Chen, Zhuosheng Zhang, Zhaopeng Tu, Rui Wang
Artificial Intelligence
Generalizable Lifelong Model Editing via Preference Optimization
Dahyun Jung, Suhyune Son and Heuiseok Lim
Knowledge editing enables rapid updates of specific factual knowledge in large
language models (LLMs) without full retraining. However, more realistic scenarios call for a lifelong framework that handles continual updates rather than one-off modifications. In such settings, existing editing methods often overfit to target
prompts, significantly degrading both the generalization of the edited knowledge and the model's general capabilities. To address this issue, we propose GLIME (Generalizable Lifelong Model Editing), which combines knowledge editing with preference optimization over generation behavior. GLIME further incorporates replay-based editing and a gradient constraint to preserve previously edited knowledge. Experimental results show that GLIME significantly improves knowledge generalization in lifelong editing settings while maintaining both editing performance and general capabilities.
Read the full abstract ▾
Artificial Intelligence
EASE: Behavior-Adaptive Skill Curation for Self-Evolving Agents
Zhen Xiong and Qiaoyu Tan
Agent skills provide a lightweight mechanism for self-evolving
agents to accumulate reusable procedural knowledge without updating model parameters. However, existing learned skill curators typically optimize curation without explicitly modeling downstream executor behavior. We show that this can cause systematic cross-executor degradation: curators trained with different executors perform best when paired with their own training executor, indicating that effective skill curation is executor-dependent. We formulate behavior-adaptive skill curation and introduce EASE, a framework that learns a single curator that adapts its decisions to different executor behaviors. EASE maintains an online behavioral profile of recent execution patterns and conditions the curator on this profile, the current trajectory, and retrieved skills to add, modify, or remove skills from an evolving repository. We train the shared curator jointly across multiple frozen executors with reinforcement learning, using
retrieval-aware and behavior-aware temporal attribution to focus optimization on curation actions with observable downstream influence. Across ALFWorld, ScienceWorld, and WebShop, with executors ranging from Qwen3-8B/32B and GPT-OSS-120B to unseen Kimi K2.6, DeepSeek V4 Flash, and Gemini 3.5 Flash, EASE outperforms strong skill- and
memory-based baselines without per-executor finetuning. EASE also maintains 34.5–41.0% fewer skills, improves skill
retrieval by 36.3–38.7% and measured edit utility by 51.8–60.0%, and reduces deployment-time inference
tokens by 9.1–14.5%. These results establish behavior-adaptive skill curation as an effective principle for building self-evolving
agents.
Read the full abstract ▾
Artificial Intelligence
SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation
Zhenrui Yue, Huimin Zeng, Yueqi Wang et al. (+8 more)
Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for improving large
language models (LLMs) on various tasks, yet its sparse outcome rewards lack
token-level credit assignment for intermediate steps. To address this, on-policy self-
distillation (OPSD) leverages a self-teacher with privileged context to provide additional dense learning signals. However, because the self-teacher is often overconfident and imposes excessive penalties on long
reasoning trajectories, OPSD frequently struggles in practice. To mitigate this, we propose self-instructing policy optimization (SIPO) with a contrastive self-teacher to provide dense credit. At each iteration, SIPO samples multiple rollouts per
prompt from the current policy, scores them with environment rewards, and constructs two teacher contexts for each rollout by pairing the reference answer with mistakes made within the group. The model then re-evaluates its own responses under both contexts, using the difference between the two teacher log-probabilities as
token-level feedback, so that biases shared by both contexts are expected to largely cancel. The resulting objective yields a
token-level advantage for every rollout: the reward still sets the main direction of each update while the self-teacher redistributes credit across
tokens. Even in groups where every rollout fails and group-relative advantages vanish, SIPO still provides a learning signal. By preserving direct optimization of the task reward while providing dense,
token-level feedback, this approach bridges reinforcement learning and on-policy self-
distillation. Extensive experiments across multiple
reasoning and code-generation
benchmarks demonstrate that SIPO outperforms both RLVR and OPSD baselines without an external teacher or additional generation.
Read the full abstract ▾
All authors Zhenrui Yue, Huimin Zeng, Yueqi Wang, Yaokun Liu, Fengran Mo, Jinghan Zhang, Mung Yao Jia, Gyuseok Lee, Yang Zhang, Na Wei, Dong Wang
Artificial Intelligence
Distinguish or Homogenize: Last-Chance Policy Identification and Risk-Budgeted Recovery under Irreversible Resource Depletion
Yibo Guo and Xiaodan Wang
Under irreversible resource depletion, an
agent can spend resources to distinguish among latent fault models, or to change the system state so that the remaining models admit a common acceptable continuation–at which point further diagnosis becomes unnecessary. This distinguish-or-homogenize principle identifies a path that existing frameworks for identification, planning, and diagnosis do not make explicit: prior formulations treat the mapping from fault models to acceptable policies as a given, whereas LCPI makes it a function of the
agent's own actions. We formalize this principle through Last-Chance Policy Identification (LCPI), where correctness is evaluated at the state the
agent reaches rather than at the initial state. The Last Identifiable Margin (LIM) marks the feasibility boundary between distinguishing and homogenizing. For deterministic diagnostic graphs we provide the Exact-LIM recursion; for noisy finite-horizon recovery we propose Risk-Budgeted Compatibility Planning (RBCP), which searches a compatibility-aware frontier under a hard worst-case failure constraint. Across incident recovery on abstract microservice
topologies and latent-damage
navigation in MiniGrid, RBCP improves risk-feasible recovery while satisfying the failure budget. A sham control–cost-matched actions that preserve model incompatibility–eliminates the gain entirely, confirming that the benefit comes from changing which policies are acceptable for which models, not from extra search or additional budget.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CE
Frontier Autolab: Organizational Memory, Adversarial Dissent and Temporal Leakage in Multi-Agent LLM Firms Across Fifty Years of Technological Change
Bravish Ghosh
Multi-
agent LLM systems are increasingly structured like organizations, with roles, critics and shared
memory, yet they are evaluated on tasks that last minutes. We ask how such an organization behaves when the ground it stands on keeps moving. Frontier Autolab is a long-horizon testbed in which one simulated firm, voiced by sixteen role personas and a dedicated Red Team, must re-found itself in nine technology eras from 1990 to 2040. Each era is temporally gated: the firm decides from a dated briefing, a historian-judge then reveals what happened and scores the decision on a five-dimension rubric, and lessons enter a persistent Playbook. Six eras are scored against history, one against the live
market and two are open forecasts. Across four trajectories (36 era decisions, 180 subscores) we find a consistent foresight-commitment gap: in all 24 historically scored eras the judge rated the firm's recognition of the coming shift above its choice of where to build (mean gap 1.9 points on a 10-point scale), because boards chose the layer their existing assets could reach. Organizational design shaped long-run character. A Red Team armed with numeric kill gates produced fifty years of gated pilots and no product, and the rubric rated this firm highest; firms whose
memory stored
market-structure lessons pivoted every era, while a firm whose
memory stored only validation procedure kept one method throughout. We also show why such results are hard to trust. Scores rise across eras in every run while the judge's own hindsight subscore falls (within-run r = -0.58), so apparent learning is confounded with recall of history, and we trace further distortions to self-judging, briefing selection and score aggregation. We release all records and an API harness, and specify fictional and post-cutoff eras that would turn the testbed into a
benchmark.
Read the full abstract ▾
Artificial Intelligence
BiFE: Search-Efficient Discovery of CPU-Only Branching Policies via LLM-based Bi-Fidelity Evolution
Ce Zhang, Bin Zhang, Zhiwei Xu et al. (+5 more)
In branch-and-bound (B&B) for mixed-integer linear programming (MILP), branching variable selection critically impacts efficiency. Existing neural branching policies often require GPU inference, while CPU-efficient symbolic expressions lack the representational capacity for complex logic. Large
Language Model (LLM)-generated code provides a flexible search space for designing lightweight branching rules with diverse algorithmic logic. To discover effective rules within LLM-based evolutionary frameworks, a core challenge arises: full B&B evaluation on real instances is prohibitively expensive, whereas offline imitation learning suffers from distribution shift. To address this, we introduce a Bi-Fidelity Evolutionary framework (BiFE). It employs low-fidelity imitation scores as a rapid pre-screener and selectively applies high-fidelity on-instance evaluation only to elite candidates, effectively balancing search efficiency with performance reliability. Experiments validate both the search efficiency of BiFE and the competitiveness of its discovered rules, which outperform the SCIP solver and other baselines on CPUs, and even surpass certain GPU-based neural policies.
Read the full abstract ▾
All authors Ce Zhang, Bin Zhang, Zhiwei Xu, Hao Chen, Xinyue Lu, Shanwei Fan, Yingxuan Teng, Guoliang Fan
Artificial Intelligence
Can Agents Design Libraries for Agents?
Gabriel Orlanski, Alex L. Zhang, Avi Trost et al. (+4 more)
Agents increasingly build on code written by other
agents, and they reimplement rather than reuse, growing the codebases later
agents must work in. To measure how well
agents design libraries for other
agents, we introduce LibraryDesignBench, a two-phase
benchmark in which an
agent implements a full-featured library from a specification that defines required capabilities and potential use cases without prescribing the design. We evaluate the library through the correctness and simplicity of programs written by three user
agents from different model families. The
benchmark spans 242 expert-validated programming problems across 15 library-design tasks in four
languages. On eleven of the fifteen tasks,
agent designers reproduce the abstractions of the human-written production library. Downstream
agents adopt
agent- and human-written libraries alike but underuse them, reimplementing capabilities the library already provides. Our failure analysis finds that downstream
agents write extra code mainly because
agent-written libraries are rigid or hard to use, not because capabilities are missing. We also experiment with giving designers more prescriptive,
agent-first guidance and having them test their library with subagents; this improves downstream scores and yields simpler programs. LibraryDesignBench provides both a testbed for evaluating library-design practices for
agent users and an initial design baseline that improves downstream reuse.
Read the full abstract ▾
All authors Gabriel Orlanski, Alex L. Zhang, Avi Trost, Vincent Sunn Chen, Frederic Sala, Aws Albarghouthi, Ludwig Schmidt
Artificial Intelligence
Can AI Scientists Change Their Minds? Prior-Evidence Conflict in Synthetic Universes
Kargi Chauhan
Can a scientific
agent distinguish a law it inferred from evidence from one it merely recognizes? We introduce Synthetic Universes, a controlled
benchmark that pairs canonical famous worlds with matched twisted twins governed by nearby noncanonical mechanisms. We evaluate each reported law twice: by executing it on held-out continuations and transfer settings, and by independently checking whether it recovers the generating mechanism. In the current checkpoint of a pre-specified 60-
cell study, 22 trials were graded and one additional run ended in infrastructure failure. Among 20 twin trials, 8 pass predictive verification while 5 recover the generator. The dissociation is bidirectional: six parsable outputs predict successfully while missing the mechanism, whereas three recover the mechanism but fail predictive rollout. Drag exhibits the first pattern (5/5 predictive pass, 1/5 mechanism recovery);
Gravity exhibits the second (1/5 predictive pass, 4/5 mechanism recovery). Because matched famous controls, the corrected identifiability sweep, and the Evidence Ladder remain incomplete, we do not claim a confirmatory causal prior-conflict effect. Instead, the completed runs establish a narrower verification result: predictive adequacy and mechanism recovery are distinct scientific claims and require distinct tests.
Read the full abstract ▾
Artificial Intelligence
JudgeProfile: Understanding and Steering Subjectivity in LLM Judges
Qi Cao, Kangning Liu, Xuan Kan et al. (+10 more)
LLM judges are inherently subjective, often favoring different responses in pairwise comparison when neither option is objectively wrong. To study this subjectivity, we introduce JudgeProfile, a framework that dissects LLM evaluation into perception (how a judge compares two responses across specific attributes like clarity, correctness, and detail) and prioritization (how much each attribute influences the final choice). We curate SubjectiveSet, a
dataset of 50,013 response pairs from 17 public data sources, evaluated by 21 LLM judges across 87 attributes. We find a hidden consensus in perception: judges frequently agree on attribute judgments even when their overall choices diverge. Building on this separation, we first characterize each judge's prioritization using attribute weights estimated from its own overall choices. These weights differ across judges even when estimated from the same attribute judgments. We then learn new weights from reference labels to adapt their decisions to a target evaluation standard. Reweighting perceived attributes improves average held-out agreement with reference labels from 66.48% to 71.97%, outperforming fine-tuning and rubric prompting. Our findings show that understanding and steering the subjectivity of LLM judges requires
attention not only to what they perceive, but also to how they prioritize it.
Read the full abstract ▾
All authors Qi Cao, Kangning Liu, Xuan Kan, Shunwen Tan, Yang Pei, Dake Chen, Yatai Ji, Zixuan Ye, Yuanpeng Tu, Daniel Li, Junbiao Tang, Pengtao Xie, Zihao He
Artificial Intelligence · Cross-listed from cs.CL
Lost in Conversation or Lost in Translation? Diagnosing Multi-Turn Degradation in RAG
Pranav Handa and Ariful Azad
When conversing with large
language models (LLMs), users often begin with a simple question and build towards a multi-hop question through follow-up turns.
Retrieval-augmented generation (RAG) and its graph-based variant (GraphRAG) have become the dominant approaches for grounding LLM responses in external evidence, yet both are evaluated almost exclusively on single-turn, fully specified queries. We systematically investigate this evaluation mismatch through a large-scale simulation study. Building on prior work on multi-turn LLM evaluation, we transform questions from multi-hop question answering (QA)
benchmarks into underspecified conversations and evaluate ten LLM assistants with eight
retrieval systems across 1.5 million simulated conversations. Our findings reveal that multi-turn interaction causes widespread performance degradation, incurring relative performance drops of up to 21% and increasing unreliability by 47%, making RAG systems simultaneously less accurate and less reliable. We identify two distinct failure modes behind this degradation. Systems are either lost in translation, where conversational rephrasing distorts the
retrieval query, or lost in conversation, where
retrieval succeeds but the LLM fails to synthesize evidence distributed across turns.
Read the full abstract ▾