Artificial Intelligence · Cross-listed from cs.LG
Program-as-Weights: A Programming Paradigm for Fuzzy Functions
Wentao Zhang, Liliana Hotsko, Woojeong Kim et al. (+3 more)
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly outsourced to large
language model APIs at the cost of locality, reproducibility, and price. We propose fuzzy-function programming: compiling such a function from a natural-
language specification into a compact, locally-executable neural artifact. We instantiate this paradigm with Program-as-Weights (PAW), in which a 4B compiler trained on FuzzyBench, a 10M-example
dataset we release, emits parameter-efficient adapters for a frozen, lightweight interpreter. A 0.6B Qwen3 interpreter executing PAW programs matches the performance of direct prompting of Qwen3-32B, while using roughly one fiftieth of the inference
memory and running at 30
tokens/s on a MacBook M3. PAW reframes the foundation model from a per-input problem solver into a tool builder: invoked once per function definition, it produces a small reusable artifact whose subsequent calls per function application are cheap and offline.
Read the full abstract ▾
All authors Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng
Artificial Intelligence
Online Safety Monitoring for LLMs
Mona Schirmer, Metod Jazbec, Alexander Timans et al. (+3 more)
Despite
alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs online and raising an alarm when safety can no longer be assumed is therefore critical. We study a simple real-time monitor that turns a verifier signal from an external model into an alarm decision by thresholding, with the threshold calibrated via risk control. In experiments on mathematical
reasoning and red teaming
datasets, we show that this simple design is competitive with more advanced monitors based on sequential hypothesis testing.
Read the full abstract ▾
All authors Mona Schirmer, Metod Jazbec, Alexander Timans, Christian Naesseth, Maja Waldron, Eric Nalisnick
Artificial Intelligence
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
Yanjun Zhao, Ruizhong Qiu, Tianxin Wei et al. (+6 more)
Understanding and
reasoning over long contexts has become a key requirement for deploying large
language models (LLMs) in realistic applications. Although recent LLMs support increasingly long context windows, they often fail to use relevant evidence that is already present in the input, revealing a gap between context access and effective context utilization. In this work, we propose Recursive Evidence Replay as LLM Harness for Long-Context
Reasoning (RECONTEXT), a training-free inference method for improving long-context
reasoning. RECONTEXT uses model-internal relevance signals to construct a query-conditioned evidence pool and replays it before final generation while preserving the full original context. This recursive selection process separates evidence organization from answer generation without training, external
memory, or context
pruning. We also provide a theoretical analysis based on associative
memory, which characterizes the context as a
memory store, the question as a
retrieval cue,
attention as cue-trace association, and replay as trace reactivation. Experiments on eight long-context
datasets with 128K context length show that RECONTEXT consistently improves evidence utilization across Qwen3-4B, Qwen3-8B, and Llama3-8B, achieving the best average rank on all three backbones. Code is available at https://github.com/Yanjun-Zhao/ReContext.
Read the full abstract ▾
All authors Yanjun Zhao, Ruizhong Qiu, Tianxin Wei, Yuanchen Bei, Zhining Liu, Lingjie Chen, Ismini Lourentzou, Hanghang Tong, Jingrui He
Artificial Intelligence
What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates
Arman Ghaffarizadeh, Danyal Mohaddes, Aliakbar Izadkhah et al. (+1 more)
LLM
agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly to say. We study whether such social structure, without any explicit objective in the
prompt, changes what an
agent expresses publicly relative to an off-the-record (OTR) channel elicited under the same condition. We introduce a dual-channel debate framework in which
agents produce public utterances that enter the shared history alongside OTR responses that are recorded but never shown to the other participant. Across 10 models, 3 scenarios, and 5 variations within each scenario,
alignment-inducing settings produce systematic public-OTR divergence in the targeted
agent, with its decision divergence rising from a $\sim$3% baseline to roughly 40%. The effect is consistent across four aggregate analyses: stance, semantic similarity, natural
language inference, and survey responses. In some cases, the OTR response explicitly attributes public accommodation to relational pressures, such as career risk or sponsorship obligation. The findings suggest that
agent evaluation should extend beyond explicit goals and detect emergent objectives. We present a dual-channel evaluation framework and complementary behavioral measures that operationalize this assessment.
Read the full abstract ▾
All authors Arman Ghaffarizadeh, Danyal Mohaddes, Aliakbar Izadkhah, Shahriar Noroozizadeh
Artificial Intelligence · Cross-listed from cs.CL
Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
Yuxuan Li, Lingxi Xie, Xinyue Huo et al. (+6 more)
Long-form TV dramas present a formidable challenge for comprehensive
video understanding, where deciphering complex storyline often relies on speaker recognition, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce DramaSR-532K, a large-scale
benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose DramaSR-LRM, a robust approach built upon a large
reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via
multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short utterances where acoustic biometrics are inherently unreliable. All the data and code will be made publicly available at the project page: https://www.github.com/198808xc/DramaSR-LRM.
Read the full abstract ▾
All authors Yuxuan Li, Lingxi Xie, Xinyue Huo, Jihao Qiu, Jiacheng Shao, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Qi Tian
Artificial Intelligence · Cross-listed from cs.LG
DemoPSD: Disagreement-Modulated Policy Self-Distillation
Yunhe Li, Hao Shi, Wenhao Liu et al. (+5 more)
On-policy self-
distillation (OPSD) has emerged as a practical method for training large
language models (LLMs) to reason, where a single model acts as both the teacher and the student with different levels of information access. However, recent studies have found that the teacher's dense
token-level supervision, conditioned on privileged information, can lead to overfitting to in-domain patterns, suppress exploration, and hurt cross-domain generalization, while also introducing a more fundamental issue: *privileged information leakage*, where the student encodes answer-dependent shortcuts that are unavailable at test time. We introduce **DemoPSD**, a novel framework that resolves such problems through the idea of *selective adoption of teacher guidance*. Instead of fitting the full teacher distribution, DemoPSD steers the student toward a *reverse-KL barycenter target*, a weighted
geometric combination of the teacher and student distributions, that naturally balances learning from the teacher with preserving the student's own
reasoning capacity. We measure the difference between their distributions and use such a discrepancy to adaptively control the blending at each
token position. We provably show that DemoPSD achieves **(1)** *leakage attenuation*, i.e., effective mitigation of privileged information leakage; and **(2)** *exploration preservation*, i.e., preservation of exploration capacity under dense
token-level
distillation. Extensive experiments on SciKnowEval across four scientific fields show that DemoPSD outperforms both GRPO and SDPO while maintaining higher training
entropy and robustly generalizing to out-of-distribution GPQA
benchmarks.
Read the full abstract ▾
All authors Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song
Artificial Intelligence · Cross-listed from cs.LG
Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials
Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng et al. (+4 more)
Machine learning interatomic potentials (MLIPs) have become a hallmark of AI for scientific simulation. While efforts on new architectures and
datasets have led to increasingly accurate and general models, the choice of optimizer for training has largely remained unexplored, defaulting to Adam and its variants in the community. Here, we implement and systematically compare a class of recently proposed
matrix-structured optimizers, including
Muon, SOAP, and the hybrid SOAP-
Muon, for training NequIP and Allegro MLIP models. We find that these optimizers can substantially outperform Adam in both convergence speed and final accuracy. SOAP and SOAP-
Muon emerge as robust and consistently strong methods, while
Muon only provides partial gains relative to Adam. The improvements are particularly pronounced under partial force supervision. Our results indicate that optimizer choice is an overlooked yet impactful design axis for MLIPs.
Read the full abstract ▾
All authors Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng, Laura Zichi, Chuin Wei Tan, Marc L. Descoteaux, Boris Kozinsky
Artificial Intelligence
G-RRM: Guiding Symbolic Solvers with Recurrent Reasoning Models
Timo Bertram, Sidhant Bhavnani, Richard Freinschlag et al. (+3 more)
In this work, we focus on SE-RRMs, a symbol-equivariant instantiation of RRMs that exhibits improved extrapolation to larger problem sizes. We propose a neuro-symbolic approach, “Guiding with Recurrent
Reasoning Models” (G-RRM), which integrates SE-RRMs with symbolic solvers for constraint satisfaction problems. SE-RRMs act as neural solvers that generate full solution proposals and guide classical symbolic solvers, such as backtracking or SAT-based methods like Glucose 4.1 and CaDiCaL 3.0.0, that produce globally correct solutions. Centrally, we investigate when neural guidance with G-RRM improves the search efficiency of symbolic solvers. % Our experiments show that the efficacy of G-RRM depends on two conditions: first, the problem instances must have an expansive combinatorial search space to expose potential gains, and second, the solver architecture must be capable of dynamically overwriting its branching choices to recover when neural hints are imperfect. When these conditions hold, guidance drives median conflict counts to zero and yields significant wall-clock speedups: on $9\times9$ Sudoku, where the SE-RRM correctly solves $91.1\%$ of instances, backtracking accelerates by $33.3\times$ and Glucose 4.1 by $1.70\times$ (median, $p<0.001$), with Glucose 4.1 retaining a $1.17\times$ speedup on perfect-hint $25\times25$ grids. In contrast, CaDiCaL 3.0.0, whose runtime is overhead-dominated and which always respects the injected branching hints rather than overwriting them, shows no significant speedup (median $1.02\times$, n.s.) and even a small significant mean slowdown ($0.90\times$) on $9\times9$. These results delineate the regimes in which neural guidance translates into practical speedups.
Read the full abstract ▾
All authors Timo Bertram, Sidhant Bhavnani, Richard Freinschlag, Erich Kobler, Andreas Mayr, Günter Klambauer
Artificial Intelligence · Cross-listed from cs.CV
Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning
Xuehui Wang, Xuankun Yang and Wei Shen
Visual
token pruning is a crucial strategy for accelerating VLMs by compressing redundant image patches, yet existing methods often fail to preserve critical cues under dense instructions and fine-grained queries. In this paper, we investigate this failure and identify two underlying bottlenecks: the widespread dispersion of textual noise that corrupts dense cross-modal scoring, and the feature fragmentation inherent to standard
token selection. To address these issues, we propose
Entropy-Aware Dense
Pruning (EADP), a framework that reformulates
pruning as a structured compression problem. EADP first leverages statistical
entropy to quantify and filter out textual noise, yielding a robust, fine-grained instruction relevance score. Subsequently, instead of naive Top-K selection, EADP casts
token selection as a submodular maximization problem with a spatial prior, explicitly ensuring a holistic and non-redundant visual representation. Extensive experiments demonstrate that EADP improves the accuracy-efficiency trade-off of VLMs, robustly preserving fine-grained visual cues under strict
token budgets while achieving SoTA performance on challenging
multimodal benchmarks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution
Jiale Amber Wang, Kaiyuan Wang and Pengyu Nie
Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update
benchmarks often isolate the test from the code change, and rely on static metadata that does not verify whether a test is executable or semantically tied to the code change. This makes it difficult to evaluate whether a test automation
agent understands how a code change should propagate into the test suite. We introduce TestEvo-Bench, a
benchmark of test and code co-
evolution tasks mined from software repositories, with two tracks: in test generation, the
agent shall write new tests to capture the new software behavior; in test update, the
agent shall adapt failing existing tests to the changed software behavior. Each task is anchored to a real commit history and packaged with environment configuration to support execution-grounded metrics such as pass rate, coverage, and mutation score. TestEvo-Bench is also a live
benchmark: each task records the timestamp of the test and code changes, and new tasks are periodically mined by our automated pipeline, so evaluation can be restricted to tasks postdating a model's training cutoff to reduce data leakage risk. The current snapshot contains 746 test generation and 509 test update tasks, curated from 59,950 candidate co-
evolution records across 152 open-source Java projects. We experiment with four state-of-the-art
agents that combine strong harnesses (Claude Code, Gemini CLI, and SWE-
Agent) with strong foundation models (Claude Opus 4.7 and Gemini 3.1 Pro). Results show that they achieve up to 77.5% success rate on test generation and 74.6% on test update. However, success rate is materially lower on the most recent
benchmark tasks and drops significantly under limited per-task cost.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CY
Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting
Vivienne Ming
Whether pairing people with AI helps or hurts is usually reported as a single average effect. Using a real-money prediction
market (Polymarket) as an objective, externally resolved
benchmark, this pilot shows that the value of human-AI collaboration depends on a specific, measurable form of human capital. Analyzed at the level of the individual forecaster, hybrid performance is trimodal: most people either deferred to the model (matching it) or used it to rubber-stamp a prior guess (performing worse than the model alone), while a minority engaged in genuine complementary
reasoning and reached accuracy matching or even exceeding (i.e., lower error than) the
market itself. Collaborative traits (perspective-taking, intellectual humility, and curiosity) rather than raw cognitive ability or model
benchmarks, distinguished who reached that mode. The results are preliminary but statistically robust, and motivate a pre-registered replication now in preparation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs
Junhao Shi, Siyin Wang, Xiaopeng Yu et al. (+3 more)
Vision-
Language-Action (VLA) models are fundamentally bottlenecked by the scarcity of expert demonstrations – triplets of observations, instructions, and actions that are costly to collect at scale. We argue that this bottleneck stems from conflating two distinct learning objectives: acquiring physical competence (how to move) and acquiring semantic
alignment (what to do). Crucially, only the latter requires
language supervision. Building on this Decomposition Hypothesis, we propose Task-Agnostic Pretraining (TAP), a two-stage framework that first learns transferable motor priors from cheap, unlabeled interaction data – including discarded off-task trajectories and autonomous
robot play – via a self-supervised Inverse Dynamics objective. A lightweight second stage then grounds these priors in
language using minimal expert data. On the SIMPLER
benchmark, TAP matches models trained on over 1M expert trajectories while using orders of magnitude less labeled data, yielding a 10% absolute gain over standard behavior cloning. On a real-world WidowX platform, TAP retains 25% success under camera perturbations where internet-scale baselines collapse to 0%, demonstrating that task-agnostic pretraining produces robust, transferable physical representations and offers a scalable path forward for
Embodied AI.
Read the full abstract ▾
All authors Junhao Shi, Siyin Wang, Xiaopeng Yu, Li Ji, Jingjing Gong, Xipeng Qiu
Artificial Intelligence · Cross-listed from cs.CV
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Donghyun Lee, Jitesh Chavan, Duy Nguyen et al. (+5 more)
Diffusion transformers (DiTs) achieve state-of-the-art image and
video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training quantization (PTQ) is the natural remedy, yet DiT activations shift across timesteps,
prompts, and guidance branches, forcing prior methods to re-fit calibration data for every new checkpoint or modality. We present OrbitQuant, a data-agnostic weight-activation quantizer that bypasses range estimation by quantizing in a normalized, rotated basis. In this basis, a randomized permuted block-Hadamard (RPBH) rotation concentrates each coordinate around one fixed, known marginal regardless of the input, so a single Lloyd-Max codebook serves all timesteps,
prompts, and layers of a given input dimension. We extend the same quantizer to weight rows offline, absorbing the rotation into the weights so that it cancels inside each linear layer and only a forward rotation on the activations remains at runtime. The same recipe transfers from image to
video with no per-modality tuning. Across FLUX.1, Z-Image-Turbo, Wan 2.1, and CogVideoX, it sets the state of the art for PTQ at several low-bit settings. It also pushes PTQ of image
diffusion transformers to W2A4 with usable generation quality.
Read the full abstract ▾
All authors Donghyun Lee, Jitesh Chavan, Duy Nguyen, Sam Huang, Liming Jiang, Priyadarshini Panda, Timo Mertens, Saurabh Shukla
Artificial Intelligence · Cross-listed from cs.LG
Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation
Zhuowei Chen and Xiang Lorraine Li
Post-training large
language models (LLMs) without real-world interaction feedback or human-labeled supervision remains challenging, particularly in specialized domains where expert annotations are costly to obtain. Recent annotation-free self-
evolution methods address this by using the model's own outputs as supervision signals, constructing a teacher via additional context and aggregating predictions across multiple rollouts through majority voting to produce pseudo-labels. However, these approaches are not without drawbacks: SFT- and GRPO-based variants suffer out-of-domain performance degradation, while reward-based on-policy RL inflates calibration error. In this paper, we propose
Neuron On-Policy Self-
Distillation (
Neuron-OPSD), a data-centric framework for annotation-free self-
distillation that leverages internal
neuron activations to guide both training-data selection and teacher context construction. The model is then trained via on-policy
distillation from the teacher distribution, requiring no ground-truth labels at any stage. Across specialized-domain
benchmarks,
Neuron-OPSD improves in-domain task performance while preserving cross-domain generalization and mitigating calibration collapse over prior annotation-free baselines. This framework is particularly relevant to settings where online interaction or external supervision is costly or infeasible, and is conceptually distinct from offline RL approaches that rely on logged, reward-labeled trajectories.
Read the full abstract ▾
Artificial Intelligence
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
Zhilin Wang, Han Song, Runzhe Zhan et al. (+13 more)
Autonomous
agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy
Evolution, a controlled evaluation setting in which a harness-model
agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a
benchmark built from compact interactive RL environments that evaluates how
agents iteratively improve explored policies. On the EvoPolicyGym suite, GPT-5.5 achieves the strongest aggregate rank score and top-two performance on all 16 environments. Beyond leaderboard results, EvoPolicyGym also provides trajectory-level diagnostics that distinguish how
agents allocate budget, convert feedback into parametric tuning. These analyses show that strong autonomous policy
evolution depends not only on isolated task wins, but on discovering task-appropriate mechanisms and refining policies under bounded feedback.
Read the full abstract ▾
All authors Zhilin Wang, Han Song, Runzhe Zhan, Jusen Du, Jiacheng Chen, Tianle Li, Qingyu Yin, Yulun Wu, Zhennan Shen, Tong Zhu, Yanshu Li, Guanjie Chen, Derek F. Wong, Yafu Li, Yu Cheng, Yang Yang
Artificial Intelligence · Cross-listed from cs.SE
Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study
Achint Mehta
Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system
prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent
agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum) and a visual quality review. The runs spanned several model generations, two
agent harnesses, two
reasoning effort levels, a testing tool, and two design oriented
prompts. Capability tier dominated: frontier models clustered near the ceiling while a low cost local model fell to 24 to 37 points. A criterion level analysis revealed what run totals conceal. Container deployment was the dominant defect, failing first try in 44 percent of runs, with its failure rate shifting sharply across model generations while mean totals moved less than a point. The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria. Raising
reasoning effort from High to xHigh lifted first try perfect runs from 28 percent to 89 percent and cut corrective
prompts about five fold, for 9 to 29 percent more cost. A design oriented
prompt raised visual quality, 4.5 versus 3.0 on a 5 point scale, without lifting function, and a one paragraph paraphrase of its directive reproduced the entire lift. The practical lesson is to match the fix to the failure: most first run failures came from weak
reasoning, which a stronger model or more effort prevents, not from visible flaws a checking tool would catch.
Read the full abstract ▾
Artificial Intelligence
Automated grading of Linux/bash examinations using large language models: a four-level cognitive taxonomy approach
Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard et al. (+2 more)
Scalable and reliable grading of command-line examinations remains a challenge in computing education, where rising enrolments make manual marking difficult and rule-based autograders cannot handle partial credit, equivalent solutions, or syntactic variation. This paper evaluates whether four frontier Large
Language Models (GPT, Claude Opus, Gemini, and GLM) can approximate expert judgment when grading short Linux/bash command responses. The study adopts a four-level cognitive taxonomy that combines cognitive complexity and operational impact, ranging from information
retrieval (L1) and basic file manipulation (L2) to structural operations (L3) and advanced system management (L4). The models were tested with two
prompt variants, a minimal baseline and a rubric-enhanced version, on 1200 real responses from second-year Computer Engineering students independently graded by three expert instructors. Gemini~3.0 Pro with rubric-guided prompting achieved the highest human-AI agreement (ICC(3,1) = 0.888, MAE = 0.10, Bland-Altman bias = -0.014). Agreement declined consistently as taxonomy level increased, with the largest discrepancies at higher levels. Across all models, rubric quality had a larger effect than provider choice, with structured
prompts consistently improving agreement. These results show that question complexity is a reliable predictor of the difficulty LLMs face in grading accurately, and they establish a principled, taxonomy-based framework for determining which questions are suitable for AI-assisted grading and which require human review, while also providing a transferable evaluation protocol and
prompt templates.
Read the full abstract ▾
All authors Manuel Alonso-Carracedo, Ruben Fernandez-Boullon, Pedro Celard, Francisco J.Rodriguez-Martinez, Lorena Otero-Cerdeira
Artificial Intelligence · Cross-listed from cs.RO
WorldSample: Closed-loop Real-robot RL with World Modelling
Yuquan Xue, Le Xu, Zeyi Liu et al. (+5 more)
Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing
robots to improve through trial-and-error interaction beyond the states observed in demonstrations. However, deploying RL on real
robots remains constrained by high interaction costs, since each physical rollout is costly and reflects only one realized action-outcome path. To address this challenge, we propose WorldSample, a physically grounded data augmentation framework for real-
robot RL that closes a real-synthetic loop between physical rollouts, world-model generation, and policy improvement. Grounded on real rollouts, WorldSample generates high-fidelity synthetic transitions through a post-trained world model, which greatly lowers the visual
hallucination. Specifically, rather than simply using these transitions as real-world experience, WorldSample introduces Policy-Paced Learning (PPL) to regulate the training process through sample selection and scheduling, balancing useful augmentation against value overestimation and mitigating the
hallucination-induced noise. Experiments on
robot manipulation tasks involving contact-rich and precise tasks show that WorldSample improves policy success rate by 28% while reducing training steps by 59% compared with baselines. Furthermore, WorldSample improves world model visual fidelity by 19.4dB in PSNR and 0.47 in SSIM over demonstration-only post-training, validating the effectiveness of the real-synthetic loop for both policy and world model performance.
Read the full abstract ▾
All authors Yuquan Xue, Le Xu, Zeyi Liu, Zhenyu Wu, Zhengyi Gu, Xinyang Song, Bofang Jia, Ziwei Wang
Artificial Intelligence · Cross-listed from cs.LG
QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition
Quoc Bao Phan and Tuy Tan Nguyen
Federated learning (FL) enables collaborative model training across distributed devices without sharing raw data, making it suitable for
privacy-sensitive robotic sensing applications. However, multi-
agent systems generate heterogeneous and non-independent and identically distributed (non-IID)
multimodal sensor streams that degrade conventional FL
algorithms, while classical fusion modules introduce substantial parameter overhead and communication cost. This paper proposes QFedAgent, a hybrid
quantum-classical personalized FL framework for multi-
agent activity recognition. The approach integrates a variational
quantum circuit fusion module that models accelerometer–gyroscope interactions through
quantum state encoding and
entanglement, requiring only 72
quantum rotation parameters versus 33K in classical multi-layer perceptron-based fusion, achieving approximately 10x total parameter reduction. Experiments on the OPPORTUNITY
dataset under subject-based non-IID partitions demonstrate 97.7% mean test accuracy, confirming that parameter-efficient
quantum fusion remains competitive with conventional
federated baselines.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Neuron-Aware Active Few-Shot Learning for LLMs
Zhuowei Chen, Liwei Chen, Christian Schunn et al. (+2 more)
Active Few-Shot Learning (AFSL) adapts LLMs to specialized domains by identifying the most valuable unlabeled samples for annotation and use as few-shot demonstrations, effectively reducing human annotation costs while promoting high performance. However, existing methods typically rely on output-level signals for sample identification, such as predictive
entropy or semantic similarities with test-time data based on external
embeddings, which often overlook models' internal dynamics, which could pinpoint specific knowledge gaps. To bridge this gap, we propose NeuFS, a
Neuron-Aware Active Few-Shot Learning framework that shifts the selection paradigm from output-level proxies to models' internal dynamics. NeuFS utilizes
neuron activation patterns to represent sample directly, and includes a dual-criteria selection strategy that: (1) ensures few-shot sample diversity with
neuron patterns for broader example coverage, while (2) prioritizing on identifying informative and challenging few-shot samples LLMs tend to hallucinate by quantifying
neuron consensus. Experiments on three
datasets demonstrate that NeuFS excels in both
reasoning and text classification tasks, outperforming existing AFSL baselines. Ablation studies further highlight that internal
neuron activations provide a more principled and effective selection signal than external
embeddings, validating the superiority of the proposed NeuFS.
Read the full abstract ▾
All authors Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho, Xiang Lorraine Li
Artificial Intelligence
Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments
Xianhui Meng, Zirui Song, Yuchen Zhang et al. (+10 more)
Large
Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible object layout patterns in non-Manhattan settings, primarily because they struggle to model non-orthogonal spatial relationships, leading to high
geometric violations and low physical fidelity. To address this challenge, we propose SPG-Layout, a novel text-driven framework designed to generate physically plausible indoor scenes within complex non-Manhattan environments. Specifically, we first utilize statistical priors of object distributions to guide the training process, enhancing environmental understanding and fidelity. Furthermore, mirroring human design workflows, we adopt a hierarchical layout strategy that prioritizes the placement of large objects, thereby substantially minimizing layout violations. By synergizing these components, SPG-Layout achieves a balanced optimization of semantic realism and physical plausibility. To evaluate performance in these complex settings, we constructed a new
benchmark comprising 500 diverse non-Manhattan environments. Extensive experiments demonstrate that SPG-Layout consistently and significantly outperforms existing methods across both Manhattan and non-Manhattan environments. The code will be publicly released.
Read the full abstract ▾
All authors Xianhui Meng, Zirui Song, Yuchen Zhang, Li Zhang, Yongxuan Lv, Xiuying Chen, Kun Wang, Yan Luo, Kai Chen, Hangjun Ye, Long Chen, Jun Liu, Xiaoshuai Hao
Artificial Intelligence · Cross-listed from cs.RO
ACID: Action Consistency via Inverse Dynamics for Planning with World Models
Gawon Seo, Dongwon Kim and Suha Kwak
Decision-time planning with action-conditioned world models has become a popular paradigm for
embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the goal, leaving the realizability of the intermediate transitions unchecked–a predicted trajectory can look convincing while the environment rollout drifts away from it. In this paper, we propose ACID, a decision-time planning framework that introduces cycle action consistency: the action inferred backward from a predicted transition by an inverse dynamics model should recover the one that was conditioned on. We fold this per-step residual into the planning cost via a scale-invariant adaptive weight. Across four action-conditioned world models and eight tasks encompassing object manipulation and articulated control in simulation, visual
navigation, and real-
robot manipulation, ACID consistently improves planning and matches the baseline's accuracy with substantially less planning compute.
Read the full abstract ▾
Artificial Intelligence
Fast Multi-dimensional Refusal Subspaces via RFM-AGOP
Thomas Winninger
Steering and monitoring activations in Large
Language Models (LLMs) are increasingly used for both safety and interpretability. Early work assumed behaviours are encoded along single linear directions, but recent findings suggest complex behaviours, such as the refusal to answer harmful queries, live in multi-dimensional subspaces. However, existing methods for extracting these subspaces are computationally expensive, which becomes prohibitive on
reasoning models who produce long
reasoning traces. By adapting the Recursive Feature Machine (RFM)
algorithm – which can be computed efficiently – with a probe-informed initialization, we are able to identify the multi-dimensional refusal subspace in seconds, on
reasoning (Qwen 3) and non-
reasoning (Qwen 2.5) models. While RFM allows for faster subspace identification, it also showed better performances on the ablation task than its alternatives. More work is planned to better understand the relations between subspaces found by different methods. If confirmed, RFM could be a cheap and scalable complement to existing subspace-extraction methods in LLMs.
Read the full abstract ▾
Artificial Intelligence
Steerability via constraints: a substrate for scalable oversight of coding agents
Thomas Winninger
Coding
agents are capable; human oversight is the bottleneck. Unconstrained
agents introduce security risks, erode codebase scalability, and make human review increasingly costly. We argue that the same methods used for decades to manage large human engineering teams: access control, network policies, strict coding conventions enforced by tooling; transfer directly to coding
agents, and are cheaper (in
token) than recent agentic scaffolding. We sketch a start-to-end system on this principle, and report a controlled experiment in scalable oversight: a small reviewer (Gemma 4 e4b) inspects a Python codebase containing 11 inserted
backdoors. Recall rises from 54.5% (unconstrained, no tools) to 90.9% (constrained substrate plus a ~200-LoC `docs` CLI), with substrate and tools contributing independently. We choose Python deliberately: substrate-level oversight gains are largest where the
language gives the fewest guarantees by default; the principles extend to
languages like Rust.
Read the full abstract ▾
Artificial Intelligence
Hardware-Enforced Semantic Coordination for Safety-Critical Real-Time Autonomous Systems
Uwe M. Borghoff, Paolo Bottoni and Remo Pareschi
Recent advances in agentic AI are producing increasingly complex autonomous systems that integrate large
language models, world models, optimization engines, specialized neural architectures, autonomous platforms, and human operators. While much current research focuses on improving
reasoning capabilities, safety-critical real-time deployment also requires bounded and verifiable coordination among heterogeneous components operating concurrently under uncertainty. Software-mediated coordination presents fundamental limitations in domains where bounded latency, deterministic coordination, and enforceable safety guarantees are essential. Hence, we propose a hardware-enforced semantic coordination architecture in which selected coordination semantics are implemented directly at the hardware level via field-programmable gate arrays (FPGAs). The approach builds on the Topic-Based Communication Space Petri Net (TB-CSPN) framework, which separates semantic
reasoning from interaction management. In this approach, selected TB-CSPN coordination mechanisms are mapped onto FPGA primitives, creating a hardware-native semantic coordination layer. Focus is not on acceleration, but on enforcing temporal synchronization, semantic gating, authorization constraints, and bounded coordination behavior directly in hardware. Semantic
reasoning remains adaptive and software-driven, while embedded coordination semantics become deterministic.
Read the full abstract ▾
Artificial Intelligence
DRIFTLENS: Measuring Memory-Induced Reasoning Drift in Personalized Language Models
Xi Fang, Weijie Xu, Yingqiang Ge et al. (+3 more)
Personalization changes what a model says to a user; we show that it can also change the
reasoning trajectory used to justify the response. Modern LLMs personalize interactions by storing user attributes, preferences, and prior context, then injecting this information into future
prompts. We study whether such
memory reshapes
reasoning on open-ended questions where no single ground-truth answer exists. To quantify this effect, we introduce DRIFTLENS, a ground-truth-free framework that maps each expressed
reasoning step to a value category and measures divergence between a question's no-
memory trajectory and its trajectory under injected user-attribute
memory. We first validate that DRIFTLENS distinguishes content-free pragmatic noise from substantive
reasoning changes. Across four LLMs and 10 user-attribute categories, including age, occupation, and disability, user-attribute
memory induces medium-to-large
reasoning drift above each model's pragmatic-noise floor, even when final answers remain fluent, on-topic, and plausible. We then evaluate GRPO- and DPO-based post-training methods for reducing drift. Both reduce drift, but neither uniformly dominates; effects on downstream capability, helpfulness, and instruction following are model-and reward-dependent. These results suggest that
memory-induced
reasoning drift is a measurable and only partly mitigated failure mode of personalized
language models.
Read the full abstract ▾
All authors Xi Fang, Weijie Xu, Yingqiang Ge, Yuhui Xu, Stephanie Eckman, Chandan K. Reddy
Artificial Intelligence · Cross-listed from cs.CV
VisionAId: An Offline-First Multimodal Android Assistant for People with Visual Impairment, Featuring Personalized Object Retrieval
Cristian-Gabriel Florea and Stelian Spînu
Over 285 million people worldwide live with a visual impairment, for whom everyday tasks such as avoiding obstacles, locating personal belongings, recognizing familiar faces, or handling cash remain persistent obstacles to personal autonomy. Existing assistive applications are typically limited to recognizing predefined categories, depend heavily on cloud connectivity, or require dedicated hardware. We present VisionAId, an Android application that turns a commodity smartphone into a real-time visual assistant. The system integrates six on-device deep learning models (metric
monocular depth estimation, instance
segmentation, visual and facial
embeddings, face detection, and a custom banknote detector) running entirely through ONNX Runtime, with an optional cloud large
language model (Google Gemini Flash) used only for narrative scene description and automatic object labeling. A distinctive contribution is a few-shot pipeline for personal objects: the user photographs an object from several angles, and the system later locates that specific instance in the environment, guiding the user toward it with augmented-reality markers, spatial audio, and distance-proportional haptics. All feedback is
multimodal (Romanian
speech synthesis, voice commands, vibration). On a reference device (Samsung
Galaxy S21 Ultra), INT8 quantization reduces depth latency from ~1200 ms to ~491 ms, the custom banknote detector reaches an mAP@50 of 0.986, and metric depth is calibrated to below 1 cm of error within 3 m.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Understanding Agent-Based Patching of Compiler Missed Optimizations
Batu Guan, Zirui Wang and Shaohua Li
Compiler missed optimizations refer to cases in which compilers failed to optimize certain code. It takes many compiler developers' efforts to implement or patch such missed optimizations. In this paper, we present a systematic study of how well
agents patch compiler missed optimizations. We identify a significant challenge that patching a missed optimization requires more than just fixing the reported case, and instead requires generalizing to similar cases. We construct a
benchmark of real-world LLVM missed optimization issues and compare
agent-generated patches with patches from developers in terms of optimization scope. Our results show that coding
agents often optimize the given examples, but many generated patches either cover only part of the developer-intended scope or partially overlap with it; in some cases, they further generalize beyond the reference patch. We further introduce historical-knowledge augmentation techniques that leverage prior LLVM optimization pull requests through
retrieval and
distillation, showing that they improve developer-aligned generalization and yield practical benefits when applied to real-world IR.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
World Wide Models: Literary Tools for Cultural AI
Nina Begus
LLMs stage a new form of cultural encounter that is massive, automated, and monolingual. Literary disciplines have always negotiated cultural struggles with comparative reading of literature, narratological and poetic analysis, critical theory, world literature, and translation. These tools have now become indispensable for building culturally literate AI. The essay develops a layered framework toward more nuanced textual models and pluralistic interpretations of AI, emphasizing the natural intersections of literature and AI development, connecting current debates in critical theory with structural monolingualism, and suggesting a new application of world literature approaches to address global AI textuality through macrostructure, circulation, and untranslatability.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from stat.ML
Beyond Cultural Persona Bias: Response Geometry as a Measure for Language Models and People
Yuan Yuan
Researchers are increasingly prompting
language models with cultural personas so that they answer questionnaires as diverse human groups would. However, studies often report that these persona responses do not predict the models' behavior. We argue that whether the persona is Western or non-Western, the model's answers carry a cultural preference, and that this preference masks the variables that could predict its behavior. We examine the prompted preference at two levels: aggregate Big Five scores and response geometry, the correlation
matrix between dimensions within each respondent, represented as a symmetric positive-definite (SPD)
matrix. In DeepSeek-V3 and GPT-4o, when the item order is fixed, the prompted preference appears at both levels. Randomizing item order reduces it in the response geometry, while leaving it in the Big Five scores: the Big Five still separate the two personas at $95$–$97\%$, while response geometry falls to chance. In randomized administration, the response geometry still contains information about the respondent. In DeepSeek-V4-Flash, SPD features are associated with whether the same instance sorts Asian American public figures as “foreign” in a text IAT ($p = .047$), while the Big Five do not. In human studies conducted using randomized item order, the response geometry identifies people from test-retest sessions in $81$ – $85\%$, against chance $0.4\%$, and predicts sex and, weakly, age. In addition, SPD features also predict complex human behavior (e.g., cumulative GPA, $R^2 = 0.28$, permutation $p = .003$), where the Big Five do not.
Read the full abstract ▾