Artificial Intelligence · Cross-listed from cs.LG
AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision
Brent Kong, Tejas Ram and Tony Yue Yu
AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervision. We find that vanilla AlphaZero achieves strong play across both domains but cannot preserve the exact trajectories required for optimal play: in Connect Four, it fails to maintain the optimal line of play, while in Chomp, it fails to consistently restore the $g=0$ invariant. On rectangular Chomp boards, multi-frame inputs alone do not remove this gap. Nevertheless, AZAL substantially improves oracle consistency across multi-seeded full-game traces and sampled-state evaluations. On Chomp, AZAL reaches perfect full-game oracle consistency on 10x11 and high but not complete consistency on 9x10; on Connect Four, AZAL improves oracle-match rate and delays the first oracle mistake, but does not reach perfect play.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation
Sijia Gu, Noor Nashid and Ali Mesbah
While autonomous coding
agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where
agents prematurely terminate tasks and systematically avoid complex programmatic logic, resulting in inadequate code coverage. Currently, mitigating this premature termination requires continuous human-in-the-loop supervision. This heavy reliance on human intuition creates a bottleneck that negates the efficiency gains of automated generation. We propose SCATE, a framework for adaptive, automated supervision of coding
agents that replaces human intervention during test generation. By formulating supervision as a contextual bandit problem, SCATE learns to select the most promising testing actions based on the current coverage and class testability metrics, maximizing coverage gains while minimizing wasted generation effort. Our empirical evaluation demonstrates that SCATE integrates seamlessly with different coding
agents. When applied to GEMINI-CLI, it achieves 32.3% higher line coverage and 30.9% higher branch coverage than the
agent-only baseline. A comparison with CLAUDE CODE confirms the framework dynamically adapts its policy to optimize each
agent's unique strengths. SCATE also consistently outperforms state-of-the-art non-agentic approaches across all metrics.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
The Patchwork Problem in LLM-Generated Code
Viraaji Mothukuri and Reza M. Parizi
LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed. The root cause is frequently structural rather than logical. A generated endpoint references configuration keys never declared in the project, an import targets a package that does not exist in any registry, or a new route omits the authentication guard applied to every sibling endpoint. Each patch is locally valid but globally incoherent, and standard CI toolchains rarely surface these failures. As LLM-powered coding tools see widespread adoption, this blind spot poses a growing risk to software quality. We call this the patchwork problem. This paper formalizes structural coherence as consistency invariants over graph representations of repository artifacts, including import, call, dependency, configuration, schema, resource, control-flow, and routing graphs, and introduces an eight-category failure taxonomy distinguishing defects specific to LLM generation from those merely amplified by it. We present a hybrid verification framework that delegates to mature static analysis tools where they already excel and deploys purpose-built detectors for cross-cutting invariants underserved by existing toolchains, targeting provable constraint violations rather than heuristic pattern matching. Empirical evaluation across two frontier models under four prompting strategies reveals that the vast majority of structural failures evade type checking, testing, and SAST entirely, and that failure patterns diverge qualitatively between models in ways that challenge model-agnostic mitigation strategies. External validation on real-world AI-generated repositories confirms that these failures are not artifacts of controlled experimentation but are prevalent wherever LLMs write code with minimal human oversight.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding
Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya et al. (+5 more)
Vision-
language-action models (VLAs) inherit semantic capabilities from pretrained VLMs, yet large-scale post-training on
robot data and architectural modifications can reshape the backbone so extensively that it becomes difficult to isolate what the VLM contributes to control. Directly converting pretrained VLMs into VLAs with minimal architectural change offers a more transparent path to understanding how VLM capabilities transfer across model scales. The core obstacle is output-distribution mismatch: predicting actions as bare numeric
token sequences moves generation away from the VLM's pretrained
language distribution, degrading the capabilities we seek to preserve. To address this, we propose CLAP (Causal
Language-Action Prediction), which prepends each numeric action sequence with a natural-
language action description, causally conditioning precise action-
token prediction on a
language-action plan without modifying the backbone architecture. With only 4-5 hours of training, 2B CLAP achieves 90.8% on LIBERO (+14.9 pt over VLA-0) and improves robustness on LIBERO-PRO under
language, object, and spatial perturbations. Ablations attribute the gains to action-grounded
language semantics, and on a real UR5e
robot 2B CLAP reaches 60% success against 15% for matched VLA-0. We release CLAP at 0.8B, 2B, and 4B as an open-weight, multi-scale compact VLA family from a single VLM lineage, enabling controlled analysis of VLM-to-VLA capability transfer.
Read the full abstract ▾
All authors Yuri Ishitoya, Jeremy Siburian, Masashi Hamaya, Haruto Suzuki, Kuniaki Saito, Toshihiko Fukushima, Cristian C. Beltran-Hernandez, Mai Nishimura
Artificial Intelligence · Cross-listed from cs.CV
MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs
Hantao Zhang, Jinru Sui, Ed Li et al. (+2 more)
Recent
benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model. We introduce MultiView-Bench, a diagnostic
benchmark expressly designed to evaluate multi-view integration for holistic 3D scene comprehension. Unlike existing
datasets that focus on pixel-level mapping or camera-relative
navigation, MultiView-Bench requires models to decouple object positioning from transient perspectives and ground them in a fixed global coordinate system. This capability serves as a prerequisite for VLMs before being deployed for downstream tasks such as mechanical part assembly. Our systematic evaluation of frontier VLMs reveals consistent failure modes: strong performance on 2D planar relations from a single image, but marked difficulty with 3D spatial relations and with aggregating information across views. We further identify biases in VLMs, such as struggles with unconventional axis directions and sensitivity to object colorways and texture variations. Acknowledging these limitations, we propose ViewNavigator, which uses active viewpoint selection and evidence fusion to improve four base models by 12.3–20.0 percentage points under a six-image cap matching the fixed-view baseline; budget-extended gains are model-dependent and reach 27 percentage points for GPT-5.
Read the full abstract ▾
All authors Hantao Zhang, Jinru Sui, Ed Li, Dirk Bergemann, Zhuoran Yang
Artificial Intelligence
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi et al. (+12 more)
AI
agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal
benchmarks largely focus on simple problems that finish within minutes and are evaluated only by their final outcome. This setup overlooks intermediate progress and partial solutions, yielding sparse reward signals and an incomplete picture of
agent capability. We introduce Long-Horizon-Terminal-Bench, a terminal
benchmark of 46 long-horizon tasks spanning nine categories, including experiment reproduction, software engineering,
multimodal analysis, interactive games, and scientific computing. Each task follows a Terminal-Bench-style setup with a reference solution or simulation engine, but is further decomposed into fine-grained graded subtasks. This design enables dense intermediate rewards and partial credit, allowing evaluation to capture not only whether an
agent reaches the final goal, but also how far it progresses on open-ended workflows. Tasks in Long-Horizon-Terminal-Bench typically require hundreds of episodes and minutes to hours of execution, stressing long-horizon planning, long-context management, and iterative debugging rather than one-shot problem solving. We evaluate 15 frontier models and find that
agents consume on average 9.9M
tokens per task, with roughly 231 episodes and 85.3 minutes of execution time per run, making Long-Horizon-Terminal-Bench more demanding than prior terminal-based
benchmarks. Even the strongest tested model achieves 15.2% pass@1 at a partial-reward threshold of 0.95 and 10.9% at a perfect-reward threshold of 1.0, while the mean pass rate across models is 4.3% and 1.7% under the two thresholds, respectively. These results reveal headroom for improvement. We further analyze failure modes and error patterns, and release Long-Horizon-Terminal-Bench to support future progress on long-horizon terminal
agents.
Read the full abstract ▾
All authors Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Zhichao Liu, Xiyang Wu, Anhao Li, Chengsong Huang, Ergan Shang, Yue Yu, Ninghao Liu, Lichao Sun, Haotao Mi, Leowei Liang
Artificial Intelligence · Cross-listed from cs.LG
NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision
Berkay Anahtarci
Large
language models increasingly provide labels, evaluations, and feedback for tasks specified in natural
language. When a specification admits multiple readings but the supervision channel does not reveal which is operative, additional labels reduce sampling error without resolving the resulting identification problem. We introduce Natural
Language PAC (NL-PAC), a framework that uses a fixed model's thresholded decoding law to define admissible labels and candidate targets. The probability that multiple labels are admissible equals the diameter of the pointwise-admissible target class, and under target-blind supervision every learner incurs worst-case risk of at least half this diameter, at every sample size; the exact randomized minimax risk over this class is attained by a data-independent strategy. Finite-sample confidence bounds make these quantities certifiable from held-out unlabeled inputs. In a frozen Qwen~2.5–3B audit, one prespecified
prompt yields a positive model-relative certificate, whereas a paraphrase and exact-rule controls yield zero. A held-out bridge audit finds that supplied candidate reading clauses fail the admissibility condition needed to transfer the certificate to coherent readings. The guarantee is specific to the audited model,
prompt, threshold, and input distribution; extending it to human interpretations requires external validation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
Ning Liu, P Aditya Sreekar, Kalle Kujanpää et al. (+11 more)
Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM
agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce. We present Eluna, a production-deployed agentic system for reliable SOP execution. Eluna is a graph-guided, multi-
agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-
agents, each with persistent code execution and live data access. To meet production latency and accuracy needs, we use asymmetric episodic
distillation where a strong teacher is improved through episodic error
memories, then a smaller student is fine-tuned on the corrected trajectories with
memory stripped, internalizing corrections without inference-time overhead. On a 13-task
benchmark and two production applications, our fine-tuned models match or exceed their teacher, beat all larger off-the-shelf baselines, and reach 94% expert agreement on the ticket processing application.
Read the full abstract ▾
All authors Ning Liu, P Aditya Sreekar, Kalle Kujanpää, Zhaoxuan Zhu, Kaiwen Liu, Chuanneng Sun, Jorge Marchena Menendez, Matthew Bales, Tianyu Yang, Shahnawaz Alam, Rose Yu, Baoyuan Liu, Kristina Klinkner, Shervin Malmasi
Artificial Intelligence · Cross-listed from quant-ph
A Novel Parallel QCNN Architecture with Efficient Classical Simulability
Lawrence Nguyen and Hiu Yung Wong
This work presents a study of an implementation of a novel
Quantum Convolutional Neural Network (QCNN) for binary classification of images from the Modified National Institute of Standards and Technology (MNIST)
dataset. Using a novel architecture inspired by previous QCNN and classical convolutional neural network (CNN) implementations, we use a hierarchical partitioning approach to implement a QCNN
circuit that can be approximated and simulated efficiently on a classical machine for a large problem. First, the original image is partitioned such that each process handles a smaller portion of the image, which is encoded into independent states. Then, these partitions merge and combine, resulting in states that contain information from both partitions while halving the number of processes. After repeating this until one process remains, we reduce the dimensionality of the state until a single
qubit remains for measurement. Using this approach, we can use multiple processes in parallel to simulate a large QCNN program without the need for exponentially growing hardware requirements as the number of
qubits increases. In our work, we use this scheme to train a 128-
qubit model, which is impossible to run on any classical supercomputer without the novel architecture. We also explore the impact of this new model architecture on prediction accuracy by training it to perform binary classification on the MNIST
dataset with a small number of
qubits, and comparing it to a model without partitioning. Our initial findings show that partitioning images into smaller sub-images with this architecture does not degrade the model's performance and sometimes even improves it, likely because it reduces the Barren plateaus issue in the partitioning process.
Read the full abstract ▾
Artificial Intelligence
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
Maureese Williams and Dymitr Nowicki
Large
Language Model (LLM)
agents have shown promise in multi-step planning tasks, but existing approaches like LATS (
Language Agent Tree Search) and ReAct rely heavily on LLM inference during planning, leading to high computational costs and
stochastic behavior. We present GATS (Graph-Augmented Tree Search), a planning framework that combines systematic UCB1-based tree search with a layered world model to eliminate LLM calls during inference while achieving superior planning performance. Our three-layer world model integrates: (L1) exact symbolic action matching, (L2) statistics learned from execution logs, and (L3) LLM-based prediction for unknown actions. On synthetic planning tasks with branching paths and dead-ends, GATS achieves 100% success rate compared to 92 % for LATS and 64% for ReAct. On a comprehensive stress test spanning 12 challenging scenarios – including coding workflows, web
navigation, and long-horizon tasks – GATS maintains 100% success while LATS drops to 88.9 % and ReAct to 23.9%. GATS requires zero LLM calls per task during planning (vs. 37 per task for LATS) and produces deterministic plans with zero variance across runs. Our results demonstrate that systematic search with learned world models can substantially outperform LLM-guided exploration for
agent planning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning
Sunshine Jiang, John Marangola, David Zhang et al. (+6 more)
Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but such jitter only yields rollouts close to the original. Escaping a weak policy often requires global perturbations that action noise cannot produce. Large
language models (LLMs) and
vision-
language-action (VLA) models offer a pathway: they condition the policy on a natural
language prompt, and since the rollout follows from it, modifying the
prompt induces global changes. The challenge is finding
prompts that induce useful global changes. With a weak policy that rarely succeeds, reward is too sparse to select on. Our idea is to refine
prompts from the rollouts themselves: a
vision-
language model (VLM) reasons over the rollout
video, diagnoses how the policy responded, and rewrites the
prompt to elicit better behavior next time. This procedure resembles posterior sampling, a classical RL exploration framework, at the level of
prompts: the VLM maintains an implicit distribution over useful
prompts and updates it from observed rollouts. We call this strategy
Prompt-Driven Exploration (PDE). Across manipulation and
reasoning tasks, PDE enables RL to learn successful policies even from zero-reward starts, and improves sample efficiency more broadly. Our website is available at https://xinyunsunshine.github.io/
prompt-rl.
Read the full abstract ▾
All authors Sunshine Jiang, John Marangola, David Zhang, Raghuram Kowdeed, Ruiyang Luo, Nitish Dashora, Richard Li, Pulkit Agrawal, Zhang-Wei Hong
Artificial Intelligence · Cross-listed from q-bio.QM
TheBioCollection: Unified Pre-Training Scale LLM Corpus for Biology
Hyunjin Seo, Hyeon Hwang, Gyubok Lee et al. (+7 more)
The push toward large
language models for biology (BioLM) has created a need for training corpora that can endow models with a genuine understanding of biology. However, existing biological resources, such as molecular databases,
protein repositories, genomic annotations, single-
cell atlases, and pathway databases, are scattered across heterogeneous formats and remain unorganized into a cohesive corpus for
language model training. We present TheBioCollection, a 52.6B-
token pre-training-scale corpus that converts these disparate resources into a unified, training-ready form spanning small molecules,
proteins, genomic sequences,
cells, and pathways. Beyond consolidating existing data, TheBioCollection enriches each record with tool-computed biological properties and introduces new instruction tasks for capabilities that current corpora barely cover. We pair the corpus with TheBioCollection-Eval, a matched suite probing recognition, generation, and prediction across molecular,
protein, genomic, cellular, and cross-domain settings. Holding the base
Gravity-16B-A3B architecture fixed, training on TheBioCollection more than doubles its overall score on TheBioCollection-Eval with gains in every domain, while leaving general linguistic ability nearly intact.
Read the full abstract ▾
All authors Hyunjin Seo, Hyeon Hwang, Gyubok Lee, Jay Shin, Jimin Park, Taesoo Kim, Sanghoon Lee, Hongjoon Ahn, Sungjun Han, Sangwon Jung
Artificial Intelligence · Cross-listed from cs.CV
OpenCoF: Learning to Reason Through Video Generation
Xinyan Chen, Ziyu Guo, Renrui Zhang et al. (+2 more)
Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent
video generation models offer a
reasoning path distinct from previous Chain-of-Thought (CoT):
reasoning can unfold through temporally connected frames, known as Chain-of-Frame (CoF)
reasoning. However, existing
video generators are primarily trained on general
video corpora, still lacking diverse supervision and dedicated designs for CoF
reasoning. To address this gap, we introduce OpenCoF, a framework comprising the OpenCoF-17K
dataset, a
reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned
video model for studying whether diverse temporal supervision improves CoF behavior. Across four
video reasoning benchmarks, Wan-CoF achieves considerable gains over the Wan2.2-I2V-A14B baseline. Building on this, we empirically explore more advanced designs for CoF capabilities, i.e., equipping the model with visual and textual
reasoning tokens. This mechanism respectively captures low-level visual cues and high-level semantic priors for spatial and temporal
reasoning. Through performance comparisons and
attention analysis, we examine how these
tokens contribute across model depth, denoising steps, space, and time. Our results suggest that stronger
video reasoning requires both broad temporal supervision and explicit mechanisms for organizing intermediate
reasoning state. We open-source the
dataset, model, and code to facilitate future research on
reasoning-oriented
video generation.
Read the full abstract ▾
All authors Xinyan Chen, Ziyu Guo, Renrui Zhang, Dongzhi Jiang, Hongsheng Li
Artificial Intelligence
Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation
Yifan Zhou, Qihao Yang, Yan Li et al. (+14 more)
Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current
benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), a
benchmark for scientific lineage
reasoning and lineage-grounded idea generation. IG-Bench is organized around the IdeaGene framework: each paper or proposal is represented as a set of minimal, typed, evidence-grounded Idea Genome objects, and a GenomeDiff aligns these objects to record inheritance, mutation, loss, external import, and novel insertion under six operational evolutionary dynamics. The
benchmark contains 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise GenomeDiff records across 10 scientific domains. It supports two evaluations. IG-Exam (42 task types, 1,029 instances) tests closed-form lineage
reasoning across Idea Genome abstraction, inheritance tracing, evolutionary
reasoning, and lineage verification. IG-Arena evaluates generation with a lineage-conditioned Population-
Evolution Score(PES), asking whether a proposal can be inserted as a coherent descendant of a given lineage population: it should inherit the right Idea Genome objects, vary meaningfully from nearby work, and offer selection value for future research. Experiments on 14 LLM-based scientists expose a compositional bottleneck. The strongest system reaches only 27.3% exact accuracy on lineage
reasoning, and structured lineage context reshuffles system rankings rather than helping every participant uniformly.
Read the full abstract ▾
All authors Yifan Zhou, Qihao Yang, Yan Li, Donggang Li, Xiru Hu, Hokin Deng, Ziyang Gong, Xuanyi Zhou, Huacan Wang, Xiangchao Yan, Wanghan Xu, Wenlong Zhang, Shaofeng Zhang, Yue Zhou, Yifan Yang, Zhihang Zhong, Xue Yang
Artificial Intelligence · Cross-listed from cs.LG
SLORR: Simple and Efficient In-Training Low-Rank Regularization
David González-Martínez and Shiwei Liu
Low-rank factorization is widely used to compress neural networks, but modern models are often not naturally amenable to aggressive factorization without significant accuracy loss. Existing training-time low-rank regularizers can improve compressibility, but they often require SVDs of large weight
matrices, modify the model architecture (introducing additional trainable parameters), or rely on stateful cached quantities. To address these limitations, we introduce SLORR, a simple, stateless, and architecture-preserving framework for in-training low-rank regularization, instantiated with two main variants based on the Hoyer sparsity metric and the
nuclear norm. SLORR directly regularizes the original weight
matrices using GPU-friendly approximations for the forward and backward passes of the regularizers, for which we provide approximation guarantees. We first evaluate SLORR on ImageNet-1K across short-horizon continued training of ResNet-50, ViT-B/16, and ViT-L/16, and pretraining of ResNet-18, where SLORR induces compressibility while introducing less than 8% training overhead. We further evaluate SLORR-Hoyer in LLM pretraining at 135M and 560M scales: SLORR-trained compressed models preserve performance substantially better than unregularized models while adding less than 1% average training overhead.
Read the full abstract ▾
Artificial Intelligence
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
Kristina Schaaff, Quintus Stierstorfer and Valerie Hekkel
In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, we examine usage patterns across gender, age group, study cluster, degree, and study mode. To date, existing research on educational chatbots has largely relied on comparatively small samples and self-reported survey data, while large-scale evidence on actual usage behavior remains limited. Our findings show that Syntea is already embedded in the study routines of many learners, but that usage differs across demographic and structural contexts. By identifying these patterns, our study provides an empirical basis for the further development of AI-based learning support and contributes a large-scale analysis of educational chatbot usage in higher education.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
Duen Horng Chau, Donghao Ren, Fred Hohman et al. (+1 more)
While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional
embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally. This graph encodes the data
manifold in its original high-dimensional space, before the distortion that UMAP's 2D projection introduces. We demonstrate the untapped potential of this internal representation, showing how standard graph
algorithms applied to this graph enhance data sensemaking: (1) PageRank identifies representative data points, (2) k-core decomposition reveals dense core regions versus sparse periphery, and (3) clustering coefficient detects tight-knit neighborhoods with highly-similar data points. Through quantitative and qualitative evaluation on MNIST and Fashion MNIST, we show that these graph-based analyses are not only practical but also competitive with or complementary to purpose-built methods (e.g., k-medoids for exemplar selection, HDBSCAN for density-based clustering).
Read the full abstract ▾
All authors Duen Horng Chau, Donghao Ren, Fred Hohman, Dominik Moritz
Artificial Intelligence
AUTOPILOT VQA: Benchmarking Vision-Language Models for Incident-Centric Dashcam Understanding
Siddharth Damodharan, Radhika Gupta, Ali Alshami et al. (+2 more)
Recent advances in
Vision-
Language Models, Large
Language Models, and
Multimodal Large
Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question answering
benchmark for dashcam
video understanding. The
dataset evaluates different systems through structured questions designed around real-world driving incidents and near-incidents. The
benchmark covers diverse safety-relevant categories, including weather and lighting conditions, traffic environment, road layout, road surface state, signage, involved entities, accident occurrence, impact location, and avoidability-related
reasoning. By requiring models to answer grounded questions about both contextual scene properties and event-level incident details, AUTOPILOT-VQA moves beyond object recognition toward temporally grounded, safety-aware
reasoning. The
dataset is released as part of the AUTOPILOT CVPR 2026 competition and provides a standardized
benchmark for assessing the reliability of autonomous driving systems in different scenarios. Our
benchmark support developments for more interpretable, robust, and safety-conscious
vision-
language systems for real-world autonomous driving.
Read the full abstract ▾
All authors Siddharth Damodharan, Radhika Gupta, Ali Alshami, Ryan Rabinowitz, Jugal Kalita
Artificial Intelligence
Workflow as Knowledge: Semantic Persistence for LLM-Mediated Workflows
Emanuele Quinto, Carlo Andrea Rozzi and Francesco Zanitti
Large
language model (LLM) applications increasingly use explicit workflows for tool use,
retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but
language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow definitions, workflow instances, inference records, context snapshots, and dependency relations are represented as persistent knowledge objects in a shared knowledge substrate. Its central semantic distinction is between derive and infer: derive is deterministic computation over available state; infer is mediated LLM judgment under declared context and executor-controlled capability policy. The result is a preliminary conceptual account of semantic persistence: workflows do not merely produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and reviewable knowledge objects, while formal transition semantics remain future work.
Read the full abstract ▾
Artificial Intelligence
The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs
Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg et al. (+4 more)
Post-Training Quantization has become widely used to compress large
language models to make them deployable on resource-constrained devices. However, the evaluation of quantization methods mainly uses accuracy and perplexity, which cannot capture the behavioral changes in the quantized variants. In this work, we propose Correctness Agreement, a decision-level metric that can measure the intersection of correct predictions between the base model and its quantized variant. We use this metric across multiple models and quantization bit levels (8-bit to 2-bit), and we find that the base and quantized variants usually have a shift in behavior even when accuracy and perplexity are preserved. In order to explain this effect, we study the effect of quantization on the structure of the
attention weights using statistical and distributional measures. The results reveal a breakpoint at low bit widths and show that query and key projections are more sensitive to quantization than the value and output projections. These results prove the illusion of equivalency between the base and quantized models and inspire behavioral evaluation beyond perplexity and accuracy for quantization methods.
Read the full abstract ▾
All authors Baha Rababah, Shahzeb Qamar, Lorenz Sparrenberg, Rafet Sifa, Murat Kantarcioglu, Cuneyt Gurcan Akcora, Carson K. Leung
Artificial Intelligence · Cross-listed from cs.CL
Trusting sovereign language models as scientific instruments: evidence from Portugal's AMALIA
Manuel Pita
National
language models are becoming publicly funded epistemic infrastructure. Public ownership, linguistic specialization, and open weights create a presumption of trustworthiness. Such an instrument, built by and for a
language community, looks like the natural choice for measuring what that community says and values. Whether such a model validly measures anything is untested at release. The evaluation of LLMs as measurement instruments is typically task-specific and stops at agreement with human coders. Agreement cannot distinguish an LLM instrument that measures a construct from one that reaches matching codes through surface correlates. We audit the presumption on a favourable case: AMALIA, Portugal's publicly funded 9B model, coding the moral foundation of authority in European Portuguese. The recovery gap operationalizes the audit: decompose the codebook into its theory-defined clauses, recombine them through the theory's explicit rule, and measure how much of the original
prompt's performance the stated theory reproduces. In a pre-registered, out-of-sample study on a transcreated (English to European Portuguese) corpus, AMALIA agrees with trained coders within six points of open models eight to thirteen times its size. Yet, the recovery gap shows that only about half of coding performance on authority can be attributed to the theory. A larger
multilingual LLM closes the recovery gap on the same corpus, suggesting the shortfall lies in the annotator model, not the corpus or its translation. Sovereignty earns operational and performance trust; epistemic trust requires calibration – and the audit method is inexpensive, and portable across models,
languages and tasks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Pose-to-Biomechanics: Bridging 3D Human Pose Estimation and Biomechanical Attribute Prediction
Ayda Eghbalian and Kevin Desai
Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable. However, most pose
estimators remain optimized for
geometric keypoint accuracy, while many real-world applications in rehabilitation, sports science, ergonomics, and clinical movement analysis require biomechanical quantities that describe how the body moves, loads, and activates. In this work, we propose BioModule, a lightweight plug-in temporal
transformer that attaches downstream of any 3D pose
estimator and predicts biomechanical attributes from standard 17-joint 3D skeletons. BioModule is
estimator-agnostic and requires no modification of the upstream pose model, enabling existing pose
estimators to be extended toward physically interpretable motion analysis. To train and evaluate BioModule, we construct a large-scale aligned
dataset pairing Human3.6M
video and 3D keypoints with the biomechanical label space of Human3.6Mplus. We establish and verify anatomical correspondence between coordinate systems of the two
datasets, enabling frame-accurate cross-modal supervision. Using this aligned supervision, BioModule predicts biomechanical quantities. We further
benchmark BioModule across seven state-of-the-art 3D pose
estimators, providing the first systematic analysis of how upstream pose estimation quality propagates to downstream biomechanical prediction fidelity. The results position BioModule as a compact, modular bridge between
vision-based pose estimation and biomechanically meaningful human motion analysis.
Read the full abstract ▾
Artificial Intelligence
Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
Yifan Wu, Lizhu Zhang, Yuhang Zhou et al. (+5 more)
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action
agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study
memory as an active intervention mechanism rather than passive
retrieval. A separate
memory agent runs alongside an unmodified action
agent, updating a structured
memory bank from the recent trajectory and deciding whether to inject a
memory-grounded reminder or remain silent. The module is plug-and-play with frontier action
agents and existing
agent harnesses. Across Terminal-Bench 2.0 and $\tau^2$-Bench, it improves pass@1 for both weaker and stronger action
agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on $\tau^2$-Bench. Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general
retrieval. As an early step toward open-weight
memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench.
Read the full abstract ▾
All authors Yifan Wu, Lizhu Zhang, Yuhang Zhou, Mingyi Wang, Bo Peng, Serena Li, Xiangjun Fan, Zhuokai Zhao
Artificial Intelligence · Cross-listed from cs.SE
ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation
QiHong Chen, Aaron Imani and Iftekhar Ahmed
Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing
retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains. We propose ProjAgent, a repository-level code generation system that introduces procedural similarity as an explicit
retrieval signal. ProjAgent decomposes the target function into intermediate
reasoning steps and employs an agentic workflow to retrieve repository functions that exhibit similar procedural behavior at each step. The retrieved procedural context is integrated with conventional semantic
retrieval to construct a richer repository context for code generation. ProjAgent further incorporates a conservative static-analysis feedback loop that iteratively repairs generated code using compiler and static-analysis feedback. Evaluated on REPOCOD, ProjAgent achieves 41.14% Pass@1, outperforming existing
retrieval-based baselines. These results demonstrate that procedural similarity is an effective and previously unexplored
retrieval dimension for repository-level code generation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
A Practical Investigation of Training-free Relaxed Speculative Decoding
Guoxuan Xia, Luka Ribar and Paul Balanca
Speculative decoding accelerates sampling from an autoregressive LLM by using a faster auxiliary model to draft
tokens which are then verified in parallel by the LLM. Standard speculative decoding is lossless: its rejection and resampling steps exactly preserve the LLM's sampling distribution. Recent work argues that relaxing this strict guarantee can yield further speed-ups, controlled capability-speed trade-offs, or even capability gains. We practically investigate training-free relaxed speculative decoding techniques, unify existing approaches within a shared framework,
benchmark them on contemporary settings, and distil takeaways and empirical findings for practitioners. Important takeaways include: relaxation can require considerable capability evaluation unlike lossless speculative decoding, and many relaxed approaches rely on a drafter that is a good
language model, making them unsuited for lightweight dedicated multi-
token-prediction drafters.
Read the full abstract ▾
Artificial Intelligence
SolarChain-Eval: A Physics-Constrained Benchmark for Trustworthy Economic Agents in Decentralized Energy Markets
Shilin Ou, Yifan Xu and Luyao Zhang
As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy
markets, autonomous
agents may improve
market utility, but may also exploit invalid physical data, create artificial liquidity, and produce unstable governance decisions. Therefore, we propose SolarChain-Eval, a physics-constrained
benchmark for evaluating trustworthy economic
agents. It formulates
market governance as a Gymnasium-compatible Markov Decision Process, where
agents make hourly decisions. SolarChain-Eval evaluates each policy across multiple dimensions, including
market utility, physical safety, slippage, action smoothness, spatial
fairness, and auditability. To support agentic evaluation, SolarChain-Eval incorporates an LLM-based Planner/Auditor layer. The Planner defines episode-level action bounds and audit rules, while the Auditor reviews and revises high-risk actions. All interventions are recorded through structured logs, including trigger signals, proposed actions, revised actions, and audit rationales. Experiments with static, random, myopic, RL, and RL+LLM policies reveal a clear utility-safety trade-off. RL
agents improve
market utility but can still produce unsafe behavior. When the physics penalty is removed, reward-maximizing
agents exploit invalid generation and increase artificial liquidity. The LLM Planner/Auditor improves auditability and mitigates selected risks, but it cannot fully compensate for a misspecified reward function. These results indicate that trustworthy agentic AI evaluation requires both physical constraints and transparent intervention traces. We release data and code as open access on GitHub for replicability.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search
Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao et al. (+8 more)
Large
language model (LLM)-based web search
agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks. A single ReAct-style
agent is constrained by one long trajectory and limited context, making it difficult to handle depth and coverage simultaneously. Existing multi-
agent systems improve search coverage through parallel execution and aggregation, but still exhibit clear limitations in recursive depth, collaboration adaptability, and evidence-grounded expansion. We propose WebSwarm, a progressive recursive delegation framework that jointly constructs task decomposition, recursive expansion, and
agent collaboration during inference. WebSwarm dynamically instantiates agentic search nodes, each coupling a local objective with a search mode that specifies how the node should organize search and collaboration. Each node can either solve its objective itself or further delegate child nodes; after solving, it returns evidence and results upward, enabling parent nodes to further expand, revise, or aggregate the search process. To guide this process, WebSwarm first probes how task-relevant information is organized on the web to ground subsequent node expansion, and reuses process-level experience across homogeneous sibling nodes. Experiments on BrowseComp-Plus, WideSearch, DeepWideSearch, and GISA show that WebSwarm consistently outperforms single-
agent and multi-
agent baselines on deep, wide, and interleaved deep-and-wide tasks. Further analyses of ablation, task difficulty, web tool efficiency, and model generalization explain WebSwarm's effectiveness and provide insights for multi-
agent search systems.
Read the full abstract ▾
All authors Xiaoshuai Song, Liancheng Zhang, Kangzhi Zhao, Yutao Zhu, Zhongyuan Wang, Guanting Dong, Jinghan Yang, Han Li, Kun Gai, Ji-Rong Wen, Zhicheng Dou
Artificial Intelligence
Formal Mechanisms for Market Stability in Self-Interested Agent Societies: A Marketplace Simulation Study
Eugene Ng Yi Sheng and Bingquan Shen
Self-interested
agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such
agents to maintain
market stability, and how resilient those mechanisms are to
adversarial attack. We instantiate the research question as a multi-
agent marketplace simulation where 18 LLM
agents (DeepSeek-V3) with complementary production specialties must trade within a constrained social network to obtain utility. We conduct two experimental phases: (1) a mechanism comparison across eight conditions under progressive troll injection over 200 rounds, identifying Mediation as the top-performing mechanism; and (2)
adversarial red-teaming of Mediation using iteratively
prompt-optimised LLM-driven trolls, finding that the best attack (v6) reduces honest-
agent utility by 13.3% but cannot collapse the
market. Mediation enables recovery even under sustained
adversarial pressure. We define
adversarial robustness as a mechanism's ability to sustain positive honest-
agent utility under optimised attack, and find that Mediation is robust: it can be bent but not broken.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
Ali Larian, Qian Lin, Chang Zong Wu et al. (+1 more)
As autonomous
agents are increasingly deployed across diverse operational contexts, aligning their behavior with human intent demands reward functions that remain robust to such changes rather than overfitting to any single environment. Inverse reinforcement learning (IRL) provides a principled way to infer such objectives from human feedback. However, existing analyses of optimal teaching approaches for IRL focus on single-environment, demonstration-only settings, leaving underexplored how heterogeneous feedback modalities and environment dynamics jointly constrain reward functions that generalize across multiple environments. Because demonstrations in one MDP entangle reward information with that environments specific structure, the resulting rewards frequently fail to generalize when the
agent is deployed in a new setting. We first analyze how different feedback modalities constrain rewards, showing that, in the unlimited-data regime, comparisons impose strictly stronger global constraints than other modalities. Beyond this theoretical analysis, we introduce a hierarchical machine teaching
algorithm for reward learning that operates across multiple MDPs. The
algorithm first greedily selects informative environments that expose complementary reward constraints, then strategically queries low-cost feedback within those environments. Empirically, our method achieves substantially lower regret and stronger generalization to held-out environments than uniform teaching baselines under identical feedback budgets, demonstrating the importance of multi-environment, multi-modal teaching for learning dynamics-robust reward functions.
Read the full abstract ▾
All authors Ali Larian, Qian Lin, Chang Zong Wu, Daniel S. Brown
Artificial Intelligence · Cross-listed from cs.CL
UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing
Xinlong Zhao, Dongsheng Liu, Hengyu Zhao et al. (+9 more)
As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large
Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refinement methodologies face significant limitations in quality, efficiency, and reliability: Rule-based approaches are constrained by fixed heuristics and struggle with instance-level variations; LLM-based approaches improve quality but fail to meet the efficiency and reliability requirements of large-scale data processing. To address these challenges, we propose UltraX, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing. Specifically, UltraX builds a reliable program-supervision generation pipeline. In this pipeline,
dataset-adaptive
prompt optimization first guides an expert LLM to produce high-quality end-to-end refined texts, and Line
Alignment Mapping and Dynamic Context Replacement then convert original-refined text pairs into structured program supervision. Meanwhile, UltraX improves supervision quality and stabilizes the training distribution with low-confidence example filtering and ratio-controlled sampling by operation combination. During inference and execution, it normalizes and validates model outputs through sliding-window prediction, global operation aggregation, and systematic post-processing, improving the stability and reliability of large-scale execution. Experiments show that UltraX achieves the highest average performance across all corpora and also matches or surpasses baselines with fewer training
tokens, demonstrating stronger data efficiency and refinement reliability.
Read the full abstract ▾
All authors Xinlong Zhao, Dongsheng Liu, Hengyu Zhao, Zixuan Fu, Zheng Wang, Jie Cai, Jie Zhou, Qiang Ma, Xuanhe Zhou, Xu Han, Yudong Wang, Zhiyuan Liu