Artificial Intelligence · Cross-listed from cs.SD
Attractive and Repulsive Pattern Control in Sequence Generation
Francois Pachet
Variable-order Markov models preserve local symbolic syntax by adapting context length, but long continuations can enter recurring high-order "tunnels": repeated suffixes, locally periodic passages, or copied fragments longer than the formal Markov order. This paper introduces signed pattern control for variable-order Markov generation with BP-Regular sampling. A weighted recurrence automaton computes an activation R for a chosen family of target patterns, and belief propagation samples exactly from P_beta(x) proportional to P_0(x) exp(beta R(x)). Negative coupling makes the target patterns costly during sampling; positive coupling rewards the same patterns and turns them into controlled attractors. The target family may be mined online from overactive generated material, supplied by a score or style vocabulary, or designed as an experimental probe. The main experiments use the online homeostatic case, choosing patterns that become overactive in the sampling history. On six duration-bearing monophonic sources, including Bach and Telemann material, the negative branch reduces generated 8-gram self-reuse, increases the effective number of generated 8-grams, and increases coverage of training-supported 4-gram contexts while preserving substantial lower-order support. A pitch-sequence replication on five Weimar Jazz Database solos gives the same anti-reuse signature outside Baroque material. The same signed mechanism also provides a positive branch for probing attractor basins, phase transitions, and hysteresis in the underlying variable-order model.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from eess.AS
End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users
Allan Henry, Solange Rossato, Christian Graff et al. (+2 more)
Voice control offers an intuitive alternative to manual drone piloting, yet most existing systems rely on rigid command vocabularies that fail to handle the spontaneous, disfluent
speech of naive users. This paper addresses this gap by proposing an End-to-End Spoken
Language Understanding architecture for real-time human-drone interaction in French. Our model combines a frozen Self-Supervised Learning acoustic encoder with a lightweight LSTM-based classification head, augmented by a cross-modal knowledge
distillation objective that aligns acoustic representations with semantic
embeddings from a text teacher, without requiring transcription at inference time. We evaluate our approach on VoiceStick, a novel French corpus of spontaneous
speech collected during real teleoperation sessions with 29 nonexpert dyads. On simple voice commands, our best configuration achieves 93% accuracy at 7 ms inference latency, outperforming cascade baselines (79%, 202 ms) with a 29x speedup. On the full spontaneous
speech test set, our architecture reaches 82% accuracy, with crossmodal
distillation consistently improving robustness across all configurations. These results demonstrate that End-to-End architectures are not only feasible but preferable for spontaneous voice-guided
UAV teleoperation, combining semantic robustness, low latency, and calibrated confidence.
Read the full abstract ▾
All authors Allan Henry, Solange Rossato, Christian Graff, Sylvain Huet, Jose-Ernesto Gomez-Balderas
Artificial Intelligence · Cross-listed from cs.SE
Is Agent Code Less Maintainable Than Human Code?
Shaswat Patel, Betty Li Hou, Arun Purohit et al. (+4 more)
Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding
agents have demonstrated strong performance on single-issue tasks, it remains unclear how maintainable their code is when future
agents build on top of it, potentially leading to compounding downstream effects. We investigate how
agent code compares to human code in these maintenance settings, presenting CodeThread, a framework to construct controlled experiments from repository-level coding
benchmarks. Applying CodeThread to four frontier coding
agents and four
benchmarks, we find that
agents are less effective at resolving tasks when building on
agent code compared to human code, with task resolve rate drops of up to 13.1%. Regression analysis reveals that many traditional software engineering maintainability metrics do not explain this difference. Instead, the clearest signals are subtler behavioral differences in
agent code, such as changes to input validation and error handling, along with differences in downstream code size and task difficulty. These findings highlight the need to evaluate these systems not only by immediate task resolution but also by code maintainability, and point to potential sources of downstream errors introduced by
agent code.
Read the full abstract ▾
All authors Shaswat Patel, Betty Li Hou, Arun Purohit, Kai Xu, Jane Pan, He He, Valerie Chen
Artificial Intelligence · Cross-listed from cs.RO
THREAD: Trajectory Planning for Hybrid Rigid-Soft Manipulators with Environment-Aware Diffusion
Shivani Kamtikar, Pranav Asthana, Naveen Kumar Uppalapati et al. (+2 more)
Manipulation in confined environments, such as threading a manipulator through narrow apertures, remains a fundamental challenge, especially for conventional rigid
robots. Hybrid rigid-soft manipulators offer promise but face two compounding planning challenges: backbone shapes feasible in free space become infeasible under environmental contact, and planning rigid and soft segments independently ignores their kinematic coupling. We present THREAD, the first
diffusion-based trajectory planner for hybrid manipulation, learning a generative prior over physically realizable backbone trajectories conditioned on local environment geometry, with physics-inspired losses encoding
curvature, smoothness, and collision constraints jointly across both segments. Trained in simulation, THREAD achieves 92.4% task success with 5x fewer collisions than the strongest baseline. We show cross-embodiment real-world transfer with minimal online updates, successfully threading through apertures as small as 1.3x the soft segment diameter.
Read the full abstract ▾
All authors Shivani Kamtikar, Pranav Asthana, Naveen Kumar Uppalapati, Girish Krishnan, Girish Chowdhary
Artificial Intelligence · Cross-listed from cs.CL
CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks
Ashwin Vinod, Ying Ding and Elias Stengel-Eskin
LLM
agents in knowledge intensive question answering take
retrieval and
reasoning actions with incomplete knowledge about whether their current answer is uncertain, unsupported, or already complete. This produces two failure modes: committing to confident but unsupported answers, which hurts accuracy, and over-retrieving when the evidence in hand already suffices, resulting in wasted compute. To give
agents a more complete picture of the state space they are operating in, we introduce calibrated verifier telemetry (CalVerT), which augments the
agent's state with additional telemetry: a calibrated self-confidence score and a grounding verifier score. We show that CalVerT can improve
agents in both training-free and training-based settings. On four QA
benchmarks, we find that CalVerT raises F1 by triggering
retrieval in cases where
agents over-rely on parametric knowledge, while cutting redundant
retrieval in cases where
agents have sufficient context to answer. We show that CalVerT can augment existing QA frameworks without training. Moreover, CalVerT also improves trained systems: by simply augmenting an
agent's state with telemetry, we observe improvements after reinforcement learning, as compared to an
agent with identical training but no CalVerT telemetry.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
Tianqi Du, Qi Zhang, Yifei Wang et al. (+1 more)
Recently, world models have emerged as a promising paradigm for building intelligent
agents by learning predictive models that estimate future environment states conditioned on observations and actions. In particular, JEPA-style latent world models provide an efficient alternative to pixel space prediction by learning action-conditioned dynamics in compact representation spaces. However, existing latent world models typically rely on one-step prediction and must be recursively rolled out for long-horizon planning, which leads to compounding errors and a mismatch between training objectives and downstream planning tasks. To address this limitation, we propose Variable-length Latent World Models (VLWMs), a framework that learns to predict future latent states conditioned on action sequences of variable lengths. Instead of training only on one-step transitions, VLWMs directly model temporally extended dynamics, allowing the same predictor to evaluate action plans over different horizons. We further introduce a curriculum training strategy that progressively expands the action horizon, stabilizing optimization from short-range dynamics to long-range prediction. At test time, we design planning methods tailored to VLWMs to better exploit their variable-length predictive capabilities. Experiments on long-horizon control tasks show that VLWMs significantly improve latent space world models, achieving 13% average improvement over the state-of-the-art LeWM across different
datasets, with especially large gains on tasks requiring extended planning. These results suggest that VLWM provides a simple yet effective paradigm for improving long-horizon prediction and planning in latent world models.
Read the full abstract ▾
All authors Tianqi Du, Qi Zhang, Yifei Wang, Yisen Wang
Artificial Intelligence · Cross-listed from cs.GR
Scene-Level Heterogeneous Physics Simulation with 3D Gaussian Splats
Xiaoyang Liu, Shangzhe Wu and Kai Han
3D Gaussian Splatting (3DGS) has achieved state-of-the-art photorealistic rendering, but the representation gap prevents these assets from being physically interactive. Production-grade physics engines do not understand the 3DGS representation, while prior physics-for-3DGS methods are monolithic silos. These prior works are fundamentally limited, demonstrating only object-centric physics in isolated environments, such as on an ideal plane. They are incapable of interacting with complex static collision geometry or heterogeneous assets. We propose a novel framework that, for the first time, bridges this gap by enabling 3DGS assets to participate in scene-level, heterogeneous, multi-solver physical simulations. Our core contribution is a Representation Abstraction Framework that translates all diverse assets, including 3DGS, virtual meshes, and fluids, into a unified physical particle set. This abstraction is key to enabling complex behaviors, such as the non-rigid deformation of 3DGS assets, within a unified physics pipeline. This particle set, along with the static scene collision boundaries derived from scene capture, is processed within a solver-agnostic physics kernel. The physical results are then mapped back to drive each asset's specific visual reconstruction. This architecture unlocks capabilities impossible with prior art. We demonstrate complex, two-way interactions between deformable 3DGS assets, standard CG assets such as fluids and meshes, and large-scale captured static environments, showcasing realistic coupled phenomena that were previously unattainable.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.MA
Cohort Organized Learning: Clustering Through Agreement
Finn Henry O'Shea and Maria Elena Monzani
In this article we describe Cohort Organized Learning (CoOL), a method for clustering data without explicit distance or similarity computations. Herein, we will describe CoOL, derive the gradients determined by expectation maximization to train the networks, show how to monitor convergence during training and evaluate the clusters after training, and discuss a series of examples and use cases. We also discuss CoOL's limitations and future prospects on related tasks. Because CoOL uses neural networks to estimate the clusters, it can be used to cluster any data that can be made compatible and we illustrate this on vector data and images.
Read the full abstract ▾
Artificial Intelligence
Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents
Rajesh Mangannavar, Zachary Coalson, Pranay Dugar et al. (+1 more)
Translating natural-
language planning intent into verified plans is a longstanding challenge: people communicate goals in
language, while classical planners require formal PDDL specifications. Recent agentic frameworks bridge this gap by orchestrating a pool of specialized repair
agents inside a verifier-checked refinement loop, but the orchestrator at the centre is itself a prompted frontier LLM, paying a frontier-LLM API call at every refinement step. We present
HALO (Hybrid
Agent-Learned Orchestrator), which trains the orchestrator from refinement trajectories that an external verifier has certified as ending in valid plans, across 11 PDDL domains.
HALO pairs a small QLoRA-tuned policy with three hardcoded rules for trivially decidable selections, and operates over an expanded 21-
agent action space. Unlike approaches that
prompt a frontier LLM at every step or learn an orchestrator from sparse end-of-episode rewards, our key observation is that the verifier already provides strong guidance: every accepted trajectory is a sequence of demonstrably correct (state,
agent) decisions, directly usable as supervision. Across PlanBench, Natural Plan, and classical planning
benchmarks,
HALO matches or exceeds the GPT-5-mini prompted baseline on success rate, sits within three percentage points of the stronger Gemini-3-Flash prompted baseline, reduces orchestration cost by more than an order of magnitude (\$0.18 to \$0.004 per task against GPT-5-mini, roughly 45$\times$ cheaper; roughly 15$\times$ cheaper than Gemini-3-Flash), and cuts total LLM calls per episode by 40 to 50 percent.
Read the full abstract ▾
All authors Rajesh Mangannavar, Zachary Coalson, Pranay Dugar, Prasad Tadepalli
Artificial Intelligence · Cross-listed from cs.CV
HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning
Awais Rauf, Ahmed Hasssan and Greg Slabaugh
Understanding long
videos requires fine-grained perception and multi-step, higher-order
reasoning over complex, long-range spatio-temporal dynamics.
Vision-
language models (VLMs) encode
video frames into visual
tokens and attempt to perform both perception and multi-step planning latently, within a single forward pass. This coupled formulation, however, is bottlenecked by the LLM's limited capacity to discover and execute multi-step strategies in its latent representations. To address this bottleneck, we propose Hierarchical Programmatic Probing (HPP), a framework that decouples semantic perception from higher-order temporal
reasoning by reformulating long
video understanding as iterative, programmatic exploration of a hierarchically segmented
video. Specifically, a coding-capable LLM plans and executes a multi-step strategy in an interactive coding environment, probing the
video for information and invoking a VLM for localized perception on demand. To make probing tractable over long
videos, we introduce three components: information-density-aware hierarchical
segmentation, late-interaction semantic
retrieval, and structured probing functions for coarse-to-fine temporal localization. We validate HPP on LongVideoBench, which requires both fine-grained perception and long-range relational
reasoning, and show that decoupling the two via iterative programmatic probing yields substantial gains. Further results on EgoSchema, VideoMME, and MLVU demonstrate the effectiveness of our approach across diverse long-
video benchmarks.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
Zesen Liu, Zihan Zhang and Dongdong She
Summarization-based
prompt compression is increasingly used by LLM
agents to shorten long, distributed contexts, but it shifts the security boundary: filters inspect the pre-compression
prompt while the backend acts on a newly generated compressed context. We identify relinking, a compression-boundary vulnerability where the compressor behaves as a confused deputy, summarizing distributed, locally benign fragments into a complete malicious instruction. Unlike
prompt injection, relinking need not place an explicitly malicious payload in the source context. We show that relinking arises from summarization itself:
attention makes separated fragments jointly available, pre-training makes compatible fragments plausible to connect, and post-training favors compact backend-actionable summaries. We formalize the attacker-induced form as
adversarial relinking and present Relink, an automated DSL-based tool that splits malicious payloads into benign fragments while keeping the complete payload absent before compression. Across four long-context
agent benchmarks, Relink achieves 86.9% Relink Rate and Backend Action Rate versus 17.0% for clean-split controls. Existing defenses fail to reliably capture
adversarial relinking; our KBRA defense reduces residual Backend Action Rate to 0.0%.
Read the full abstract ▾
Artificial Intelligence
Entropy Objectives in Markov Decision Processes
S. Akshay, Raghav Goyal, Aditya Neeraje et al. (+1 more)
We consider the problem of synthesizing control policies that enforce a concentration property on the state distributions of a
stochastic system. We present a formalization of this problem in terms of synthesizing strategies for maintaining an
entropy-based objective in Markov Decision Processes (MDPs). We first show that even relaxed versions of this problem are complexity-theoretically hard. We then present a sound and (conditionally) relatively complete method to verify and synthesize strategies for such
entropy objectives. The main challenge is the non-linear nature of such objectives, and our approach addresses this by exploiting and combining ideas from convex duality and invariant synthesis. We also investigate the role of
memory and randomization in ensuring
entropy objectives. Finally, we implement our ideas to evaluate our approach empirically on a few illustrative
benchmarks.
Read the full abstract ▾
All authors S. Akshay, Raghav Goyal, Aditya Neeraje, Piyush Srivastava
Artificial Intelligence · Cross-listed from cs.CL
Denoising Iterative Self-Correction: Structured Verification Loops for Reliable LLM Reasoning
Shen Yin, David Ken and Joel Stremmel
Large
language models produce fluent but often incorrect multi-step
reasoning, and naive correction methods risk degrading already-correct answers. We introduce Denoising Iterative Self-Correction (DISC), a test-time procedure that treats verification question outputs as noisy measurements of where a solution may be corrupted. Using these signals, DISC progressively reduces errors across multiple verify-judge-correct passes, analogous to traditional iterative denoising. A binary judgment gate controls correction precision by blocking rewrites that would damage already-correct answers while the verifier and corrector together repair errors. We evaluate this trade-off using two paired diagnostics: an improvement-to-degradation ratio (precision) and a repair rate (recall). Across three
benchmarks (BIG-Bench Mistake, HotpotQA, GPQA Diamond) and four models, DISC dominates Chain-of-Verification and Self-Refine on the precision-recall trade-off, reaching 81.6% accuracy with 13x more improvements per degradation than Chain-of-Verification and 5x more than Self-Refine on BIG-Bench Mistake (Sonnet~4.5). On GPQA Diamond, we identify a capability floor below which judges acknowledge contradictions in evidence but cannot translate that recognition into a correction. We further show that cross-model role allocation – assigning verification and judgment to a model different from the generator – mitigates self-confirmation bias.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet et al. (+3 more)
AI
agents acting on behalf of users are constantly making decisions, and for users to trust their
agents, those decisions must align with what they actually want.
Privacy is an important
alignment problem for
agents: every message, post, or tool call an
agent makes is a contextual judgment about what is appropriate to share, with whom, and under which conditions. Because such judgments depend on social expectations and norms, human judgment does not merely label
privacy violations but also helps define them. While existing work relies on unreliable proxies for both training and evaluation, we place human judgment at the center of agentic
privacy alignment. We introduce PrivacyAlign, a
dataset of 1,350 samples with 3,516 detailed annotations from 599 unique annotators across diverse scenarios where current LLMs actually leak, and use it to ground both
alignment training and automated evaluation in human
privacy norms. Building on these annotations, we first show that conditioning LLM judges on human annotations and explanations for reference responses to the same
prompt makes their judgments more reliable. We then introduce annotation-conditioned reward modeling, which uses these annotations to score new responses during RL, and show that small open-weight
agents trained with this reward better align with human
privacy norms, with strong gains on PrivacyAlign and existing
privacy benchmarks for
agents.
Read the full abstract ▾
All authors Manveer Singh Tamber, Abhay Puri, Marc-Etienne Brunet, Perouz Taslakian, Jimmy Lin, Spandana Gella
Artificial Intelligence · Cross-listed from cs.CL
Clinical Term Extraction using Open-Source Small Language Models
Noah Marchal, William E. Janes, Mihail Popescu et al. (+1 more)
Clinical information for amyotrophic lateral sclerosis (ALS) care documented in unstructured clinical notes limits downstream analysis without extraction into structured formats. Open-source small
language models with few-shot prompting for detecting the presence of ALS-relevant clinical terms in patient documentation were evaluated without task-specific training data. The detection task targeted 17 categories spanning functional scores, respiratory measures, medications, and related clinical and non-clinical attributes. Clinical note content was normalized from JSON-encoded discharge summaries and processed with a
prompt template having structured JSON outputs. We compared 26 open-source models using aggregate, label-level, and manual-validation multilabel classification metrics. Manual validation showed that a regex rule baseline had higher overall micro-F1 and lower Hamming loss than any single SLM or TF-IDF baseline, while Qwen3-4B-Instruct-2507 was the highest-performing SLM by micro-F1. Model rankings varied by metric and label category, with the TF-IDF baseline showing high recall but low precision, some SLMs showing higher precision but lower recall, and Hammer2.1-7b showing strong performance for ALSFRS-R subscore detection. These findings support targeted hybrid extraction workflows rather than replacement of existing rule-based methods.
Read the full abstract ▾
All authors Noah Marchal, William E. Janes, Mihail Popescu, Xing Song
Artificial Intelligence · Cross-listed from cs.CL
TACO: Task-Aware Column Description Generation Using LLMs
Ting Cai, Rakesh R. Menon, Yiru Chen et al. (+8 more)
Generating accurate and informative column descriptions (e.g. "membership status of customers" for the column name "cust_mem") is essential for a wide range of downstream NLP tasks on tabular data, including NL2SQL, table question answering, and entity linking. This problem arises in enterprises, domain sciences, government data portals, and so on. Despite its importance, most real-world
datasets suffer from missing or cryptic documentation, often due to abbreviated column names or domain-specific jargon. Existing approaches largely rely on single-
prompt large
language models (LLMs), which struggle with three key issues: (i) inconsistent or incorrect handling of abbreviations, (ii) hallucinated or incomplete descriptions, and (iii) redundancy or vagueness that hinders downstream performance. We present TACO, a task-aware framework for automatic column description generation using LLMs. TACO introduces a three-step pipeline: (1) abbreviation expansion, which standardizes column names; (2) description generation, which produces initial semantic descriptions enriched with synonyms and search-oriented keywords; and (3) description revision, which refines these outputs using simulated downstream tasks. In addition, we investigate human-in-the-loop extensions and release new evaluation
datasets for entity linking and schema enrichment. Extensive experiments across public and proprietary
datasets show that TACO consistently outperforms existing methods, improving downstream task performance by up to 32%.
Read the full abstract ▾
All authors Ting Cai, Rakesh R. Menon, Yiru Chen, Zifan Liu, Yuan Tian, Fei Wu, Anudeep Chimakurthi, Prashanthi Ramamurthy, Sunav Choudhary, Kun Qian, Yunyao Li
Artificial Intelligence · Cross-listed from cs.LG
Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers
Vatsal Ananthula and Adarsh Kumarappan
Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal
reasoning. We propose verifier-coupled
reasoning, a framework that inserts inline claims into
reasoning traces and trains an auxiliary consistency head to predict programmatic verifier outputs from rationale-span hidden states. The central finding is a gap between decodability and faithfulness: consistency training reliably makes verifier information decodable from rationale representations, but decodability does not guarantee faithful generation. In LeanCheck (formal
theorem proving), rationale-only and proof-only pooling achieve perfect directional separation under counterfactual conflict. In KataGo (Go engine), commentary spans encode 10-way win-rate buckets at 81% accuracy. Yet in a code setting, the model achieves 98.6% coupling while its generated explanations remain unfaithful: fluent prose with correct structured claims, but describing unrelated
algorithms; a controlled pretrained-vs-from-scratch comparison shows the gap is not capacity-driven. Synthetic activation patching confirms causal influence (73-89% vs. 31% baseline), FEVER reveals that evidence-only pooling isolates genuine evidence sensitivity at the cost of raw accuracy, and per-claim analysis shows that consistency loss disproportionately benefits fine-grained claims over binary ones. These results establish that consistency losses are effective diagnostics and representation-shaping tools, but not sufficient conditions for faithful
reasoning.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
Tianyou Wang, Anson Lei, Joe Watson et al. (+1 more)
Imitation learning has emerged as a powerful paradigm for learning visuomotor policies, but its generalisation and stability are limited by the scale and quality of demonstration data needed. A promising direction is to leverage more abundant but heterogeneous data sources, which differ in action space and often lack action labels altogether. Existing co-training approaches that combine heterogeneous data sources rely on heuristic and hand-engineered
alignment techniques. In contrast, we argue that action representations should be grounded in prediction: actions that produce the same effect on the environment should share the same representation, regardless of their sources. To this end, we instantiate this principle by using a grounded latent-action world model (GLAM), a pair of generative models with a shared latent action space across data sources that is grounded by predicting future observations consistently across sources. This latent action space is used to train downstream behavioural cloning (BC) policies which map observations to latent actions and decode them back to
robot actions, providing a paradigm for learning from heterogeneous data. Empirically, we demonstrate that GLAM successfully learns an aligned latent action space that facilitates action transfer across data sources with and without action labels. Across five manipulation tasks in simulation and in the real world, GLAM-aligned policies significantly outperform BC baselines and prior latent-action methods, achieving an average of +48% improvement in task success rate with the same data-scarce setting.
Videos and code are available at https://viccccciv.github.io/glam/.
Read the full abstract ▾
All authors Tianyou Wang, Anson Lei, Joe Watson, Ingmar Posner
Artificial Intelligence · Cross-listed from cs.SD
Improving Text-to-Music Generation with Human Preference Rewards
Yonghyun Kim, Junwon Lee, Haiwen Xia et al. (+2 more)
We describe our entry to the efficiency track of the Academic Text-to-Music (ATTM) Grand Challenge at ICME 2026. Beyond the challenge protocol's FAD-CLAP and CLAP score, we add a learned human-preference reward from TuneJury, a twin pairwise ranker trained over open music-preference
datasets. The reward serves both as a training-time conditioning signal and as a sample-selection criterion. The pipeline combines five engineering decisions on a 120M-parameter FluxAudio-S backbone, four at training time and one at inference: (i) training-time reward conditioning that doubles as an inference-time CFG axis, (ii) a sweep over five score-conditioning architectures, where training and inference use different variants, (iii) expert iteration on the top decile, (iv) a short preference-tuning pass (CRPO) for audio-text
alignment, and (v) inference post-processing via joint CFG, source separation, and loudness normalization. Per-stage decomposition on 100 Song Describer
prompts shows training-time reward conditioning as a functional conditioning axis, expert iteration as the dominant contributor, the preference-tuning pass adding only noise-level gain, and the inference-time score scalar already saturated by the end of the chain.
Read the full abstract ▾
All authors Yonghyun Kim, Junwon Lee, Haiwen Xia, Yinghao Ma, Chris Donahue
Artificial Intelligence
Hallucination as Context Drift: Synchronization Protocols for Multi-Agent LLM Systems
Carson Rodrigues
Multi-
agent LLM systems routinely produce hallucinated outputs that cannot be explained by model deficiencies alone. A significant class of these failures arises not from model incapacity but from context drift: the divergence of internal knowledge states between concurrent
agents. When
agents enter a collaborative task with mismatched or stale representations of shared world state, their joint
reasoning produces contradictions that manifest as
hallucination. We define the Context Divergence Score (CDS), a lightweight scalar metric quantifying knowledge-state discrepancy between
agent pairs across spatial, temporal, and task dimensions, and propose the Shared State Verification Protocol (SSVP), which lets
agents periodically exchange compressed state summaries and flag high-divergence conditions before joint
reasoning. We evaluate SSVP across two domains (multi-
agent travel and software project planning) using Claude Haiku. In controlled experiments (n=30 per condition, travel; n=10, software) across 8 scenarios, naive full-broadcast synchronization increases
hallucination rate by 34% above the no-sync baseline (HR: 0.658 vs. 0.492, p=0.0022, d=1.18), a contamination effect from propagating erroneous
agent states. SSVP avoids this failure mode while showing modest, consistent reduction (HR: 0.463, d=0.30) and achieves significantly lower
hallucination than full-broadcast (p=0.0005, d=1.47) using 58% fewer API calls. The contamination effect does not replicate in the software domain, where all conditions converge to low HR (<0.2), confirming it is specific to tasks where one erroneous shared belief cascades across evaluation dimensions. Our results reframe
hallucination mitigation as a distributed systems problem and establish context synchronization as a first-class primitive in multi-
agent LLM design.
Read the full abstract ▾
Artificial Intelligence
ChainWorld: Composing Long-Horizon Desktop Workloads from Atomic OSWorld Tasks
Vincent Siu, Manasi Sharma, Dawn Song et al. (+3 more)
Computer use
agents are evaluated almost exclusively on atomic desktop tasks, but realistic desktop work requires sustaining state across multiple objectives. We study this gap with ChainWorld, which composes atomic OSWorld tasks into long horizon desktop workloads through directional compatibility search while preserving the source evaluators. The resulting workload contains 347 chains of length two to four and compares two renderings of the same task sequence. In single turn evaluation, all tasks are presented together in one
prompt. In multi turn evaluation, tasks are revealed one at a time. Across four current computer use
agents, maximum chain completion is 31%. Multi turn evaluation improves completion for three models, but both protocols remain challenging. The two protocols also expose different failure profiles. Single turn failures concentrate on artifact precision, while multi turn failures more often reflect session management problems such as fragmented progress and later turn disengagement.
Read the full abstract ▾
All authors Vincent Siu, Manasi Sharma, Dawn Song, Daniel Yue Zhang, Chenguang Wang, Ying Liu
Artificial Intelligence · Cross-listed from cs.LG
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta et al. (+1 more)
Large
language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations. We test that claim under a budget-matched, multi-seed protocol on eight PMLB tabular
benchmarks, comparing an LLM advisor (LLM-OptFlow) against four classical baselines (random search, Optuna-TPE, Gaussian-process
Bayesian optimization, and successive halving) over one shared search space, with paired tests and bootstrap 95% CIs across 8 x 5 = 40 (task, seed) units. The finding is cautionary. The advisor's strong first point is not an LLM output at all: like prior LLM-HPO systems the loop is seeded with a fixed default configuration, evaluated before any model call, which alone reaches 88.7% mean best-CV, identical to within 0.01 pp across all seven advisor models tested. The LLM's own proposals add only +0.40 pp of cross-validation accuracy over that seed and nothing on held-out test (LLM-Default = -0.01 pp, p = 0.92). When the same seed is granted to classical search, the apparent lead collapses: against seeded random search it leads by +0.20 pp at 2 evaluations, is tied by 5, and is behind by 12 (-0.37 pp). Without the seed, classical search ties the advisor by 12 evaluations and beats it by 40 (+0.6 to +0.8 pp, p <= 1e-4). Two LLM-specific behaviors survive: a single-task exploration failure (vehicle), and a rule-based confidence filter that removes ~33% of wasted compute without changing accuracy. The recommendation is deflationary: on tabular HPO, seed classical search with a sensible default; an LLM advisor adds no measurable generalization benefit and is overtaken within a handful of evaluations. We release the harness and a script that reproduces every statistic.
Read the full abstract ▾
All authors Carson Rodrigues, Oysturn Vas, Isaiah Abner DCosta, Nithish Kumar Prabhakaran
Artificial Intelligence
Counsel: A Meta-Evaluation Dataset for Agentic Tasks
Sashank Pisupati, Henry Broomfield, Eujeong Choi et al. (+5 more)
As agentic systems tackle increasingly complex multi-step tasks, evaluating their trajectories presents a major bottleneck - human annotation of a single trajectory on popular agentic
benchmarks can take hours, making it difficult to scale evaluations for measuring performance or curating training data. This has driven widespread reliance on automated approaches such as LLM-as-a-judge (LLMJ) to critique
agents at the process and outcome-levels at scale, however, the soundness of LLMJ critiques often goes unmeasured. Here, we introduce Counsel, the first public
dataset of meta-evaluations for agentic tasks. Counsel consists of process-level critiques from open-weight LLMJs on two
agent benchmarks: tau-bench (customer support
agents) and DA-Code (coding
agents), and human meta-evaluations of these critiques. Human annotators label critiques on each flagged error as "spot on", "correct location but poor
reasoning", or "should not have flagged", achieving reliable inter-annotator agreement (Krippendorff's alpha of 0.78). The resulting
dataset stratifies LLMJ critiques by human
alignment across both error location within a trajectory and
reasoning quality, serving as valuable data to calibrate, improve, or train LLMJs for
agents. Comparing open-weight judges, we find that more capable judge models and more
reasoning effort both enabled improved human agreement, with the strongest judge reaching ~88% agreement on location and ~65% on
reasoning. Counsel is generated using open-weight models and is permissively licensed for broad community use, which we hope will enable rigorous study and improved
alignment of LLM-based evaluators for agentic systems.
Read the full abstract ▾
All authors Sashank Pisupati, Henry Broomfield, Eujeong Choi, Antonia Calvi, Charlie Wang, Roman Engeler, Max Bartolo, Patrick Lewis
Artificial Intelligence · Cross-listed from cs.CV
A DVDrive Approach for doScenes Instructed Driving Challenge
Zijian Fu, Xiangyang Chu, Mengshi Qi et al. (+3 more)
Instruction-conditioned trajectory prediction is an emerging problem in autonomous driving, where a model predicts the future ego trajectory not only from visual scene context and historical motion, but also from a natural-
language maneuver instruction. This paper presents our submission to the doScenes Instructed Driving Challenge, built upon OmniDrive, a
vision-
language-action driving
agent with 3D perception,
reasoning, and planning capabilities. We adapt OmniDrive to the doScenes setting by training it on instruction-annotated nuScenes scenes and generating a 6-second ego trajectory represented by 12 future waypoints. To improve multi-view visual grounding, we further introduce a DVPE-style divided-view perception module into the OmniDrive perception head. Instead of attending globally to all camera features, the proposed module groups query features and image
tokens into divided local view spaces and performs visibility-aware cross-
attention within each view. This design reduces irrelevant cross-view interference and helps the model better align
language instructions with local driving-relevant visual evidence. The code is publicly available at: https://github.com/feel12348/doscenes-omnidrive.
Read the full abstract ▾
All authors Zijian Fu, Xiangyang Chu, Mengshi Qi, Huadong Ma, Guanghao Zhang, Wei Li
Artificial Intelligence · Cross-listed from cs.CV
Cross-Modal Corroboration for Annotation-Free Wildlife Monitoring
Bharath Pillai, Varun Viswapriyan, Christopher Stewart et al. (+2 more)
Scaling wildlife monitoring for real-world conservation deployments requires automated analysis of smart sensors that operate under severe annotation scarcity. We propose leveraging expert knowledge of species activity patterns as an annotation-free validation signal for
multimodal monitoring pipelines. We operationalize agreement as the
alignment of independently derived hourly activity curves both with each other and with published behavioral priors-a three-way convergence that rules out shared-data confounds and
dataset-internal correlation as alternative explanations. Our
vision pipeline combines zero-shot species detection via BioCLIP 2, sliced inference to handle deployment-constrained camera positioning, and geometry-based geographic localization from camera trap imagery. Our acoustic pipeline detects species vocalizations via a fine-tuned classifier. We validate the pipeline on a breeding herd of Milu deer and demonstrate that both modalities independently recover activity patterns consistent with known deer behavioral ecology with minimal manual annotation. The framework applies to species detectable in both visual and acoustic modalities for which behavioral priors are documented in the literature, suggesting a practical path toward self-validating wildlife-monitoring pipelines at conservation scale.
Read the full abstract ▾
All authors Bharath Pillai, Varun Viswapriyan, Christopher Stewart, Tanya Berger-Wolf, Jenna Kline
Artificial Intelligence · Cross-listed from cs.LG
The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning
Lucas Fagan, Michele Tarquini, Ali Shehper et al. (+6 more)
Mathematical search problems present a unique challenge for Reinforcement Learning (RL) due to vast search spaces and sparse rewards. In previous works, the Andrews-Curtis (AC)
conjecture was established as an illustrative example of such problems. In this work, we identify a critical structural barrier in the AC landscape: a "Two-Hump" distribution, where problem instances are either trivially solvable or effectively impossible, with a scarcity of intermediate "hard-but-solvable" instances required for effective learning. We tackle this challenge through two primary avenues: novel data generation techniques to populate the difficulty gap, and significant algorithmic enhancements including the introduction of supermoves and
Transformer-based architectures. We demonstrate substantial performance improvements over previous baselines, and release new comprehensive
benchmark datasets including AC-19 (125,192 AC-trivial presentations of varying difficulty with length at most 19) and AC-1M (1,136,154 hard AC-trivial presentations of length at most 30), the first large-scale, publicly available
datasets of this kind.
Read the full abstract ▾
All authors Lucas Fagan, Michele Tarquini, Ali Shehper, Maksymilian Manko, Angus Gruen, Coco Huang, Giorgi Butbaia, Davide Passaro, Sergei Gukov
Artificial Intelligence · Cross-listed from cs.LG
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
Bonan Wang, Letian Tao, Bin Shuai et al. (+7 more)
Deep reinforcement learning is pivotal for closed-loop autonomous driving yet remains constrained by severe bottlenecks in sampling efficiency. Standard parallel sampling mitigates this but suffers from the straggler effect, where the premature termination of a single environment necessitates a synchronized batch re-initialization, leading to suboptimal sample utilization and prohibitive re-initialization latency. To address this, we propose FAST, a synchronous parallel framework tailored for closed-loop simulation. Specifically, FAST employs Dynamic Parallel Sampling
Alignment (DPSA) to maintain vectorization synchronization by extending terminated episodes via virtual continuation, thereby decoupling the sampling loop from individual terminations. By dynamically triggering global truncation based on the termination rate of parallel clips, FAST effectively eliminates the bottleneck of premature resets without sacrificing data diversity. Furthermore, to strictly preserve theoretical consistency, we incorporate a Scaled Mask-Padding Optimization (SMPO) that leverages validity masking and adaptive loss normalization to nullify the bias from auxiliary padding data. Empirical evaluations demonstrate that FAST achieves at least a 1.78 times wall-clock speedup over the single-clip baseline while preserving statistical unbiasedness.
Read the full abstract ▾
All authors Bonan Wang, Letian Tao, Bin Shuai, Jiaxin Gao, Wenxin Zhao, Wei Xiong, Kehua Sheng, Bo Zhang, Yang Guan, Shengbo Eben Li
Artificial Intelligence · Cross-listed from cs.CV
The Unreasonable Effectiveness of VLMs for Zero-shot Procedural Mistake Detection
Serdar Ozsoy, Lars Doorenbos, Federico Spurio et al. (+2 more)
Procedural mistake detection is important for quality control and user assistance across many disciplines. Recent work in this field has achieved significant gains by using the
reasoning capabilities of
Video-
Language Models (VLMs) as components within multi-stage pipelines, which consist of separate modules for supervised temporal action
segmentation, error detection, and explainability. Consequently, they remain dependent on tailored training
datasets and require task-specific training, limiting their wider applicability. To remedy this, we introduce zero-shot procedural mistake detection and propose a unified Zero-shot Procedural Mistake detection (ZeProM) framework that jointly solves procedural mistake detection and temporal action
segmentation with a single pre-trained VLM. By evaluating our framework on two canonical mistake detection
benchmarks, EgoPER and CaptainCook4D, we find that ZeProM can perform these tasks successfully, while approaching, or even outperforming, the performance of fully supervised methods. For instance, we achieve a 4.4 point improvement in EDA and a 2.0 point improvement in F1@.5 on average over all five EgoPER tasks compared to the strongest supervised methods. Overall, our results show the potential of unified methods for procedural mistake detection, and we hope this will steer the field away from highly complex pipelines and toward more generally applicable solutions.
Read the full abstract ▾
All authors Serdar Ozsoy, Lars Doorenbos, Federico Spurio, Gianpiero Francesca, Juergen Gall
Artificial Intelligence
Composing Verifiable Conceptual Models via Building Blocks: Towards Design-Time Verification of Agentic AI Workflows
Noe Y. Flandre, Alexander C. Nwala and Philippe J. Giabbanelli
Agentic AI systems orchestrate multiple LLM-based
agents through workflow architectures that coordinate decisions, tools, and external actions. While current platforms emphasize runtime safeguards, little support exists for verifying workflows during system design. From a Modeling & Simulation perspective, this gap is analogous to composing conceptual models without verifying whether their building blocks interact coherently. We propose a design-time verification approach that models agentic workflows as compositions of reusable building blocks and checks their compatibility through twelve structural rules. We implemented these rules in a software prototype and evaluated them using two openly released
datasets: 48 workflows with known design flaws and 168 variants that preserve workflow logic but alter graph structure. Results show that our verifier reliably detects violations even when flawed designs are obscured through structural transformations such as splitting tasks between
agents. Future works could combine our verification with community repositories of building blocks to compose safe agentic workflows.
Read the full abstract ▾
Artificial Intelligence
AI Alignment From Social Choice Perspectives
Daniel Halpern, Evi Micha, Ariel D. Procaccia et al. (+3 more)
Alignment from human feedback uses human judgments about model outputs to steer the behavior of
language models after pretraining. When those judgments reflect conflicting views of desirable behavior, the learned objective becomes an aggregate determination of what the model should prefer. We survey recent work that has studied this aggregation problem through the lens of social choice theory. We illustrate how the social choice perspective helps identify failure modes in the feedback aggregation layer and reveals a broader design space for handling disagreement in explicit and principled ways.
Read the full abstract ▾
All authors Daniel Halpern, Evi Micha, Ariel D. Procaccia, Benjamin Schiffer, Itai Shapira, Shirley Zhang