Artificial Intelligence · Cross-listed from cs.LG
Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
Khang Luong, Dinh Thai Son, Hoang Ta et al. (+2 more)
We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a single bit indicating whether the sampled reward belongs to that set. We consider a distribution-free finite-variance setting with arm-wise localization, where direct empirical mean estimation is no longer available and clipping becomes unavoidable. We first formulate a time-uniform 1-bit mean-estimation primitive based on randomized threshold queries and a clipped tail-integral identity. We then embed this primitive into candidate-challenger best-arm identification
algorithms. A fixed-clipping
algorithm gives a simple anytime $(\epsilon,\delta)$-PAC guarantee, while a phased adaptive-clipping
algorithm matches the clipping level to the current resolution and yields a gap-adaptive sample complexity. We also prove a $K$-arm worst-case information-theoretic lower bound showing that the logarithmic penalty caused by finite-variance 1-bit feedback is intrinsic. This bound matches the leading dependence of the phased
algorithm up to lower-order $\log\log$ factors.
Read the full abstract ▾
All authors Khang Luong, Dinh Thai Son, Hoang Ta, Hung The Tran, Tuan Quang Dam
Artificial Intelligence · Cross-listed from cs.CL
When History Fails to Become Experience: Action Calibration in Language Agents
Jingyu Liu, Zhiwen Wang, Yuxin Jing et al. (+2 more)
Language agents should draw on prior attempts and environmental feedback to improve subsequent decisions within the same task. However, providing additional interaction history can sometimes reduce task success, suggesting that
agents do not consistently use this information effectively. To investigate this limitation, we examine how
agents use history. We find that history improves task completion overall, yet much of this benefit persists even when past actions are shuffled. Disrupting the correspondence between actions and observations causes only a modest decline in task success. We therefore hypothesize that
agents do not reliably connect past actions with their outcomes when deciding how to proceed. To test this hypothesis, we explicitly label each returned observation as the outcome of the preceding action. This simple annotation improves task success and reduces next-action repetition without introducing new environmental information. Building on this insight, we introduce a learned calibrator that explicitly reassesses past actions and selectively records experience to guide subsequent decisions, improving task success beyond outcome labeling alone.
Read the full abstract ▾
All authors Jingyu Liu, Zhiwen Wang, Yuxin Jing, Huanyu Zhou, Yong Liu
Artificial Intelligence
Dynamic LLM Routers are Often Misguided
Sam Wang, Julia White, Sahibzada Allahyar et al. (+3 more)
Dynamic LLM routers promise to cut inference costs by sending each query to the cheapest model that can answer it correctly. We analyze six commercial routers across 14 settings on a diverse
benchmark spanning eight task categories, finding that none of them outperforms a router that randomly selects between two well-chosen models at matched cost. Some underperform by more than 10 percentage points. We trace this gap to four patterns prevalent across routers: difficulty blindness, length reversal, semantic matching, and roster suboptimality. We show that the first three are what the standard objective rewards: cost-accuracy Pareto efficiency on realized costs favors escalating moderately hard queries over the hardest ones, shorter queries over longer ones, and routing by a query's source over its difficulty. We also argue that the two assumptions that would justify large rosters, model granularity and model specialization, do not hold empirically. We propose an alternative evaluation methodology that does not reward these patterns, and as a proof of concept, we design a simple two-model router that avoids all four. Nevertheless, its gain over random routing is limited, because a well-chosen roster leaves little to route.
Read the full abstract ▾
All authors Sam Wang, Julia White, Sahibzada Allahyar, Dhruv Atreja, Urchade Zaratiana, Kelton Zhang
Artificial Intelligence · Cross-listed from cs.CV
Correcting Guided Diffusion Trajectories with Spectral Alignment
Gihoon Kim and Taesup Kim
The practical success of conditional image generation hinges on fine-grained differences in condition
alignment and visual fidelity. Classifier-free guidance (CFG) is central to this success, but its lack of an explicit criterion makes it difficult to assess whether the guided trajectory is progressing as intended. To address this gap, we show that spectral
alignment provides a principled criterion for understanding guidance behavior and improving guided
diffusion sampling through adaptive correction. Our analysis identifies the spectra of intermediate states as an indicator of consistency with the expected spectral
evolution of the forward process. Based on this observation, we introduce Spectral Correction Guidance, a method that corrects deviations from an analytic reference spectrum during sampling. The proposed method is training-free and applicable across
diffusion backbones and conditional generation tasks without modifying the underlying model. Experiments demonstrate consistent gains in preference-based metrics over baseline guidance methods in text-to-image generation and improved generation quality over CFG on ImageNet. These improvements persist across a range of guidance scales and with fewer denoising steps. Our analyses and ablations provide insight into guidance behavior and how the proposed method affects generation quality.
Read the full abstract ▾
Artificial Intelligence
On the Chain-of-Thought Monitorability of Looped Language Models
Han Wang, Ishwar B Balappanawar and Huan Zhang
Chain-of-thought (CoT) monitoring provides a promising approach for detecting undesirable model behavior. Looped
language models (LoopLMs) repeatedly apply shared
transformer layers, increasing effective computational depth and enabling additional latent computation without increasing model size. However, the effect of looped architectures on CoT monitorability remains largely unexplored. In this work, we provide the first systematic evaluation of CoT monitorability in LoopLMs. We study two complementary settings: (1) varying the loop depth within the same LoopLM family to isolate the effect of additional recurrent computation, and (2) comparing LoopLMs with non-looped
language models matched by parameter size,
transformer-layer count, or effective depth to study whether LoopLMs are less monitorable. Across eight tasks from MonitorBench and both standard and stress-test settings, we observe task-dependent reductions in CoT monitorability under stress tests on specific Logic/Science/Engineering Cue Answer tasks, while other tasks exhibit weaker or qualitatively different trends. Our diagnosis suggests that these declines are not fully explained by task difficulty, verification pass rate, or generated
token length; qualitative examples further suggest changes in how deeper-loop models explicitly use or attribute provided cues. Our cross-model comparison finds no evidence that LoopLMs are systematically less monitorable than non-looped
language models matched on size or depth. Overall, our results suggest that deeper loop depth can reduce CoT monitorability in some tasks under stress tests, but looped
transformer architecture alone does not necessarily imply lower monitorability.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
Jiaxin Zhang, Xiangyu Peng, Qinglin Chen et al. (+3 more)
Reinforcement learning for long-horizon
agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the
agent's belief at action time invisible to the gradient. We introduce Prospective Hindsight (PH), a self-calibrating training principle that augments any retrospective base method with a signal derived from the gap between the
agent's prospective prediction (before feedback) and the retrospective evaluation (after feedback). This per-rollout surprise identifies samples where the
agent's self-model is most inaccurate and amplifies their gradient contribution through a stop-gradient surprise-weighted advantage. Since the prospective predictor shares parameters with the policy, the two co-evolve, progressively shifting focus to the
agent's remaining blind spots. We connect this principle to a privileged-information gap and show that minimizing the surprise residual provides a descent pathway on the
agent's miscalibration rate; calibration thus emerges as a byproduct of optimization rather than from an added objective. On single-turn verifiable tasks and a multi-turn personal-
agent task (under GRPO, on-policy
distillation, and their combination), PH improves both task performance and calibration, with consistent gains across model scales. Notably, the dominant miscalibration mode shifts structurally between regimes, overconfident failures in single-turn, underconfident successes in multi-turn, yet the same training principle addresses both successfully.
Read the full abstract ▾
All authors Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Yu Li, Hiroaki Hayashi, Chien-Sheng Wu
Artificial Intelligence · Cross-listed from cs.CL
TPBench: A Turning-Point Benchmark for Dialogue Compression
Minji Park, Seunghyun Yoon and Hyuk Lim
A compressor can keep the facts of a dialogue and still drop the turn that changed them. A user corrects a price, reverses a choice, or adds a constraint. We call this failure turning-point eviction. One overall retention score hides it, because that score mixes what the user first wanted with what the user wants now. We introduce TPBench, which evaluates three complementary information targets at shared nominal retention budgets. P1 asks for the user's initial goal. P2 asks for the current value of a slot the user revised. P3 asks for both, in dialogues with a late annotated slot update. The current-value answers come from the human dialogue-state annotations of MultiWOZ and SGD. The initial-goal answer is the first sentence of the first user turn. Neither requires new crowdsourcing. The probe-specific evaluations rank compression methods differently. On the joint probe at a retained fraction of 0.30, every tested compressed method remains below full context with the main Llama reader. Deleting the turn that carries the update sharply lowers current-value accuracy, while deleting one matched irrelevant turn leaves it unchanged. A Mistral reader repeats the P2/P3 rankings and the joint-probe gap. Current-value recovery is tested on an additional corpus, LongMemEval-KU, and on Chinese RiSAWOZ: full context has the highest accuracy, and recency has the highest compressed-method mean in both evaluations.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis
Peilin Yang, Xiaoyu Liu, Jian Sun et al. (+1 more)
Vision-
language models such as CLIP exhibit strong semantic generalization, but remain limited in fine-grained visual perception. A recent work named KUEA presents a natural remedy by finetuning the image encoder under the supervision of the
vision-centric DINOv2 to align their kernel
matrices element-wisely, while regularizing the
embeddings to remain close to the pretrained visual encoder for preserving image-text semantics in CLIP. However, we show that diminishing the role of the
alignment loss to DINOv2 does not necessarily degrade its fine-grained visual performance, suggesting that the kernel-
matrix discrepancy may be insufficient for further visual representation enhancement, motivating us to revisit the
alignment formulation. In this work, we present a novel perspective to characterize representation
alignment on feature subspaces through Kernel Canonical Correlation Analysis (KCCA), which maximizes the projection correlations. In optimization, we derive an efficient end-to-end training scheme upon KKT conditions, avoiding the
eigenvalue problem in KCCA. Further, we extend our method into a 3-view formulation, i.e., 3vKCCA, in which the projections from the pretrained text encoder are also incorporated under a unified optimization framework for joint
alignment. With CLIP ViT-L/14 on ImageNet-1K, our 3vKCCA improves the MMVP-VLM accuracy from 17.8 to 25.9, substantially outperforming the existing methods, and meanwhile maintains zero-shot image–text
retrieval performance.
Read the full abstract ▾
All authors Peilin Yang, Xiaoyu Liu, Jian Sun, Qinghua Tao
Artificial Intelligence
Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State Planning
Qinchuan Cheng, Zhantao Gong, Pengzhan Sun et al. (+2 more)
Egocentric
videos capture how people carry out everyday activities, yet testing an
agent requires evaluating the consequences of actions it chooses itself. We introduce Ego2World, a
benchmark that turns annotated cooking activities into executable planning environments under partial observation. Its compiler links source steps and objects to symbolic action rules, persistent world states, and explicit task conditions, so researchers can execute an
agent's proposed actions and check their outcomes. World state and
agent belief are maintained separately, enabling controlled studies of planning and information reuse across continuing tasks. Evaluating six planners on 105 tasks shows that accepted operations often leave task goals unmet. Execution traces and condition checks distinguish interrupted runs, partial attainment, and completed execution without goal attainment. In a separate paired Qwen-Plus study, persistent belief improves action validity by 4.15 percentage points and reduces visual-query attempts by 90.27%, with higher
token use and no detected completion gain. Ego2World provides a reusable testbed for tracing how planning and
memory choices affect execution, observation demand, and task attainment, connecting recorded human activity to the development and evaluation of interactive
agents.
Read the full abstract ▾
All authors Qinchuan Cheng, Zhantao Gong, Pengzhan Sun, Angela Yao, Shijie Li
Artificial Intelligence · Cross-listed from cs.SE
Self-Supervised Scaling of Terminal Environments for Scientific Domains
Zhongzhi Li, Yucheng Shi, Zongxia Li et al. (+8 more)
Terminal
agents are increasingly deployed beyond software engineering in science and other specialized domains. Constructing training environments requires executable reference behavior and a domain-specific verifier that distinguishes semantic correctness from superficially plausible artifacts. Authoring these components for each task requires repeated engineering and limits reuse. We introduce software-in-the-loop reconstruction, a self-supervised framework that obtains reference outputs and verification targets from existing software workflows, executable programs mapping structured inputs to outputs. For each workflow, we execute multiple input configurations and partition cases into public observations and hidden evaluations. Given the instruction, input schema, and public input–output observations, an
agent constructs an editable program without access to the source workflow. The candidate is evaluated on hidden configurations against workflow outputs. A hierarchical verifier combines domain-specific semantic comparison, structural validity, and anti-shortcut checks, while public feedback supports iterative revision. The construction admits additional workflows and configurations without authoring a reference solution for each task. We instantiate SWR with 500 workflows and 46 software families across six domains. Across three attempts per task, Qwen3.8-Max solves 838 tasks and produces 1,422 verified trajectories, which we oversample to 3,000 reconstruction-only training examples. Supervised fine-tuning of Qwen3.8-27B improves mean Terminal-Bench 2 performance from 47.94% to 53.56% across three seeds and achieves the highest mean among four matched-
token corpus controls on all four reported evaluations. These results indicate that existing scientific software can provide scalable, behaviorally verified supervision for terminal
agents.
Read the full abstract ▾
All authors Zhongzhi Li, Yucheng Shi, Zongxia Li, Junyao Yang, Ruhan Wang, Yu Wang, Jingyuan Huang, Jichao Yu, Ninghao Liu, Haitao Mi, Leowei Liang
Artificial Intelligence · Cross-listed from cs.LG
MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model Heads
Linkai Ma, Xinyu Luo, Mengbo Wang et al. (+3 more)
The
Muon optimizer derives its update rule for hidden linear layers by solving a local linearization of the loss penalized by the spectral norm, motivated by an RMS-stability argument for dense linear layers. Standard
Muon implementations, however, exclude the input (
embedding table) and output (
language model head) layers from this principled treatment, for which they use AdamW instead. We present MuonIO, a single
Muon-style update for both of these layers. For the
language model head $\mathbf{L} \in \mathbb{R}^{V \times d}$, we motivate the use of the $2\to\infty$ operator norm, due to the Lipschitz continuity of the softmax output geometry, while for the
embedding table $\mathbf{E} \in \mathbb{R}^{d \times V}$, we draw on the $1 \to 2$ operator norm, based on the one-hot input geometry identified by Bernstein & Newhouse (2025). The identity $\lVert\mathbf{L}\rVert_{2\to\infty}=\lVert\mathbf{L}^\top\rVert_{1\to2}$ then puts both
matrices in the same vocabulary-oriented geometry: MuonIO applies a single normalized-vector rule, which appears as column normalization for $\mathbf{E}$ and row normalization for $\mathbf{L}$. Empirical evaluations demonstrate the effectiveness of our approach, with MuonIO reducing I/O optimizer state
memory by 50% and I/O update FLOPs by $\sim$46% compared to
Muon for 1B LLaMA pretraining on C4, while also improving validation perplexity.
Read the full abstract ▾
All authors Linkai Ma, Xinyu Luo, Mengbo Wang, Ananth Grama, Petros Drineas, Brian Bullins
Artificial Intelligence
Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution
Nguyen Ho, Bach Tung Tran, Trung Ky Nguyen et al. (+3 more)
Time series are produced continuously at enormous scale by industrial equipment, wearables, power grids, and clinical monitors, yet annotation remains manual, expensive, and expert-dependent. The binding constraint in large-scale time series analytics is therefore not data volume but label volume, and the question facing a practitioner is concrete: how many examples per class must be labeled before a classifier becomes usable? We study this question directly, in a regime where the label space is fixed and known in advance and the decision rule must be constructed from only K labeled examples per class. We propose Dual-Stream OSSE-LSTM, an episodic metric-learning framework that pairs an Omni-Scale CNN with Squeeze-and-Excitation recalibration, for multi-scale motif extraction without per-
dataset kernel tuning, with a Bidirectional LSTM for global temporal context. The two streams are independently normalized and fused into a prototype-oriented
embedding. Because decisions taken from a few labels must also be explainable, we introduce Counterfactual Integrated Gradients (C-IG), which attributes the prototype margin between target and opposing classes rather than an isolated classifier logit, and reuses the resulting maps as soft masks for test-time prototype refinement without updating the encoder. On 19 univariate UCR
datasets, OSSE-LSTM attains the highest average accuracy and per-
dataset win count at every support size, and its accuracy remains within a 0.36-point band (96.36-96.72%) across that range. Its weakest configuration still exceeding the best result any compared baseline achieves at any K (93.99%).
Read the full abstract ▾
All authors Nguyen Ho, Bach Tung Tran, Trung Ky Nguyen, Zhenchang Xia, Bolong Zheng, Long Van Ho
Artificial Intelligence
Learning to Revise Reasoning with Segment-wise On-Policy Distillation
Yuxiang Zhang, Ding Cao, Shuting Cui et al. (+3 more)
On-policy
distillation (OPD) improves large
language model
reasoning by training students on their own rollouts with dense
token-wise supervision from the teacher. However,
token-wise OPD does not explicitly provide a coherent alternative
reasoning step showing how the student's step could be revised to improve subsequent
reasoning. Furthermore, this paradigm can become less effective when the student produces a degenerate
reasoning prefix, as subsequent teacher supervision remains conditioned on that prefix and may reinforce poor
reasoning patterns. In this work, we focus on learning
reasoning revision with segment-wise OPD to rework intermediate
reasoning steps and better support subsequent
reasoning. Through controlled
reasoning interventions, we find that replacing student segments with teacher redrafts improves subsequent
reasoning accuracy. Therefore, we address the problem of turning teacher redrafts into explicit supervision for learning to revise
reasoning. We propose Segment-wise On-Policy
Distillation (Seg-OPD), which selects student segments based on an uncertainty metric and obtains corresponding teacher redrafts. Seg-OPD trains the student to prefer teacher redrafts over their paired student segments while retaining dense
token-wise OPD supervision. Extensive experiments on mathematical
reasoning and competitive programming tasks show that Seg-OPD-trained students achieve higher revision success rates than baselines. Seg-OPD consistently outperforms the compared state-of-the-art baselines in
reasoning accuracy with an average relative improvement of 5.22% across diverse models and tasks. Code is available at https://anonymous.4open.science/r/Seg-OPD.
Read the full abstract ▾
All authors Yuxiang Zhang, Ding Cao, Shuting Cui, Lei Wang, Weijieying Ren, Tianxiang Zhao
Artificial Intelligence · Cross-listed from cs.LG
Test-time Calibration Learning for Large Language Model Reasoning
Zizhuo Zhang, Xiong Peng, Jingwei Sun et al. (+4 more)
Reliable large
language models (LLMs) must not only produce accurate answers but also express confidence that faithfully reflects their probability of being correct. Such calibration is essential for identifying uncertain predictions and supporting reliable decision-making in real-world deployment. Recent studies incorporate calibration learning into reinforcement learning (RL), jointly optimizing answer correctness and verbalized confidence using ground-truth correctness supervision. However, their reliance on labeled data limits their applicability in practical test-time settings, where ground-truth labels are unavailable and calibration may need to adapt to newly encountered target tasks. To address this challenge, we propose Test-Time Calibration Learning (TTCL), a label-free framework that jointly adapts
reasoning accuracy and verbalized confidence directly on unlabeled target-task data. Specifically, TTCL derives self-supervision signals for both correctness and calibration from multiple model-generated responses, enabling calibration learning at test time without ground-truth labels. Theoretical analysis further establishes TTCL as a bounded surrogate for the ideal calibration objective. Extensive experiments on mathematical
reasoning and factual question answering demonstrate that TTCL consistently improves both accuracy and calibration across diverse models and tasks. On base models, TTCL achieves an average relative accuracy improvement of +40.13% and an ECE reduction of +70.80% across eight
benchmarks. Moreover, TTCL can further improve both accuracy and calibration for already calibrated models under domain shift, particularly when source-domain calibration transfers poorly to target tasks. In the math-to-factQA setting, TTCL achieves an average relative accuracy gain of +20.35% and reduces ECE by +53.83%. The source code is released at https://github.com/tmlr-group/TTCL.
Read the full abstract ▾
All authors Zizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao, Shixiong Kai, Mingxuan Yuan, Bo Han
Artificial Intelligence
Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning
Yehya Farhat, Michael Desmond and Anastasios Kyrillidis
Large
language models (LLMs) are increasingly deployed in enterprise, scientific, and medical applications, where
agents must incorporate domain-specific knowledge and adapt from experience. Context engineering offers a practical alternative to weight updates by improving model behavior through instructions, strategies, and evidence supplied at inference time. However, adapting context online typically requires a costly trial-and-error process, while queries are often processed independently, preventing useful experience from carrying forward.
Memory systems address this limitation by retaining information across interactions, but approaches that continually append information to a shared context face increasing
token costs, context-window limits, and performance degradation as the context expands. We introduce a unified formulation of context optimization and show that an
agent memory system update can be interpreted as an optimization update procedure over the model's context. This perspective attempts to provide a principled framework for studying
memory design and its efficiency. We then propose GraphMemory, a lightweight graph-based
memory that accumulates, refines, organizes, and connects reusable strategies. For each query, GraphMemory retrieves only the relevant subgraph, enabling online context adaptation without exposing the model to the entire
memory. Under bounded
retrieval, the amount of retrieved
memory remains constant as the number of processed examples grows. Experiments show that GraphMemory achieves competitive downstream performance while using approximately 81-85% fewer
memory-construction
tokens than our baselines.
Read the full abstract ▾
Artificial Intelligence
Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves
Min Zeng and Rui Zhang
Large
language models (LLMs) are increasingly explored for clinical
reasoning, but whether they appropriately revise judgments as patient evidence evolves remains unclear. We evaluated longitudinal belief updating using matched intensive-care trajectories from electronic health records. Across diverse LLMs, conditioning on a preceding judgment more often increased than reduced prediction error when estimates changed, replicated for a second endpoint. Controlled interventions revealed two failure modes. First, with preceding assessment fixed, models responded more strongly to worsening than matched improving respiratory evidence; this asymmetry persisted after headroom normalization at moderate and strong evidence levels. Second, with current evidence fixed, increasing prior risk from 10% to 90% shifted estimates by 26.2 percentage points, demonstrating causal influence of prior model beliefs. Prompting did not restore reliable updating. Evidence-Validated Longitudinal Update (EVLU) identified fewer, more reliable revisions, revealing a reliability-coverage trade-off. These findings establish longitudinal belief updating as a distinct dimension of LLM reliability.
Read the full abstract ▾
Artificial Intelligence
DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis
Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko et al. (+10 more)
Data journalism, the practice of using data analysis to surface newsworthy stories, depends increasingly on the ability of reporters and investigative journalists to uncover trends, disparities, and accountability narratives. In practice, exploring large structured
datasets remains slow and brittle: journalists must navigate hundreds of variables across many
datasets over years, understand data coding conventions, and write non-trivial analysis code while hypotheses evolve. Although LLMs are often touted as "ask in English, get SQL/answers," real newsroom workflows expose recurring failures, e.g., schema mismatches and drift, misread domain semantics and units, and silent assumptions. We present DataWeave, a system that addresses these needs by combining conversational interaction, schema grounding, analytical planning, and executable query generation to support exploratory analysis over structured data. Rather than treating LLMs as autonomous answer engines, DataWeave frames them as interactive partners whose outputs can be inspected, corrected, and steered as hypotheses shift. We present a case study with professional journalists using our system to analyze the U.S. Department of Education's Integrated Postsecondary Education Data System (IPEDS), a high-stakes public
dataset with substantial domain semantics and frequent schema updates. We also report how deployment experience and iterative refinement shaped the current DataWeave architecture and its analytical workflow. Our findings distill design principles and deployment lessons for trustworthy human-LLM collaboration in structured data analysis.
Read the full abstract ▾
All authors Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko, Eunice Son, Shambhavi Verma, Brian O'Leary, Venketesh Subramony, Sylvain Nazef, Jacquelyn Elias, Ron Coddington, Chris Contakes, Michael Riley, Naren Ramakrishnan
Artificial Intelligence
Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation
Xiang Chen, Futao Su, Kong Wang et al. (+2 more)
On-policy
distillation (OPD) combines student-generated rollouts with dense
token-level supervision from a teacher, but providing such supervision for every rollout requires substantial teacher computation. We introduce Success-Referenced On-Policy
Distillation (SR-OPD), which reduces this cost by selecting which
prompts and rollouts receive teacher supervision. When the student produces both successful and failed rollouts for the same
prompt, a successful rollout can serve as a natural reference for selecting failed rollouts. SR-OPD therefore focuses on such
prompts and prioritizes failed rollouts whose hidden-state trajectories show sustained divergence from a successful reference, while accounting for estimated teacher-input cost. Across three teacher-student pairs and six mathematical
reasoning benchmarks, SR-OPD uses only 3.46-5.02% of the teacher-input
tokens required by Vanilla OPD in the one-pass setting while maintaining comparable
reasoning performance. Under a controlled setting matched to 5% of Vanilla OPD's teacher-input budget, further experiments support both key design choices: focusing supervision on
prompts with both successful and failed rollouts, and using successful rollouts to guide failure selection. These results indicate that a student's own successful behavior can serve as a useful reference for allocating teacher supervision under a fixed teacher-input budget.
Read the full abstract ▾
All authors Xiang Chen, Futao Su, Kong Wang, Jiayi Chen, TanLin Li
Artificial Intelligence · Cross-listed from cs.LG
LEAP: Learning Efficient Action Proposals For LLM Agents
Zhen Xu, Qizheng Zhang, Gerry Wan et al. (+2 more)
LLM
agents are known to be slow in rollouts. An
agent completes a task one step at a time. At each step, it reasons and then chooses an action to execute. The next step and action cannot start until the previous one has finished. Speculative decoding accelerates the rollouts at the reason phase by drafting and verifying the inference
tokens. Recent works have also started to apply similar ideas at the action phase. These works use off-the-shelf models, usually large, to draft action proposals for target model to verify. Large drafters match the target more often but take longer to propose, while small off-the-shelf models are fast but rarely make the same decision as the target. We ask a more general question: what determines the end-to-end speedup of action speculation? To answer it, we develop a latency framework for the speculative round. The framework compares what a round gains with what it costs. The gain depends on how well the drafter predicts the target and on how many steps the task can take before it ends. The cost comes from drafting, from waiting for target verification and from executing tools. Guided by the framework, we introduce LEAP (Learning Efficient Action Proposals) which keeps the drafter small and makes it accurate by training it on the target actions sequences. With a small 0.6B model, LEAP agrees with the target on most decisions and makes
agents up to 60% faster in end-to-end wall clock time, with no systematic change in task success. Across various
datasets, target models and draft models, the framework accounts for most of the measured speedups. We also show the draft model can be online trained with no prior trace collection and match the performance of offline training, making LEAP practical to deploy in the real world.
Read the full abstract ▾
All authors Zhen Xu, Qizheng Zhang, Gerry Wan, Shang Zhu, Ce Zhang
Artificial Intelligence · Cross-listed from cs.CL
Zhihan Yang, Wei Guo, Jean-Marie Lemercier et al. (+14 more)
Despite the success of discrete
diffusion language models (dLMs) for fast parallel decoding, their non-smooth, high-dimensional space hinders trajectory steering for
reasoning and inference acceleration. To overcome this, we present Sigma, the first large-scale (3B/8B) continuous dLM built on steerable, low-dimensional ODE/SDE latent trajectories. Trained blockwise via likelihood optimization, Sigma jointly denoises Gaussian-corrupted
token embeddings while learning an optimal
embedding geometry. To accelerate training, Sigma leverages pre-trained weights from autoregressive (AR) models for warm-starting. During inference, we identify classifier-free guidance and score temperature as essential for high-fidelity
reasoning and coding. Across comprehensive math
reasoning and coding evaluations against state-of-the-art discrete counterparts (masked dLMs and AR baselines), Sigma achieves competitive performance with discrete models on standard
benchmarks (e.g., GSM8K, Minerva, HumanEval, MBPP) after pre-training and on challenging
reasoning tasks (e.g., MATH-500, AIME) after supervised fine-tuning. Beyond performance parity, we uncover key structural properties unique to continuous dLMs: (i)
embedding-space steering effectively governs the quality-diversity trade-off, yielding strong pass@k performance and (ii) continuous trajectories enable graceful degradation for low NFEs and efficient
distillation. These establish continuous dLMs as a promising paradigm for efficient
language generation.
Read the full abstract ▾
All authors Zhihan Yang, Wei Guo, Jean-Marie Lemercier, Simon Welker, Yonggan Fu, Mohammad Mahdi Kamani, Sajad Norouzi, Julius Berner, Tomas Geffner, Karsten Kreis, Yongxin Chen, Molei Tao, John Thickstun, Pavlo Molchanov, Ante Jukić, Arash Vahdat, Morteza Mardani
Artificial Intelligence
A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns
XinPeng Shen, Lan Zhang, Yixiao Huang et al. (+4 more)
Long-horizon
agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their extended interaction history that introduces an underexplored execution-safety concern. Under benign interaction conditions, an
agent may execute an action that violates a safety constraint specified many turns earlier. We term this failure mode Governance Hazard from Overlooked Safety Constraints across Turns (GHOST), which may cause irreversible damage. Our experiments reveal that GHOST events are not isolated cases: this failure mode, occurring precisely under benign interaction conditions, yields an occurrence rate of 11.5% on GPT-5.5. Furthermore, we theoretically show that if the residual conditional violation hazard along each safe prefix is bounded below by a non-summable sequence, the execution enters the hazard region almost surely. Leveraging this theoretical insight, we further propose
STAR-Guard, a two-layer defense coupling historical semantic safety constraint restoration with pre-execution audit.
STAR-Guard restores applicable safety constraints to reduce unsafe proposals, while its deterministic audit layer prevents residual violations from reaching the environment. Consistent with this two-layer design, we observe no GHOST events in our experiments under the GPT-5.5 setup.
Read the full abstract ▾
All authors XinPeng Shen, Lan Zhang, Yixiao Huang, Haoran Cheng, Jiewei Lai, Leilei Chen, Haoxiang Deng
Artificial Intelligence · Cross-listed from stat.ML
Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Quentin Berthet and Peter L. Bartlett
Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped. Existing analyses often impose restrictive assumptions on the estimated velocity field and yield convergence rates that fail to reflect the intrinsic low-dimensional structure common in real data, such as natural images and molecular geometries. In this work, we study the statistical generalization of flow-matching models for learning an unknown distribution $P_{\mathrm{data}}$ from finitely many samples. We derive finite-sample error bounds on the learned generative distribution, measured in the Wasserstein-$p$ distance, for all $p\geq 1$. Specifically, given $n$ i.i.d. samples from $P_{\mathrm{data}}$, we show that, for every $d>d_p^\ast(P_{\mathrm{data}})$ and appropriately chosen network architectures and hyperparameters, the learned distribution $\widehat{P}^{\mathrm{FM}}$ satisfies $ \mathbb{W}_p(\widehat{P}^{\mathrm{FM}},P_{\mathrm{data}}) \lesssim n^{-1/d}+n^{-1/(2p)}\bigl(\log(1/\xi)\bigr)^{1/(2p)}$ with probability at least $1-\xi$, where $d_p^\ast(P_{\mathrm{data}})$ denotes the Wasserstein-$p$ dimension of the target measure. Our results demonstrate that flow matching naturally adapts to the intrinsic geometry of data and mitigates the curse of dimensionality, as the convergence exponent depends on the intrinsic rather than ambient dimension. These guarantees remain meaningful in high-dimensional regimes and provide a theoretical explanation for the empirical success of flow matching on structured data distributions under substantially more relaxed assumptions than those in existing analyses.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching
Zhendong Mi, Pu Zhao, Ziyu Hu et al. (+4 more)
Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated
Transformer evaluations during denoising. Existing caching methods mainly exploit temporal redundancy at the feature or
token level, leaving the underlying mathematical structure of
diffusion features largely unexplored. In this work, we reveal that world-model features exhibit highly stable singular subspaces across nearby denoising steps, while their singular values follow predictable
evolution patterns. Building on this observation, we propose SpectralCache, a training-free spectral caching framework that reuses stable singular subspaces and estimates only low-dimensional singular values through linear extrapolation. We further exploit the spectral consistency between neighboring full-computation features to skip selected expensive backbone evaluations via singular value scaling. Extensive experiments on representative world models demonstrate that SpectralCache consistently improves inference efficiency while preserving generation quality. On HunyuanWorld-Voyager-13B, SpectralCache achieves 5.22x acceleration while maintaining a WorldScore of 65.90 for static scenes, substantially outperforming existing training-free caching methods in inference efficiency.
Read the full abstract ▾
All authors Zhendong Mi, Pu Zhao, Ziyu Hu, Xiaodong Yu, Yanzhi Wang, Grace Li Zhang, Shaoyi Huang
Artificial Intelligence · Cross-listed from cs.LG
Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis
Adam Piaseczny, Md Kamran Chowdhury Shisher, Shiqiang Wang et al. (+1 more)
Modern state space models (SSMs), such as Mamba2, provide a compelling alternative to
transformers by combining linear-time sequence modeling with recurrent state-space dynamics. However, the behavior of SSMs in distributed learning settings remains poorly understood. In particular, the existing standard
federated learning methods are largely architecture-agnostic, and do not account for the stability, selectivity, and state-space parameterization that characterize modern selective SSMs. To address this, we derive architecture-aware gradient and smoothness bounds for single- and multi-layer selective SSMs, and convergence bounds for FedAvg and FedProx, characterizing how recurrent stability, input-dependent discretization, and state projection norms affect
federated optimization. We then numerically validate the single-layer bounds on sequences generated by a teacher SSM, using a learner that follows the analyzed recurrence. We use this analysis to formulate expectations about the effects of local training and client heterogeneity, and examine these expectations by comparing nine
federated learning
algorithms on Mamba2
language modeling across six text domains. These experiments illustrate how SSM-specific bounds can provide a basis for interpreting the behavior of practical
federated learning
algorithms.
Read the full abstract ▾
All authors Adam Piaseczny, Md Kamran Chowdhury Shisher, Shiqiang Wang, Christopher G. Brinton
Artificial Intelligence
Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents
Tathagata Banerjee and Nima Moghaddas
Models of social contagion usually assume how individuals adopt beliefs and derive population behavior from it. We instead empirically measure belief adoption in
language model
agents, quantifying the probability an
agent adopts a claim given how many peers endorse it. We find this adoption kernel to be sigmoid, a characteristic of complex contagion, with a threshold that is sensitive to three sources: the claim's plausibility, the source's reliability, and the
agent's disposition. These three dimensions are well approximated by a single effective dimension which we propose can be understood as the coherence of the incoming belief with the LLM
agent's prior beliefs. Further, we observe a characteristic of complex contagion in the collective dynamics of belief adoption in a system of AI
agents: further spread on clustered than random networks. These systems also exhibit a bifurcating cascade window, and self-sustaining hysteretic consensus which lead to consensus being far harder to remove than to establish.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.chem-ph
Equivariant Flow Matching for Electron Density Prediction
Chenxing Liang, Chengdong Wang, Yuchao Lin et al. (+2 more)
Machine learning surrogates for density functional theory (DFT) have been increasingly used to reduce the cost of first-principles calculations. In this arena, predicting real-space electron densities offers a scalable and transferable initialization for self-consistent field (SCF) procedures. However, current methods face a clear dilemma. That is, grid-based architectures incur a high computational cost, while basis-set methods fail to capture the structural correlations inherent in the coefficient space. Here, we develop OrbFlow, an $\mathrm{SE}(3)$-equivariant generative model that predicts Gaussian-type orbital (GTO) coefficients via flow matching. OrbFlow retains the efficiency of a compact atom-centered basis while replacing pointwise regression with a learned probability path over the full coefficient space. It is trained through a two-phase trajectory curriculum that mitigates discretization drift during numerical integration. OrbFlow achieves state-of-the-art accuracy on QM9, reducing density error by 13.6% relative to the previous best model, and reduces error by 51% to 63% on every molecule of the MD
benchmark relative to the strongest prior method sharing its basis. The predicted density also cuts SCF iterations by up to 68% with zero-shot transfer to unseen exchange-correlation functionals and recovers dipole and quadrupole moments to within a few percent of DFT references without any SCF calculation.
Read the full abstract ▾
All authors Chenxing Liang, Chengdong Wang, Yuchao Lin, Xiaofeng Qian, Shuiwang Ji
Artificial Intelligence
Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
Jie Jin, Ziyin Ma, Min Yin et al. (+4 more)
Full-duplex voice
agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which feeds ASR-encoder hidden states through a small connector into a frozen LLM and reads each question as a single-
token distribution over its options. Nothing is decoded, and an 8-GPU node answers 80 decisions about eight utterances in about 0.1 s. With a last-layer connector, spoken QA stays close to reading the transcript (90% vs. 91%). DuplexJev also hears the speaker: gender and emotion accuracy both reach 90% (from 55% and 28%) with a cross-
attention connector, whose spoken QA drops by only 1 point (83% to 82%). We train decisions with cross-
entropy on the read-out answer
token, instead of the usual transcript
distillation, whose teacher never hears the voice, and keep
distillation for content. Encoders and LLMs are interchangeable; we release weights, training recipe, a batched-inference pipeline for full-duplex serving and a bilingual spoken-QA set.
Read the full abstract ▾
All authors Jie Jin, Ziyin Ma, Min Yin, Jinyu Chen, Haigang Song, Zhikun Pang, Xiaowen Zhang
Artificial Intelligence
Designing the Future of User Feedback for Generative AI
Alisa Frik, Julia Bernd, Amitis Karami et al. (+1 more)
Post-deployment feedback from users can be a cost-effective, scalable, and representative means to monitor and improve generative AI systems and features. When implemented effectively, giving such feedback can increase users' engagement with and trust in GenAI systems. Government regulations and industry guidelines call for post-deployment user engagement, but there is little guidance on designing mechanisms that are usable for consumers and provide actionable input for product teams. We conducted a multi-phase study as a collaboration between academic researchers and eBay. Our
benchmark evaluation of current industry approaches identified common issues including lack of discoverability, unclear terminology, and inattention to user value. Based on these findings, we developed best-practice recommendations and designed and tested a prototype feedback-collection tool. The tool aimed to provide users with an efficient, flexible, and positive feedback-giving experience, and provide product teams with rich data on performance and potential problems in a usable format.
Read the full abstract ▾
All authors Alisa Frik, Julia Bernd, Amitis Karami, Mohammad Tahaei
Artificial Intelligence
Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents
Feng Chen, Ritam Dutt, Atnaz Taheri et al. (+1 more)
An email assistant should not complete less work simply because a user phrases the same request differently. Yet most
benchmarks test each task with only one canonical request, leaving this form of robustness largely unmeasured. We test whether email assistants remain reliable when the requested information, available evidence, and expected outcome stay fixed, but the communication style or English variety changes. We construct validated variants along five communication-style axes and four rule-based dialect conditions, and evaluate them on three
benchmarks: a
retrieval-augmented generation (RAG) pipeline and two tool-using
agents. Indirect requests reduce performance on all three
benchmarks, while formal requests reduce performance on both agentic
benchmarks. Examining the systems more closely shows that these failures have different causes. Verbose requests mainly hurt a lexical retriever by making the relevant email harder to find. By contrast, indirect and dialect variants remain harmful even when the relevant email is retrieved. In the agentic setting, indirect and formal requests mainly cause the
agents to omit required actions, not to take more unsupported actions. These results show that a successful response is not enough to establish robustness: evaluations should vary how requests are expressed and separately measure whether
agents complete the requested work.
Read the full abstract ▾
All authors Feng Chen, Ritam Dutt, Atnaz Taheri, Alex Williams
Artificial Intelligence · Cross-listed from cs.CV
Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination
Shenglan Li, Zhendong Mi, Hengyi Zhu et al. (+6 more)
Vision-
language-action (VLA) models increasingly incorporate intermediate
reasoning to improve robotic manipulation, yet existing approaches primarily reason about observed states without explicitly anticipating future scene
evolution. Extending such
reasoning to explicit future rollouts at every inference step, however, introduces substantial computational overhead. We propose IG-VLA, a VLA
reasoning framework that enables models to imagine the future and internalize the gist. Our Latent Spatiotemporal
Reasoning learns to imagine task-relevant future scene
evolution directly in visual representation space, guiding action prediction without costly pixel-level
video generation. To further reduce inference overhead, we introduce Scene Gist
Memory, which internalizes
reasoning-derived scene-behavior associations into a compact Scene Gist
Token, preserving the benefits of future
reasoning while bypassing explicit future imagination at inference. Extensive experiments on LIBERO, LIBERO-Plus, and VLABench demonstrate the effectiveness and efficiency of IG-VLA. On the LIBERO-Plus
Language suite, both the
reasoning and gist policies outperform the strongest baseline by nearly 6% in success rate. The gist policy also achieves up to 6.38x speedup over baselines, reducing inference latency from 1081ms to 169.5ms per action chunk on a single NVIDIA A6000 GPU. These results demonstrate that future spatiotemporal
reasoning can be effectively internalized for efficient VLA deployment.
Read the full abstract ▾
All authors Shenglan Li, Zhendong Mi, Hengyi Zhu, Jingwu Luo, Chun Kit Chan, Geng Yuan, Yanzhi Wang, Pu Zhao, Shaoyi Huang