Artificial Intelligence · Cross-listed from cs.LG
From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon
Jihwan Kim, Dogyoon Song and Chulhee Yun
Different optimizers can fit the same training data while selecting classifiers with substantially different geometries, but whether this difference provably affects population performance remains unclear. We show that row-wise normalization can achieve strictly higher population accuracy than full-batch Adam, a proxy for random-reshuffling Adam, and exact-SVD
Muon in high-dimensional multiclass classification. Under an isotropic Gaussian-cloud data model, this advantage arises because row normalization's class-wise Euclidean geometry asymptotically preserves the population decision-boundary directions, whereas Adam's coordinate-wise geometry and
Muon's spectral geometry introduce nonvanishing distortions. Beyond isotropy, the advantage persists for full-batch training on class means with independently oriented class-mean and test-noise covariances. It holds for power-law spectra with class-mean exponent below one, even under heavily anisotropic test noise. When both covariances are diagonal and sufficiently close, the advantage over Adam can reverse, while applying the same random rotation to both restores it by changing only their
alignment with Adam's coordinate axes. Synthetic and last-layer
language-model experiments support the predicted advantage.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.SE
Characterizing Overconfident Failure in LLM-Based Code Generation
Ravishka Rathnasuriya and Wei Yang
Large
language models (LLMs) are increasingly used for automated code generation, but generated programs can appear syntactically plausible while still failing execution-based correctness checks. Existing validation methods, such as testing and program analysis, remain essential but are often incomplete, costly, or applied only after generation. Model-derived uncertainty is therefore a natural early reliability signal. This paper studies the dilemma of overconfidence in code LLMs where incorrect programs are often generated with
token-level confidence comparable to correct programs. We study this dilemma across four open-source code models and three execution-based
benchmarks. Our analysis begins by investigating whether existing uncertainty metrics provide reliable proxies for execution correctness in code generation. We then characterize overconfidence at both global and local
token levels, asking whether incorrect programs remain indistinguishable from correct ones under confidence and
entropy summaries, including selective generation and the limits of instruction tuning. Finally, we evaluate whether common mitigation strategies reduce this failure mode. Our study yields four findings. First, existing uncertainty signals provide only partial and model-dependent evidence of execution failure. Second, overconfidence persists at both program and
token levels, and uncertainty-based selection does not consistently improve accepted-set accuracy. Third, instruction tuning can increase certainty on failing generations without consistently improving correctness discrimination. Fourth, common mitigation techniques improve specific aspects of reliability but do not reliably resolve overconfident failure. Our exploratory latent analysis suggests that hidden representations may encode correctness-related signals that output confidence does not expose.
Read the full abstract ▾
Artificial Intelligence
DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration
Yingda Shen, Yuxiang Wang, Kunyu Feng et al. (+7 more)
Voice
agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search,
reasoning, and coding are handled through asynchronous delegation. A duplex model supports continuous listening and speaking, but complex
reasoning and tool use may exceed its capabilities. A coding
agent can plan and execute extended tasks, but its sequential interface is a poor fit for live conversation. Combining them requires a harness that coordinates task acceptance, progress, cancellation, replacement, and result delivery while keeping the conversation responsive. Existing harnesses often rely on coupled heuristics, making them difficult to improve systematically from evidence. We present DuplexAgent, a full-duplex collaboration system whose harness expresses this workflow as six editable modules, and Duplex-Harness-RSI, a closed loop that revises them from interaction traces. A simulator automatically generates timed test conversations, runs the system, and produces failure traces that identify the collaboration modules requiring repair.
Reasoning LLMs and coding
agents in the delegation pool also serve the improvement loop: the Exam Planner selects the next tests from observed weaknesses and the repair archive, and the Harness Editor proposes targeted module changes. The capabilities that serve the user thus also improve the system's coordination. Experiments on intelligence, agentic, and duplex
benchmarks show that DuplexAgent combines continuous interaction with difficult
reasoning and complex task execution, achieving stronger spoken-knowledge and executable-tool scores than the compared delegated systems while maintaining strong interruption response. A harness ablation further shows that this modular, verifiable loop outperforms the initial harness and repeated editing that lacks its diagnosis and repair archive.
Read the full abstract ▾
All authors Yingda Shen, Yuxiang Wang, Kunyu Feng, Qinke Ni, Jiaqi Li, Minghao Hsu, Junan Zhang, Dekun Chen, Yutong Bian, Zhizheng Wu
Artificial Intelligence
ORDO: Operation-level Round-aware Dynamic Ordering for MIP Presolve
Zehuan Chen and Chunhe Song
Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only optimize parameter configurations and cannot express the non-commutative temporal dependencies among actions, whose default order is nearly unique on most domains, yet functionally necessary: artificially shuffling the order of the same sequence inflates the tail of the solve-time distribution by up to several-fold. We recast presolve planning as autoregressive sequence generation over a unified atomic action space, moving the decision object to action sequences; we call this framework ORDO—Operation-level Round-aware Dynamic Ordering for MIP Presolve. Its payoff is cross-domain generalization: on multiple unseen domains it attains end-to-end zero-shot speedup—to our knowledge the first for presolve action sequences—varying by domain and not explained by corpus richness, the strongest domain reaching the largest speedup once racing is added. Deployment uses sequence racing, in which candidate sequences run concurrently and the winner is kept, enabled by an execution-and-observation facility, added by modifying the SCIP source, that injects sequences along the native path and records which actions actually execute and in which round.
Read the full abstract ▾
Artificial Intelligence
Open-ended Scientific Discovery with Possibilistic Reasoning
Anita Yang, Siu Lun Chau, Tomoya Wakayama et al. (+2 more)
Autonomous scientific discovery with LLMs requires generating and testing hypotheses adaptively as evidence accumulates while maintaining statistical validity. Existing anytime-valid methods can handle data-dependent hypotheses, but open-ended discovery poses a deeper challenge: the best discovered hypothesis may still be the best of a bad lot, with better explanations yet undiscovered, while even background knowledge such as physical laws may require revision in light of new findings. In response, we formalize the problem as Abductive Autonomous Scientific Discovery (AASD) using possibility theory. We introduce abductive utility, a computable measure of discovery progress, and possibility frontier search, the first
algorithm for AASD, which maintains anytime validity and achieves $\varepsilon$-optimal abductive utility asymptotically under suitable conditions. Experiments on synthetic and real-world scientific-discovery tasks show strong performance.
Read the full abstract ▾
All authors Anita Yang, Siu Lun Chau, Tomoya Wakayama, Krikamol Muandet, Masaki Adachi
Artificial Intelligence · Cross-listed from cs.CL
REMORY: Learning Residual Memory for Context Compaction
Hanchen Xia, Baoyou Chen, Yutang Ge et al. (+5 more)
Long-horizon
agents compact their history to continue within a finite context window, but a textual summary alone may not support every subsequent decision. We introduce REMORY, a neural
memory network that supplements the summary with a bounded sequence of soft
memory tokens. Given the history and summary, the network learns to generate
tokens that help a frozen LLM approximate the continuation it would produce with the full history. The
tokens are conditioned on the summary and appended after it, forming an analogue of a residual connection along the sequence dimension. On SummHay, REMORY improves source attribution at nearly unchanged insight coverage and approaches the full-context joint score using only 5.2% of the input positions. Across long-horizon
agent benchmarks, Qwen3.8-27B and GLM-5.3-Flash show consistent gains with residual
memory. Both models also exhibit substantially fewer repeated tool outputs and tool errors on BrowseComp and Terminal-Bench 2.1.
Read the full abstract ▾
All authors Hanchen Xia, Baoyou Chen, Yutang Ge, Naihao Deng, Senqiao Yang, Zilong Dong, Weihao Yuan, Siyu Zhu
Artificial Intelligence · Cross-listed from cs.AR
DynaTE: Accelerating Diffusion LLMs via Dynamic Token Execution
Minghan Jiang, Jiayi Wang, Shuaiting Li et al. (+2 more)
Diffusion-based LLMs (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs by enabling bidirectional parallel refinement, alleviating the sequential decoding bottleneck of AR generation. However, their parallel iterative refinement mismatches AR accelerators optimized for sequential decoding and their discrete
token generation differs from DiT accelerators designed for continuous denoising. Recent dLLM accelerators have explored workload-specific optimizations to reduce vocabulary processing overhead and redundant computation across denoising iterations. However, these approaches retain all
tokens in parallel execution, despite varying
token refinement utility and execution requirements. This paper presents DynaTE, a hardware–software co-design architecture that dynamically adapts accelerator execution to evolving
token states during dLLM decoding. DynaTE first enables adaptive
token execution by skipping low-utility
token computation, while a dimension-reconfigurable PE array maintains high utilization under varying active-
token patterns. Second, DynaTE exploits dynamic
token dependencies through FLDD to refine a small number of locally dependent
tokens within the current iteration, reducing the overall number of denoising iterations, while a Merge–Split–Merge dataflow hides the resulting serial overhead. Third, a streaming vocabulary engine interleaves multiple
token streams from the LM head to accommodate irregular output variations caused by selective
token computation and uneven vocabulary-selection demands. Evaluated on two representative dLLMs, DynaTE achieves 2.05–2.78$\times$ speedup and 2.99–3.93$\times$ higher energy efficiency over state-of-the-art dLLM accelerators, while delivering 2.55$\times$ speedup and 6.07$\times$ higher energy efficiency over Jetson AGX Orin.
Read the full abstract ▾
All authors Minghan Jiang, Jiayi Wang, Shuaiting Li, Haibin Shen, Kejie Huang
Artificial Intelligence · Cross-listed from cs.LG
How to post-train on a surrogate: Envelope sampling mitigates reward hacking
Sanjit Dandapanthula, Shuvom Sadhuka, Samir Khan et al. (+3 more)
Large
language models (LLMs) are commonly post-trained against LLM judges and other cheap surrogates because the true reward, such as human preference, is too expensive to query at scale. This practice often leads to reward hacking, where reinforcement learning against a miscalibrated surrogate leads to undesirable side effects. In this work, we study a setting in which a small number $n$ of model outputs are annotated with ground-truth labels (e.g., from expert review) and used to recalibrate the LLM judge before optimizing against it. Prior approaches to judge recalibration are costly or heuristic, and it is known that on-policy sampling fails when the surrogate is miscalibrated on a rare set of outputs. In this work, we propose envelope sampling, a theoretically-grounded method for judge recalibration that seeks to minimize an upper bound on the regret of the post-trained model under the assumption that the human reward and re-calibrated reward lie in an $L^2$ ball around the judge. We give practical
algorithms to sample from the envelope by rejection or by fine-tuning against a modified reward, and experiments on clinical note generation and on a controlled sycophancy task show that recalibrating on envelope samples mitigates reward hacking where recalibrating on base-model samples does not.
Read the full abstract ▾
All authors Sanjit Dandapanthula, Shuvom Sadhuka, Samir Khan, Michael Oberst, Aaditya Ramdas, Alexandra Chouldechova
Artificial Intelligence · Cross-listed from cs.CL
Gated Memory: Admission-Controlled Memory Formation for Conversational AI
Preeti Saraswat, Divya Neelagiri and Ajay Manoj
Personalized conversational AI relies on long-term
memory systems that extract facts from user utterances and store them in persistent vector stores. Despite progress in
retrieval, deduplication, and lifecycle management, the formation stage, the moment a fact is first written to storage has received almost no principled
attention. We identify this as the binding constraint on
memory quality in production systems. Critical contextual signals, such as the distinction between a permanent user attribute and a transient situation, exist only in the original utterance and are irreversibly lost the moment extraction produces a subject-relation-object triple. No downstream process can recover them. We propose Gated
Memory, a lightweight, modular formation framework that interposes two decision checkpoints between conversation and storage: an admission gate that evaluates every candidate fact against the full utterance context before extraction runs, and a conditional enrichment stage that grounds admitted facts through an entity scope taxonomy with
privacy constraints. The gate evaluates only the current exchange while using prior turns as read-only reference context, and produces a structured formation record. Admitted content is decomposed into atomic facts, each categorized, tagged with provenance (directly stated versus inferred), scoped to its condition of applicability, and grounded in resolved time and place, subject to a constraint that no entity absent from the context may be asserted. On the LoCoMo-10
benchmark with atypical emotional density in utterance data, Gated
Memory achieves an overall +2.6% relative improvement in LLM-judge accuracy over a strong baseline with identical
retrieval and generation, establishing formation quality as a measurable constraint on
memory performance.
Read the full abstract ▾
Artificial Intelligence
TaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks
Wei-Xiang Mao, Zhi-Kai Chen, De-Chuan Zhan et al. (+1 more)
Agents combine
reasoning with tools to interact with external systems and complete real-world tasks. Early
agents typically interleave
reasoning and actions along a single execution chain. On complex tasks, this chain becomes unreliable because growing histories obscure intermediate dependencies and allow early planning errors to propagate. Recursively decomposing a complex task into smaller subtasks offers a natural solution, yet effective decomposition must account for the system's capabilities so that each subtask can be executed by the available tools. In realistic systems, however, tool libraries can be too large to expose in full. Injecting every tool description consumes substantial context while making relevant tools harder to retrieve and useful task boundaries harder to identify. We propose tool-aware recursive decomposition, which organizes tools by functional relationships into a hierarchy of capabilities. During execution, the
agent discovers tools on demand and uses the hierarchy to recursively decompose a complex task into a subtask tree whose levels are aligned with the capabilities required at each stage. Experiments on complex real-world tasks show that the proposed method improves end-to-end task success rate by up to 40 percentage points over the compared baselines. The implementation of TaReD is available on GitHub: https://github.com/WeiXiang-Mao/TaReD.
Read the full abstract ▾
All authors Wei-Xiang Mao, Zhi-Kai Chen, De-Chuan Zhan, Han-Jia Ye
Artificial Intelligence
LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
Surya Shetty and Ulisses Braga-Neto
Large
language model
agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with minimal human oversight. Yet identifiability is often overlooked: when a plateau is reached, the
agent needs to know whether it is not yet capable enough or the model simply is not identifiable from the data, in which case no amount of further experimentation of the same kind can help. We propose the Identifiability-Driven Experimental
Agent (LLM-IDEA) for closed-loop discovery with an identifiability engine that returns a three-way plateau verdict: capability limit, resolvable within the design class, or certified exhausted. On ODEBench, 60 of the 62 systems with free constants are identifiable at round 0; the RC
circuit is certified exhausted for every experiment that protocol can run, and a harvesting model is resolvable by one added initial condition. The identifiability engine reproduces known verdicts on Lotka-Volterra, Van der Pol, Lorenz, and a pharmacokinetic model, where it recommends the intravenous arm pharmacologists use, and it ranks the depth scorer of our own
benchmark last among four observation designs. On the DiscoverPhysics
benchmark, it finds two public worlds whose explanation rubric rewards a distinction no legal experiment can make, and every model there with accurate trajectories failed the explanation grade (15 of 15, against 5 of 9 in identifiable worlds, p = 0.012). On the Alien Universe, a two-body testbed we propose in which a force law switches between a provably non-identifiable and an identifiable protocol, LLM-IDEA on the identifiable protocol reaches discovery depth at least three on 8/8 seeds versus 1/8 without it. An autonomous discovery
agent can thus compute, rather than guess, whether a plateau calls for more search, a better experiment of the same kind, or a different kind of experiment.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Neuro-Memory Fuzzy Inference System for Mimicking Human-like Car Following Behavior
Nazmul Haque and Md Asif Raihan. Md. Hadiuzzaman
This study presents the Neuro-
Memory Fuzzy Inference System (NeMeFIS), a hierarchical machine learning architecture that asymmetrically models acceleration and deceleration in car following behavior by integrating five human
memory types procedural, working, episodic, semantic, and declarative. By linking external variables to
memory functions via metaheuristics and validating them through factor and p-value analyses, NeMeFIS uncovers latent cognitive influences across Arterial, Collector, and Rural Highway corridors for different types of vehicles. Results from 54 different trained models emphasize cognitive thresholds shaped by driver perception limits and cognitive load. The trained NeMeFIS models outperform traditional statistical and conventional machine learning models in replicating realistic driving behavior, including comparisons with Linear Regression, ANFIS, and LSTM architectures. Fuzzy rule analysis reveals that declarative
memory demands the highest rule, especially during deceleration, indicating complex braking decisions. Procedural
memory drives acceleration, while semantic and declarative
memory guide deceleration. Risk perception also emerges as a key factor, particularly on urban roads. Validated on both heterogeneous and homogeneous
datasets, NeMeFIS offers a robust framework for modeling driver cognition. The findings support psychotherapeutic applications and the development of adaptive, human-like decision systems in Connected and Autonomous Vehicles (CAVs) to enhance traffic safety.
Read the full abstract ▾
Artificial Intelligence
Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?
Minhao Fan, Yinyi Liu, Jiayu Zhao et al. (+3 more)
Small
vision-
language models may be able to read external evidence yet struggle to obtain it. We introduce Harness Compilation (HC), an offline procedure that adapts the division of work between a frozen small VLM and its external harness. A large teacher uses student execution traces to revise reusable content and control, while a separate validation set selects the deployed harness. Deployment requires neither weight updates nor teacher calls. Across seven visual question-answering settings with students of at most 9B parameters, HC improves scores over bare students by 9.9-23.9 points, averaged over three independent builds per setting. Interventions on five runtime decision types (invocation, selection, argument generation, evidence integration and abstention) show why this allocation matters: requesting evidence and generating open queries can be costly, whereas bounded choices and reading supplied text can remain useful student work. Fact cards benefit all ten evaluated students, but decision policies transfer unevenly. Recompilation for a new student model helps when the transferred interface no longer fits the student. With 100 practice items, HC exceeds answer-only LoRA on three tasks. Larger training budgets can match or surpass a fixed harness, while combining the two improves SlideVQA beyond either alone. These findings support allocating work from measured student behavior rather than uniformly removing decisions.
Read the full abstract ▾
All authors Minhao Fan, Yinyi Liu, Jiayu Zhao, Zihan Teng, Song Chen, Weichen Liu
Artificial Intelligence
When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu et al. (+6 more)
Weight-only post-training quantization (PTQ) relies heavily on reconstruction loss minimization to preserve model quality at low precision. We show that the weights favored by minimizing this loss need not yield better model performance on new tasks. In fact, we find that lower reconstruction loss can even degrade model performance on the same calibration data. Our analysis further shows that weights with lower reconstruction loss on calibration data can have higher loss than other weights when the distribution of input activations changes. Motivated by these observations and our analysis, we propose Distributionally Robust Quantization (DRQ), a post-hoc refinement process that minimizes worst-case reconstruction loss over a constrained set of input activation distributions. DRQ refines the integer codes representing quantized weights within the existing quantization grid, keeping quantization parameters and inference operators unchanged. Extensive experiments show that DRQ improves models quantized by six representative PTQ methods, including AWQ, GPTQ, and ParoQuant, and delivers gains across both dense and mixture-of-experts large
language models. These results establish DRQ as a general post-hoc refinement framework for weight-only PTQ, achieving better downstream performance without adding inference overhead.
Read the full abstract ▾
All authors Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu, Baihua He, Xinyu Zhang, Harrison Bo Hua Zhu, Wenlong Chen, Li Zeng, Zhuo Sun
Artificial Intelligence · Cross-listed from cs.RO
SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning
Weizhe Xu, Jialiang Fan, Mengyu Liu et al. (+1 more)
Large
Reasoning Language Models (LRLMs) enable multi-step
reasoning for robotic task planning, but continued
reasoning can overwrite valid intermediate plans or leave constraint violations unresolved, reducing planning reliability and wasting inference-time computation. We develop an inference-time monitor that exposes and verifies intermediate plans without disrupting the original decoding trajectory. Building on this monitor, we propose SafeInferCom, a formal verifier-guided framework that preserves valid intermediate plans and directs error correction during generation. Experiments across multiple LRLMs and planning domains reveal
reasoning-response inconsistency and limited self-correction under one-shot inference. SafeInferCom improves planning success and accelerates error correction relative to one-shot inference. When combined with iterative refinement, it further improves success while reducing
token usage compared with refinement alone. We additionally evaluate SafeInferCom in VirtualHome and provide a real-world robotic-arm demonstration.
Read the full abstract ▾
All authors Weizhe Xu, Jialiang Fan, Mengyu Liu, Fanxin Kong
Artificial Intelligence
AliO: Output Alignment Matters in Long-Term Time Series Forecasing
Kwangryeol Park, Jaeho Kim and Seulki Lee
Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to predict the future sequence, have become increasingly crucial in real-world applications such as weather forecasting and planning of electricity consumption. However, state-of-the-art LTSF models often fail to achieve prediction output
alignment for the same timestamps across lagged input sequences. Instead, these models exhibit low output
alignment, resulting in fluctuation in prediction outputs for the same timestamps, undermining the model's reliability. To address this, we propose AliO (Align Outputs), a novel approach designed to improve the output
alignment of LTSF models by reducing the discrepancies between prediction outputs for the same timestamps in both the time and frequency domains. To measure output
alignment, we introduce a new metric, TAM (Time
Alignment Metric), which quantifies the
alignment between prediction outputs, whereas existing metrics such as MSE only capture the distance between prediction outputs and ground truths. Experimental results show that AliO effectively improves the output
alignment, i.e., up to 58.2% in TAM, while maintaining or enhancing the forecasting performance (up to 27.5%). This improved output
alignment increases the reliability of the LTSF models, making them more applicable in real-world scenarios.
Read the full abstract ▾
Artificial Intelligence
What to Admit and How to Present: Governing Persistent Memory in LLM Agents
Chang Liu and Deliang Ding
Persistent
memory can improve personalization in LLM
agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decisions: admission, which determines what recalled information enters the working context, and presentation, which determines how admitted information is expressed. We implement two inference-time designs without retraining: factor-compiled admission (FC), which assesses whole
memory entries, and permission-semantic admission (PS), which decomposes entries into typed units; both translate adjudicated attributes into eligibility decisions via deterministic policies. We evaluate on a four-backbone development suite and an external
benchmark with four tasks of 300 samples each. Relative to verbatim injection, FC and PS reduce pooled judge-assessed failure rates on the external
benchmark by 6.7 and 8.8 percentage points (p = 2.7e-7 and 4.1e-12), and development-set cross-domain leakage falls by up to 29.5 percentage points. A query-conditioned gating baseline shows no significant change in objective-fact failure or pooled failure. Under matched admission budgets, PS outperforms random and relevance-based selection on external objective-fact judgment after Holm correction. Holding presentation fixed, tightening admission cuts cross-domain failure by a further 17.5 percentage points (p = 1.6e-4); in contrast, no comparison between two renderings of identical adjudicated outputs survives multiple-comparison correction. Both designs increase personalization failures, and PS misses the preregistered improvement and personalization-preservation criteria. These results support evaluating admission and presentation separately: selection quality provides task-specific safety gains, while preserving beneficial
memory use remains unresolved.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation
Shunyuan Zhou, Hao Chen, Tianyu Wang et al. (+3 more)
Following retrieved evidence does not guarantee factual correctness: misleading evidence can induce a model to replace an answer it previously gave correctly. Standard accuracy measures obscure this behavior by combining answer replacement with preexisting errors. We introduce RAG-Stress, a controlled diagnostic protocol for examining the limits of evidence reliance in
retrieval-augmented generation. The protocol holds the question and reference answer fixed, edits one assertion to support a designated incorrect answer, and crosses two source priority policies with three positions of the answer span within the evidence text. We measure misleading rate (MR) on each model's subset of questions answered correctly without
retrieval, alongside clean accuracy on the full evaluation set. We evaluate fifteen systems spanning API models, open models, and search
agents trained with reinforcement learning on TriviaQA-RC, HotpotQA, and SearchQA, with additional English and Chinese MedQA evaluations. Instructions that prioritize documents consistently produce higher MR than those permitting reliance on prior knowledge. Averaged over models and positions, the gap ranges from 10.9 to 13.5 percentage points across the three QA
datasets. Mean MR follows End $>$ Beginning $>$ Middle under both policies, although individual models do not uniformly follow this ordering. A separate paired audit of 500 questions and two checkpoints supports increased harmful override without establishing a corresponding improvement in beneficial correction. These findings distinguish evidence adherence from factual reliability and motivate evaluating whether retrieved evidence preserves, replaces, or corrects a model's answers.
Read the full abstract ▾
All authors Shunyuan Zhou, Hao Chen, Tianyu Wang, Goose Lin, Zaiyuan Wang, Haiying Zhao
Artificial Intelligence · Cross-listed from cs.RO
Higher-Order Action Supervision Makes A Strong Policy Class
Peng Cheng, Yunxian Hou, Zhi Zhou et al. (+3 more)
Modern data-driven decision-making methods, such as imitation learning (IL) and reinforcement learning (RL), have achieved great success in solving many complex tasks. However, these methods often suffer from serious control instability and robustness issues when applied in real-world applications such as robotics and autonomous driving, posing notable challenges for their practical deployment. We argue that this instability issue stems largely from their limitations in solely supervising and optimizing zeroth-order actions (i.e., the action labels), failing to account for higher-order action dynamics and temporal consistency. In this paper, we show that simultaneously supervising both zeroth- and first-order actions can dramatically enhance policies' performance and control robustness. To achieve this, we introduce a novel and elegant loss scheme supported by formal theoretical guarantees that can equip any off-the-shelf policy model (e.g., deterministic,
stochastic, or flow policies) with the capability for higher-order action supervision, without requiring any structural modifications. Moreover, our proposed method can serve as a lightweight plug-and-play module that seamlessly integrates with a broad spectrum of existing offline RL frameworks. Extensive evaluations on OGBench and D4RL demonstrate that our approach yields substantial performance and robustness improvements across a wide range of continuous control environments. Notably, our method can also enhance policies' out-of-distribution (OOD) generalization capability in the challenging low-data regime, making it an ideal tool in tackling many real-world control problems.
Read the full abstract ▾
All authors Peng Cheng, Yunxian Hou, Zhi Zhou, Qian Zhang, Chang Huang, Xianyuan Zhan
Artificial Intelligence · Cross-listed from cs.CV
VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding
Runquan Gui, Hanzhu Chen, Zehao Wang et al. (+3 more)
Long-form
video understanding often involves multiple questions about different aspects of the same recording. Yet existing
video agents typically process each question through an isolated tool-use trajectory. This repeatedly restarts
video exploration and
memory construction, missing opportunities to acquire evidence jointly and progressively build a shared understanding that supports the complete question set. We introduce VAMR (
Video Agent for Multi-Question
Reasoning), which coordinates all questions about a
video through one shared tool-use trajectory. At each round, a persistent policy model can invoke tools for one or more unresolved questions and submit answers for questions with sufficient evidence. Question-conditioned visual perception retrieves fine-grained clues for several questions in one call, while layered multi-question
memory integrates reusable context into a shared
video story and preserves separate evidence for individual questions. After supervised fine-tuning initializes this interaction protocol, we propose question-horizon policy optimization (\qhpo) to optimize shared trajectories in which questions progress and finish at different rounds. Specifically, a question-level critic estimates the value of each active question, while round
alignment maps each question advantage to the rounds that directly serve it before the aligned advantages are aggregated to optimize the shared actor. Across LVBench,
Video-Holmes, and LongVideoBench, VAMR achieves the highest accuracy overall and the fewest
reasoning rounds among iterative methods. On LVBench, it reaches 62.1% accuracy, exceeding VideoARM by 4.3 points while reducing
reasoning rounds and processed frames by 85.9% and 61.4%.
Read the full abstract ▾
All authors Runquan Gui, Hanzhu Chen, Zehao Wang, Hanxin Zhu, Xin Li, Zhibo Chen
Artificial Intelligence · Cross-listed from cs.RO
PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning
Changchuan Yang, Haoxuan Xu, Wenbo Chen et al. (+5 more)
Robotic manipulation often contains repeated motions whose local observations look similar at different phases. When these phases require different actions, a policy that relies mainly on the current observation may repeat completed motions or switch phases at the wrong time. To address this phase ambiguity, we present the Pseudo-
Memory Temporal Re-encoding Module (PMTRM), a lightweight plug-in module with only 7.61M parameters that encodes a bounded history of executed states and actions into a latent sequence for existing policies. To help distinguish phases, a temporal heterogeneity objective penalizes positive similarity between distant positions in this sequence, while anchor and reconstruction losses preserve information needed for action prediction. The reconstruction decoder is used only during training, leaving the temporal re-encoder to supply history to the policy at inference. We train the module progressively on synthetic sequences and
robot data, then jointly with the policy, using temporal masking to accommodate partial histories. This integration retains the original action head and action space and adds auxiliary losses to the original policy loss. Experiments with multiple policy backbones in simulation and on a real
robot show improved task success on tasks with phase ambiguity, with little additional computation.
Read the full abstract ▾
All authors Changchuan Yang, Haoxuan Xu, Wenbo Chen, Shuai Ren, Jianlong Zheng, Huarui Zhang, Tianfu Li, Guanzhong Tian
Artificial Intelligence · Cross-listed from cs.LG
PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation
Heng Li, Yong Zhang, Ning Cheng et al. (+5 more)
Vertical-domain few-shot classification remains challenging for small
language models, as limited supervision makes it difficult to acquire domain-specific decision knowledge. On-Policy
Distillation (OPD) can improve teacher-guided adaptation by supervising student-generated rollouts, while GRPO-based reinforcement learning can further refine downstream predictions. However, existing KD-to-RL pipelines typically rely on globally fixed transition schedules, ignoring that different samples may require different amounts of teacher-guided acquisition before reward-driven refinement. We propose PIVOT (Perplexity-Informed Transition Optimization), a dynamic transition framework that routes samples between OPD and GRPO according to teacher-evaluated sequence perplexity. PIVOT moves low-perplexity samples to GRPO for reward-driven refinement while keeping high-perplexity samples under OPD for continued domain knowledge acquisition. Experiments on Banking77 and HWU64 show that PIVOT consistently outperforms continued OPD and globally synchronized OPD$\rightarrow$GRPO baselines under the same number of post-warm-up student optimization steps, achieving stronger downstream performance and more stable training dynamics.
Read the full abstract ▾
All authors Heng Li, Yong Zhang, Ning Cheng, Zhigen Li, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao
Artificial Intelligence · Cross-listed from cs.CR
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
Teruki Sano, Minoru Kuribayashi, Masao Sakai et al. (+4 more)
Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a claimant possesses a model identical to a remotely deployed model without directly accessing the reference model. However, for probabilistic AI models, repeated executions of the same query may produce different outputs and therefore different verification observations. This raises the question of how such
stochastic evidence should be accumulated and how much evidence is required for reliable verification. In this work, we characterize statistical separability in TP-CRIV of probabilistic AI models. Specifically, we relate challenge-wise behavior of matching and non-matching provers to verification-level separability. The characterization explicitly describes how the numbers of independent challenges and repeated responses affect detection performance and enables the verification budget required for a target AUC to be estimated. We instantiate the proposed characterization for LLMs using open-ended challenges. The experiments demonstrate matching-non-matching separation, close agreement between theoretical and empirical AUCs, and consistent estimates of the minimum verification budgets. These results provide a statistical basis for relating probabilistic model behavior to verification-level separability and the evidence required for third-party verification.
Read the full abstract ▾
All authors Teruki Sano, Minoru Kuribayashi, Masao Sakai, Shuji Isobe, Eisuke Koizumi, Zhang Zhang, Satoru Matsumoto
Artificial Intelligence
Social Pain Disrupts Emotion-Action Brain-State Dynamics in Adolescents with Non-Suicidal Self-Injury
Ying Xu, Xiaojun Liang, Li Zhang et al. (+4 more)
Non-suicidal self-injury (NSSI) is prevalent among adolescents with depression, but the rapid
brain-state dynamics linking social distress to maladaptive behavior remain unclear. We combine an experimental pain paradigm, electroencephalography (
EEG) microstate analysis, and interpretable deep sequence modeling to investigate NSSI-related neurodynamics in 106 adolescents with depression, including 67 with NSSI (DN+) and 39 without NSSI (DN-), during social pain, physical pain, and resting-state conditions. A model integrating disease-specific, domain-
adversarial, consistency, and contrastive learning captures higher-order dependencies in microstate sequences. Social pain yields the strongest NSSI discrimination, with 68.55% accuracy, outperforming the best baseline by 8.94% points. Model interpretation and conventional microstate analyses reveal weakened bidirectional transitions between MS3 and MS5 in DN+ adolescents during social pain. Source reconstruction associates MS3 with emotional/interoceptive processing and MS5 with action preparation, suggesting disrupted emotion-action coupling. Time-resolved analyses show greater early-to-middle action-state recruitment and later emotion-state recruitment in DN+ adolescents. In DN- adolescents, MS5-to-MS3 dynamics mediate associations between social-evaluation sensitivity and affective outcomes, whereas this mediation is absent in DN+; conversely, MS3-to-MS5 transitions are associated with greater negative affect in DN+. Together, these findings identify disrupted emotion-action coupling as a key neurodynamic mechanism underlying altered social pain processing in adolescents with NSSI, providing a mechanistically interpretable neural signature for objective identification of NSSI.
Read the full abstract ▾
All authors Ying Xu, Xiaojun Liang, Li Zhang, Yixuan Yuan, Gan Huang, Yongjie Zhou, Zhen Liang
Artificial Intelligence · Cross-listed from cs.CV
CARE: Constrained Attention Refinement for Fine-Grained Visual Classification via Teacher-Student Distillation
Ruibo Wen, Hang Shao and Yiming Lei
Fine-grained visual classification requires models to recognize subtle local traits while exposing the visual evidence behind their predictions. Class-specific
attention pathways provide a natural basis for interpretable recognition, but their constrained prediction structure limits discriminative capacity and underuses intermediate representations from strong pretrained backbones. To address this problem, we propose CARE, a constrained
attention refinement framework for interpretable fine-grained recognition via teacher-student
distillation. CARE keeps the final prediction and explanation within a class-specific
attention student, while introducing a training-only auxiliary query teacher that reads selected intermediate DINOv2 layers with learnable queries. The teacher fuses multi-level representations and transfers logit-standardized class-discriminative knowledge to the student. To further refine the explanation pathway, we design diversity and sparsity terms to regularize student
attention heads, reducing redundancy and encouraging compact trait localization. Experiments on CUB, Oxford-IIIT Pet, Stanford Dogs, and Stanford Cars show that CARE achieves strong classification performance under an interpretable frozen-backbone setting, reaching 78.5% Top-1 accuracy on CUB. Faithfulness analysis with insertion and deletion metrics further indicates that the top-ranked
attention regions retain class-relevant evidence for explanation.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
SP-DocReader: Difference-Aware Self-Play for Precise Document OCR
Wenjie Liao, Xiaohui Song, Liangjie Zhao et al. (+1 more)
Accurate page transcription remains difficult for
vision language models under limited input and training budgets. We present SP-DocReader, a self-play framework for optical character recognition (OCR) that targets residual errors after supervised fine-tuning. Reading Discrepancy Masking aligns reference and generated model
tokens through a longest common subsequence, then scores unmatched positions with their full conditioning prefixes. Focused Fidelity Loss adds direct negative log-likelihood supervision at unmatched ground-truth positions. Only the OCR module is trained, while the backbone remains frozen. We derive the combined gradient to distinguish relative score optimization from direct supervision. Compared with SFT-2, SP-DR-3 reduces Vary-600K character error rate on both backbones. On Qwen3-VL-4B, it reduces character error rate by approximately 54 percent and improves DocVQA Average Normalized Levenshtein Similarity (ANLS) by 3.7 points. These results show the value of focusing self-play training on the discrepancies that remain after supervised fine-tuning.
Read the full abstract ▾
All authors Wenjie Liao, Xiaohui Song, Liangjie Zhao, Haonan Lu
Artificial Intelligence · Cross-listed from cs.CV
Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery
Jingbo Yue, Bruce Coburn, Jinge Ma et al. (+2 more)
Single-image nutrition estimation can fail silently when visible foods are missed. Even when a food is correctly identified, its proposed region may not support portion estimation. We propose a framework that uses
multimodal large
language models (MLLMs) to inventory visible foods and separately verify food identity and whether each proposed 2D region supports portion estimation. One whole-image review uses these verification results to identify unresolved gaps and omitted foods, triggering at most one targeted recovery pass. Recovered regions are re-verified without access to the recovery
prompt, then reconciled into a final item set for nutrition estimation. The framework requires no task-specific fine-tuning. Matched evaluation on common valid-output samples shows that item-level grounding improves mass accuracy across all tested settings and energy accuracy relative to an adapted
retrieval baseline, with item-identity precision and recall also improving, while post-recovery visual coverage is assessed separately at inference time without ground-truth annotations.
Read the full abstract ▾
All authors Jingbo Yue, Bruce Coburn, Jinge Ma, Jui-Feng Chi, Fengqing Zhu
Artificial Intelligence · Cross-listed from cs.LG
ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis
Weiwei Ma, Xiaobing Yu, Peijie Qiu et al. (+5 more)
Clinical diagnosis is inherently sequential: clinicians escalate from cheap to costly tests only when additional evidence is expected to resolve diagnostic uncertainty. We present ActiveMedAgent, a framework that brings this cost-aware sequential logic to
multimodal medical AI. Given a frozen, API-accessed
vision-
language model, ActiveMedAgent tracks probability distributions over candidate diagnoses and scores each acquisition by its per-step diagnostic utility minus cost. A lightweight MLP controller is then trained offline on these scored trajectories, learning when to request additional evidence and when to commit. Across three commonly used
benchmarks, trajectory-based policy learning consistently outperforms both unguided acquisition and full-modality baselines. Notably, we identify an information overload effect. In 175 cases, the
agent produces a correct diagnosis with fewer channels while the full-modality baseline fails, showing that learning what to omit can be as important as learning what to acquire.
Read the full abstract ▾
All authors Weiwei Ma, Xiaobing Yu, Peijie Qiu, Jin Yang, Zhaoqi An, Xuanzhao Dong, Xiaoqi Zhao, Xiaofeng Liu
Artificial Intelligence · Cross-listed from cs.CL
SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning
Kenan Tang, Andong Hua, Chengxuan Qian et al. (+2 more)
Supervised fine-tuning (SFT) equips large
language models (LLMs) with specialized capabilities, but often comes at the cost of forgetting the general capabilities of their parent models (i.e., the pretrained models before fine-tuning). This trade-off is especially limiting for queries that require both specialized and general capabilities. We introduce SFT-as-context, a training-free method in which the parent model uses the SFT model's response as context to answer the query. This allows the parent model to acquire fine-tuned capabilities from the SFT response through in-context learning while preserving its own general capabilities. Across 19 parent-SFT model pairs and 11
benchmarks, SFT-as-context remains close to the SFT models on fine-tuned capabilities, with gaps of only 2.2 and 2.1 percentage points on AIME 2024 and LiveCodeBench and 2.0 macro MAE on NutriBench-English, while staying within 2.2 percentage points of the parent models on general capabilities on average. Remarkably, it can solve queries requiring both fine-tuned and general capabilities, even when neither the parent nor SFT model succeeds alone. This approach also extends beyond parent-SFT pairs: responses from a small open-source SFT model can improve a strong closed-source LLM, outperforming either model alone. Furthermore, we use a
Bayesian framework to derive theoretical guarantees that bound the error of SFT-as-context relative to the SFT model on fine-tuned capabilities and to the parent model on general capabilities. In addition, we visualize the
attention weights and find that the parent model attends more to useful SFT responses and less to irrelevant ones, suggesting that selective
attention helps the parent model use the SFT response through in-context learning.
Read the full abstract ▾
All authors Kenan Tang, Andong Hua, Chengxuan Qian, Saket Tiwari, Yao Qin
Artificial Intelligence
GameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary
Qirui Zheng, Zhengteng Lin, Yunyi Xiao et al. (+7 more)
Game commentary is an open-ended generation task requiring
multimodal perception, strategic
reasoning, and contextual knowledge. Existing AI-Generated Game Commentary (AI-GGC) studies remain fragmented across games, modalities, and evaluation protocols, while overlap-based or holistic evaluators fail to capture the functional heterogeneity of commentary. We introduce GameCommBench, a unified
benchmark spanning board games, sports, and esports, with commentary aligned to heterogeneous game contexts and annotated by commentary type. We further propose Type-Aware Commentary Evaluation (TACE), a structured framework for evaluating different types of commentary. We then validate TACE for reliability and human agreement, and use it to
benchmark representative AI commentators. Results reveal non-uniform capability profiles, with live observation and strategic analysis emerging as major bottlenecks. Together, GameCommBench and TACE provide a diagnostic foundation for comparable and interpretable AI-GGC evaluation.
Read the full abstract ▾
All authors Qirui Zheng, Zhengteng Lin, Yunyi Xiao, Junhao Li, Keyuan Cheng, Xingbo Wang, Yongyi Wang, Lingfeng Li, Yunlong Lu, Wenxin Li