Artificial Intelligence
When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate
Duofeng Xu, Bryan Hooi and Dandan Qiao
Multi-
agent debate (MAD) is often used to improve large
language model (LLM)
reasoning, but sequential debate is rarely a neutral aggregator of
agents' opinions. We show that sequential MAD suffers from a pronounced first-speaker bias:
agents disproportionately shape the final answer when they speak first. As a result, placing a stronger model after weaker ones can substantially offset its
reasoning advantage. We then focus on the disadvantaged strong-
agent-last setting and ask whether personality prompting can mitigate this imbalance. Drawing on the Big Five model, we study agreeableness and extraversion as behavioral interventions applied to either the strong or weak side. We find that their effects are trait-specific. Influence consistently shifts in the direction of lower agreeableness, and assigning low agreeableness to the stronger
agent helps restore its lost influence and improves final accuracy. Extraversion, by contrast, produces less systematic changes in influence and accuracy, with its clearest effect appearing in
agents' verbosity. These findings show that effective MAD design depends not only on model capability, but also on how speaking order and induced interaction behavior shape the debate process.
Read the full abstract ▾
Artificial Intelligence
Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided Steering
Litian Liu, Qiqi Hou, Yubing Jian et al. (+5 more)
Recent work on
hallucination detection in large
language models has shown that, for a fixed pre-trained model and
reasoning task, it is possible to estimate the model's confidence in the correctness of its outputs. Such uncertainty estimates have primarily been used to improve truthfulness by detecting or filtering confabulations. In this work, we ask whether these signals can instead be used more proactively to directly improve the accuracy of model-generated answers. We propose USteer, a simple, training-free steering mechanism that adjusts a model's layer-wise activations during inference using the gradient of a confidence measure with respect to the activations. This procedure nudges generation toward outputs with lower uncertainty at inference time, without modifying model parameters or requiring additional supervision. We show that this approach consistently reduces
hallucination across a range of tasks, demonstrating that confidence signals can be leveraged not only for detection, but also for effective inference-time control of model behavior.
Read the full abstract ▾
All authors Litian Liu, Qiqi Hou, Yubing Jian, Reza Pourreza, Mohammad Ghavamzadeh, Roland Memisevic, Yao Qin, Hong Cai
Artificial Intelligence
Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting
Liang Twist Shan, Tianyu Hu, Hao Yan et al. (+1 more)
Large
language models (LLMs) have been rapidly improving in long-context tasks, powered by Chain-of-Thought (CoT)
reasoning. However, the internal mechanisms underlying this improvement remain unclear. We investigate these mechanisms through a needle-in-a-haystack (NIAH) counting task, where an LLM is asked to count the number of records dispersed in a long text. Across twelve model comparison groups, Thinking (or
reasoning) improves counting accuracy over Non-thinking, with pronounced gains at larger counts. This motivates our mechanistic analysis, which identifies two contrasting mechanisms: (i) broad
retrieval, where Non-thinking models broadly attend to multiple needles; (ii) targeted
retrieval, where Thinking models use enumeration in CoT traces to successively retrieve needles. Targeted
retrieval concentrates
attention on individual needles and is accompanied by more compact internal representations. Moreover, causal intervention analysis suggests that Thinking models use the CoT trace to maintain and update an internal counter as needles are successively retrieved, even without explicit numbering. In small controlled experiments, both
retrieval mechanisms and counter states emerge under standard autoregressive training. Together, our results connect long-context
retrieval with representation geometry of counting, supporting a state-tracking account of CoT
reasoning.
Read the full abstract ▾
All authors Liang Twist Shan, Tianyu Hu, Hao Yan, Yiqiao Zhong
Artificial Intelligence
Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model Outputs
Wenhao Liang, Lin Yue, Wei Emma Zhang et al. (+3 more)
Routing signals of modern
vision transformers – expert gates,
attention-residual weights and halting scores – often improve probes that predict whether the model is correct, and the improvement is commonly read as evidence that routing carries information about errors beyond the model's outputs. We test this inference directly: keeping real output-routing pairs, we redraw correctness labels from a frozen output-only generator fitted on disjoint data, so that routing is uninformative by construction. Under this exact label null, a width-matched MLP comparison still reports a routing gain in 51.3% of confidence-only evaluations (308/600), while a linear comparison reports none. Holding each training trajectory fixed on a six-model panel and selecting the checkpoint by validation log loss instead of validation accuracy removes the detections (50/120 to 0/120, and 83/120 to 0/120 in an independently implemented probe), identifying accuracy-based checkpoint selection as the cause; across all output views the raw detection rate falls from 27.5% (528/1,920) to zero observed detections. The repaired comparison is not sensitive, detecting an implanted signal of about 0.005 nats in 0/20 replicates in each of two matched settings, whereas a conditional permutation test built on an estimated routing law detects it in 11/20 and 10/20 and rejects rarely under the null. On real correctness labels, the conditional analysis yields model-relative evidence in five DeiT
attention-residual families; in four it persists under two specified variants of the conditional law, and no family passes an additional noise criterion. Fitting a better probe and testing for incremental information are different problems, and each needs its own validation.
Read the full abstract ▾
All authors Wenhao Liang, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen
Artificial Intelligence · Cross-listed from cs.LG
Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score Matching
Yang Chen, Yitan Zhang, Michael Witbrock et al. (+1 more)
Inverse Reinforcement Learning (IRL) aims to recover a reward function that explains expert demonstrations. Existing IRL methods typically rely on a bi-level optimization procedure that alternates between reward learning and policy optimization, leading to substantial computational burden and training instability. In this work, we introduce a different route that eliminates policy optimization entirely by leveraging
diffusion policies. Our key insight is that a
diffusion policy encodes the action-gradient structure of the optimal soft Q function, enabling reward learning to be cast as a sequence of value recovery problems, thereby allowing us to bypass reward-policy loops inherent in prior IRL methods. Specifically, our method proceeds in three stages: (I) recovering the optimal soft Q function via action-gradient matching and estimating the corresponding soft value function (LogSumExp of Q values) in a way inspired by Gumbel regression; (II) calibrating these soft values by inferring a state-dependent offset; (III) extracting the reward by enforcing Bellman consistency. This leads to Loop-Free Inverse Reinforcement Learning (LFIRL), a fully offline
algorithm that operates in a simple, loop-free, and sequential manner. LFIRL is simple to implement and significantly improves training efficiency while maintaining strong reward recovery performance. Empirically, across Maze, Franka Kitchen, Adroit Hand Pen, and Push-T
benchmarks, LFIRL achieves 2-3x speedup over the fastest baselines, while matching or surpassing state-of-the-art methods in reward recovery quality.
Read the full abstract ▾
All authors Yang Chen, Yitan Zhang, Michael Witbrock, Shuyue Hu
Artificial Intelligence · Cross-listed from cs.CR
APTInvestBench: Evaluating Autonomous APT Investigation under Varying Telemetry
Yu Wang, Shuhao Li, Tao Yin et al. (+4 more)
Large
language model (LLM)
agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads into evidence for intrusion scoping and response. Yet success under one telemetry setting does not establish robustness to changes in log collection, retention, or sampling. We introduce APTInvestBench, a
benchmark for evaluating cross-telemetry robustness in autonomous APT investigation. It comprises 370 cases across seven SOC-inspired conditions, derived from 56 report-informed attack reconstructions with 16.4 million log records.
Agents investigate unverified leads and submit reports with record-level citations. Fixed action-level support requirements track sufficient evidence across available logs, query returns, and formal citations, separating telemetry limitations from acquisition and reporting gaps. Across eleven LLMs,
agents acquire sufficient evidence for 44.3% of recoverable attack actions on average, while formal citations support only 25.0%. More importantly, aggregate coverage can conceal substantial instability: from Full to endpoint-only telemetry, coverage declines by only 1.6 percentage points, yet 35.5% of previously covered actions lose sufficient citation support despite remaining recoverable. Across four frameworks, such losses persist even when registered supporting records remain unchanged. APTInvestBench provides reusable investigation environments and diagnostic evaluation for identifying these gaps and developing more reliable defensive
agents.
Read the full abstract ▾
All authors Yu Wang, Shuhao Li, Tao Yin, Ziyang Li, Xueying Zhao, Peishuai Sun, Jiang Xie
Artificial Intelligence · Cross-listed from cs.RO
DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?
Aditya Ramabadran, Simon Mahns and Tobias Gessler
Frontier models excel at many digital
benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present DrivingBench, to our knowledge the first
benchmark where general-purpose
vision-
language models must drive a real car. Through three tools, the models see camera frames from a Toyota Corolla and directly command its steering and velocity around a parking lot cone course at low speeds. The car may continue moving while the model thinks and new commands replace the currently running one, so inference latency is part of the task, testing the models' abilities to observe, act, monitor, recover, and complete a long-horizon objective under such constraints. We
benchmark GPT-6 Astra, Claude Fable 5.1, GPT-5.6 Sol, and Grok 4.6 in vendor-native harnesses (Codex, Claude Code, Cursor) with up to three attempts each in one conversation; Astra is the only model to finish the course, on its second attempt, with no other attempt passing 50% of the course. Two of the four models improved materially across attempts with retained context. We also detail the design principles behind our action interface, and show how the tool output format and the framing of the task combined to determine whether models would drive at all or refuse. We release our harness,
prompts, course map, and traces with
video and telemetry for reproducibility.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation Budgets
Wenhao Liang, Liangwei Nathan Zheng, Lin Yue et al. (+4 more)
When a classifier is recalibrated from only a few thousand held-out examples, the capacity of the calibration map becomes a statistical design choice rather than a purely architectural one: a scalar map can underfit structured residual miscalibration, while a highly adaptive map can be hard to estimate reliably from so small a split. We disentangle the calibration objective from adaptive capacity and propose signal-routed temperature scaling (SRTS-BCE), a 10-parameter, argmax-preserving calibrator that cross-fits a correctness-risk score over six logit statistics and fits one top-label-BCE temperature per $K=3$ risk groups, recovering TvA-TS as its $K=1$ limit. On fine-tuned CIFAR-100 / ViT-B/16, SRTS-BCE reduces $\mathrm{ECE}_{15}$ from 1.65 (scalar TvA-TS) to 0.96, matching the higher-capacity SMART+BCE head (0.95) at the full calibration budget. The two regimes separate as the budget shrinks: at $n=250$ SRTS-BCE beats SMART+BCE on all three CIFAR-100 backbones (the seed-to-draw hierarchical interval excludes zero), whereas the flagship comparison against the scalar remains directional. A protocol-frozen Tiny-ImageNet follow-up reproduces the small-budget separation and exhibits a budget-dependent ranking reversal on Swin-T; matched routing and map controls show that the effect is tied neither to the learned router nor to discrete grouping. Together the results identify post-hoc calibrator capacity as a finite-sample design choice whose preferred level shifts with the amount of available calibration data.
Read the full abstract ▾
All authors Wenhao Liang, Liangwei Nathan Zheng, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen
Artificial Intelligence · Cross-listed from cs.LG
Adaptive Self-Consistency: From Black-Box Sampling to Distribution-Valued Feedback
Jingkai Huang, Yunfan Zhang, Will Ma et al. (+2 more)
Self-consistency samples many
reasoning trajectories and aggregates their final answers, treating the LLM as a black box that returns one answer per trajectory. Yet the final answer of each trajectory is sampled from a softmax vector that is available from the model's log-probabilities. We refer to this as the grey-box setting in which each trajectory reveals this answer distribution rather than a single draw from it. We formulate efficient inference in this setting as sequential mode identification with distribution-valued observations: sample trajectories one at a time and stop as soon as the LLM's modal answer is identified at a prescribed confidence level. We characterize the asymptotic stopping rate of mode identification with distribution-valued observations exactly and show that it is never worse than the black-box rate. We then propose the ASC-D
algorithm, a betting stopping rule that attains this asymptotic stopping rate. On MMLU-Redux, ASC-D uses $46.4$–$95.6\%$ fewer trajectories than answer-only adaptive self-consistency baselines and achieves the highest fixed-budget correct-certification rate across three open-source models.
Read the full abstract ▾
All authors Jingkai Huang, Yunfan Zhang, Will Ma, Weihua Zhou, Zhengyuan Zhou
Artificial Intelligence · Cross-listed from cs.CV
On the Relaxation of Conditional Independence Assumption for Image Segmentation
Zixun Wang and Ben Dai
In semantic segmentation, a recent line of RankSEG methods directly optimizes Dice/IoU scores at inference time, improving
alignment with evaluation metrics without modifying model training. Despite its theoretical and empirical success, RankSEG relies on the restrictive Conditional Independence Assumption (CIA), which ignores crucial label correlations and therefore degrades performance in ambiguous or low-contrast scenarios. However, accounting for full label dependence is computationally prohibitive, requiring $\mathcal{O}(d^3)$ time. To address this, we replace the CIA with a Spatially Localized Dependence (SLD) structure that captures local label correlations while keeping the dependence model tractable. We further overcome the remaining computational bottleneck via a Reciprocal Moment Approximation coupled with a novel fixed-point optimization strategy that eliminates exhaustive search. The proposed
algorithm achieves a highly practical $\mathcal{O}(d \log d)$ complexity and consistently outperforms conventional argmax and CIA-based RankSEG across diverse segmentation
benchmarks. Improvements are significant in low-contrast or small-object scenarios, where label dependence offers valuable signals complementary to image information for accurate segmentation. The code of experiments is available at https://github.com/ZixunWang/RankSEG-DEP.
Read the full abstract ▾
Artificial Intelligence
Learning What to Forget: Distributional Unlearning for LLM Representation Spaces
Pinaki Mohanty, Haoran Tang, Maggie Makar et al. (+1 more)
Machine learning systems increasingly face the need to remove the influence of entire data domains, such as toxic
language, harmful behavior, or topical content, rather than isolated records. Recent work formalizes this problem as distributional unlearning: selecting a subset of a forget domain whose removal moves the training distribution away from an unwanted population while preserving proximity to the desired one. However, existing analyses often impose parametric assumptions to obtain tractable selection rules. These assumptions may be poorly suited to high-dimensional
language-model representations. We introduce Mamushi, a framework for non-parametric distributional unlearning that ranks forget examples using a probabilistic classifier whose Bayes-optimal logit equals the forget-to-retain log-density ratio (up to an additive class-prior constant). We show that thresholding the population log-density ratio yields the optimal fixed-budget selection rule for our removal–preservation objective and establish a non-asymptotic transfer guarantee relating score-estimation and threshold-calibration errors to degradation from the population-optimal selection rule. Our empirical evaluation spans real-world
datasets on toxic-
language removal and topical-domain removal regimes using different representations, with Mamushi achieving a more favorable removal–preservation trade-off than other baselines. Our work shows that Mamushi can serve as an efficient selection approach for downstream machine unlearning procedures, reducing the number of forget examples required to reach a fixed forgetting target.
Read the full abstract ▾
All authors Pinaki Mohanty, Haoran Tang, Maggie Makar, Rajiv Khanna
Artificial Intelligence
Tianchi Liao Tianchi_Liao, Lele Fu, Sheng Huang et al. (+3 more)
Multimodal federated learning (MFL) has emerged as a pivotal paradigm for leveraging distributed data to enhance model performance. However, existing methods predominantly rely on idealized assumptions of model homogeneity and balanced modality distributions, rendering them ill-suited for practical scenarios characterized by heterogeneous client architectures and severe modality imbalance. To address these challenges, we propose a
Multimodal Federated learning Prototype-guided Bilateral
Alignment (MFedPBA) framework. MFedPBA facilitates robust knowledge synergy through a dual
alignment mechanism: (i) at the feature level, it aligns heterogeneous feature spaces via a projection encoder optimized by contrastive learning and the Gromov-Wasserstein distance; (ii) at the decision level, it employs an
entropy-weighted aggregation of naturally aligned logit prototypes. This novel design achieves robust MFL by jointly tackling heterogeneous feature spaces and collectively aggregating decisions. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines under conditions of model heterogeneity and modality imbalance.
Read the full abstract ▾
All authors Tianchi Liao Tianchi_Liao, Lele Fu, Sheng Huang, Qing Hu, Hong-Ning Dai, Chuan Chen
Artificial Intelligence
How Much Can Reliability Drift Under a Fixed Confidence Distribution?
Wenhao Liang, Lin Yue, Wei Emma Zhang et al. (+3 more)
A classifier's conditional accuracy can change while its confidence distribution stays exactly the same. We study the worst-case movement of the reliability relation under
covariate shifts that preserve the distribution of the confidence score, constraining the reweighting within each confidence level by a $\chi^2$ budget; the resulting worst case, as a function of the budget, is a fragility profile. On an interval of budgets that can be computed from the source distribution, the profile equals exactly the square root of the budget times the within-level variance of the correctness propensity – the grouping-loss term of calibration-refinement decompositions. Beyond this interval the profile is governed by the tails of the propensity law, and the entire upward profile determines the centred within-level law; consequently, calibration residual and grouping variance do not determine fragility in general, though they do when labels and predictions are deterministic. Since the propensity is not observed, we restrict reweightings to a learned finite readout within confidence bins, bound the part the restriction misses by the grouping variance remaining inside readout
cells, estimate the restricted profile with role-separated labels, and provide a separate split-sample lower confidence bound. On ImageNet this bound is positive in both splits for four of six primary classifiers and nine of twelve additional ones as released, and for three of eighteen after temperature scaling. Held-out drift under optimised reweightings fitted without evaluation labels tracks the estimated profile; an exploratory label-permutation diagnostic yields near-zero agreement for this statistic while largely reproducing the correlation observed for unsigned random reweightings.
Read the full abstract ▾
All authors Wenhao Liang, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen
Artificial Intelligence
Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited Budgets
Priyanath Maji and Spandan Ghose Chowdhury
Evaluating interactive
agents is expensive.
Agent behavior is
stochastic, so reliability must be measured over repeated trials, but failures are rare and differ widely in how much they matter. Standard
benchmarks spend this budget uniformly: a read-only lookup is sampled as often as an irreversible payment action. We instead formulate evaluation as a sequential allocation problem. Given a fixed trial budget and a set of scenarios whose failure behavior is unknown, which scenarios should be run, and run again? We propose a risk-aware contextual Thompson Sampling policy that combines a pre-execution scenario context vector and a fixed impact score with the failure outcomes observed during evaluation, and we test it by offline replay over 70 $\tau$-bench airline scenarios and 824 recorded trials. Our main result is at the smallest budget: with only 50 trials ($6\%$ of the corpus), the policy recovers $86\%$ of the impact-weighted failures an oracle could find, compared to $25\%$ for uniform allocation. It discovers $3.5\times$ more impact-weighted failures (215.4 vs. 62.2) with the same number of trials, delivers $5\times$ the discovery per dollar, and cuts the budget wasted on scenarios that never fail from $34\%$ to $2.8\%$. The rest of our analysis demonstrates and qualifies this result: a budget sweep shows the advantage shrinks as the budget approaches the corpus size, and paired significance tests show that scenario context helps mainly at small budgets while posterior-based exploration helps at moderate ones. Risk-aware adaptive allocation therefore helps most exactly where evaluation budget is scarcest.
Read the full abstract ▾
Artificial Intelligence
Composing Task-specific Agent Harnesses at Test Time with Reusable Primitives
Peng Kuang, Haibo Jin, Dehao Wu et al. (+4 more)
Agent harnesses govern how large
language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting
agent performance. However, the value of each harness mechanism can differ across heterogeneous tasks: a mechanism that improves one task may impose overhead or context distraction on another, leading to the suboptimality of a global harness. We characterize this suboptimality as a mismatch induced by fixed mechanism choices, motivating task-specific harness construction. Nonetheless, generating harness code for each task introduces generation and debugging costs, with execution risks that can compound as more mechanisms are generated. To address those challenges, we introduce Harness Primitives, reusable harness mechanisms with clear application scope and composition contract mined from failed task trajectories. Based on Harness Primitives, we propose STITCH, a framework that Selects suitable primitives given Task Information and compiles them into Task-speCific Harnesses at test time. This separation enables task-specific harnesses without generating or repairing mechanism code at test time. Extensive experiments demonstrate that STITCH not only improves harness adaptability and robustness, but also scales with the primitive library size, boosting task success rates by up to 12 points over fixed harness baselines, surpassing human-designed harnesses like Codex CLI while maintaining a minimal test-time harness composition overhead of only 2.7%, 638 times more efficient than generating task-specific harnesses from scratch. Ultimately, our work demonstrates that building task-adaptive harnesses can be beneficial for completing diverse tasks and that building reusable primitives can be a promising path towards this goal.
Read the full abstract ▾
All authors Peng Kuang, Haibo Jin, Dehao Wu, Feiyang Deng, Xiaopeng Yuan, Jerry Wang, Haohan Wang
Artificial Intelligence · Cross-listed from cs.LG
Unlearning Deceptive Behaviors in LLMs with Contrastive Forget Sets
Haoran Tang and Rajiv Khanna
Large
language models often know the truth and say otherwise: a model that answers correctly when asked neutrally will affirm a user's mistaken belief, or misstate a fact its system
prompt wants hidden, once the context rewards it. Such deception is a behavior conditioned on context, not knowledge, yet machine unlearning, the natural tool for removing a behavior from the weights, is built to forget facts that a deceptive model still needs. We propose to unlearn when a model deceives rather than what it knows, with a contrastive forget unit built from the model's own realized deceptions: the same question under a deception-triggering and a neutral context, admitted only where belief holds and behavior flips. Standard objectives on this unit face a dilemma. Suppression objectives such as NPO leave much of the deception in place. Target-based objectives, which distill the model's neutral behavior into the pressured context, remove it but induce context blindness: a target generated without the context teaches the model to stop reading it, eroding benign system-
prompt instructions, secret-keeping and the
reasoning a monitor inspects, a failure invisible to deception rates and capability
benchmarks. We introduce PACT, which trains toward pressure-aware counterfactual targets (the model's own honest response, with a trace that registers the pressure and resists it) while retaining the benign uses of the triggering context. On two 32B
reasoning models, PACT reduces held-out deception from over 50% to under 3% while system-
prompt adherence, secret-keeping and the
reasoning trace stay at the base model's level. On a tug-of-war score of removal against retention, PACT reaches 0.94 and 0.86, against at most 0.77 and 0.60 for any baseline. Like removed knowledge, removed deception is shallow under relearning, and terms that simulate the attacker hold it only at a cost in context use.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from q-bio.GN
CellMSA: Context Modeling for Single-Cell Representation Learning
Suyuan Zhao, Minghao Liu, Yizhen Luo et al. (+1 more)
Single-
cell transcriptomics enables profiling of cellular states at unprecedented resolution, but its high dimensionality, sparsity, and technical batch effects pose significant challenges for representation learning. Existing single-
cell foundation models typically encode each
cell independently or only model
cells from the same batch for denoising, thereby underutilizing the rich relational information across batches and
cell types to model gene expression patterns. We argue that single-
cell models can benefit from more informative
cell-context modeling. By comparing consistency and variation across
cells, models can capture fine-grained gene-gene dependencies associated with
cell states, which are essential for learning high-quality representations. Inspired by the use of multiple sequence
alignment (MSA) context in
protein modeling, we propose CellMSA, a single-
cell representation learning framework that introduces an MSA-inspired inductive bias into transcriptomic modeling. For each target
cell, CellMSA retrieves relevant
cells from different batches and biologically related
cell types as context, and summarizes cross-
cell patterns into a context-dependent gene-pair representation. This representation is then injected into a pair-aware target-
cell encoder for fine-grained representation learning. We pretrain CellMSA on a large-scale human single-
cell corpus of approximately 109 million
cell observations, including 65.6 million primary observations. Experiments show that our framework consistently outperforms existing methods across multiple
benchmarks. Code is available at the following repository: https://github.com/PharMolix/CellMSA.
Read the full abstract ▾
All authors Suyuan Zhao, Minghao Liu, Yizhen Luo, Zaiqing Nie
Artificial Intelligence · Cross-listed from cs.HC
Characterizing Questioning Patterns and Student Engagement Through Contextual Analysis of Real-Time Classroom Interactions
Rohit Sharma, Pavani Ayinampudi, Aditya B.M.V. et al. (+5 more)
Real-time classroom polling is now routine, yet the data it produces is usually read narrowly, as a correctness score or a headcount. Such readings say little about what a poll is doing within a lecture or how it shapes engagement. This is particularly relevant for short-response formats such as True/False, where the same question format can be used to test recall, check comprehension, or direct students'
attention to a deliberately misleading statement. This study asks whether a poll's answer and instructional function can be determined by reading it against its lecture transcript, what cognitive levels of Bloom's taxonomy and instructional-function clusters the corpus contains, and how student engagement relates to answering correctly. We analyse a naturalistic corpus of 47 live sessions over 39 days, comprising 604 poll questions and 340,668 responses from 2,807 learners, most items True/False, read against time-aligned lecture transcripts and attendance. Reading each poll in context proves essential: the answer to 89% of polls is locatable in the lecture, and a recurring
attention-checking device is visible only through context. Questioning is overwhelmingly lower-order and falls into seven instructional functions, and a poll's response follows its function rather than its wording. Engagement is broad but concentrated, and the class majority answers correctly 88.5% of the time, though a small set of high-consensus yet incorrect answers cannot be detected by agreement alone. An independent survey of 579 students agrees on what the polls are and on their participation, but reveals a gap between perception and reality: students cannot judge their own correctness, and the polls they find hardest are not those they answer worst.
Read the full abstract ▾
All authors Rohit Sharma, Pavani Ayinampudi, Aditya B.M.V., Jinal Gupta, Prakash Hegade, Sakshi Sharma, Meenakshi V, SRS Iyengar
Artificial Intelligence · Cross-listed from cs.LG
DAMPER: Return-Prioritized Gradient Control for Smooth Policies
Seokmin Ko, Taewon Goo and Kihyuk Hong
Actor-critic methods achieve strong performance in continuous control, but their policies can produce highly oscillatory actions. A common remedy is to add auxiliary smoothness losses. However, their contribution can be negligible when their gradients are small relative to the native actor gradient. Moreover, existing methods often combine multiple auxiliary losses, complicating loss balancing without necessarily improving the return-smoothness trade-off. We introduce DAMPER (Direction-Aware Magnitude-Controlled Projection with Explicit Return Priority), which combines the native actor gradient with a temporal-consistency gradient through conflict-conditioned projection and adaptive magnitude control. It removes the auxiliary component opposing the actor gradient and scales the retained temporal direction relative to the actor gradient norm, preserving positive
alignment with the native actor gradient. Experiments with TD3 and SAC on six continuous-control tasks show reduced action oscillation relative to the native
agents in all 12 task-backbone pairs and the best oscillation score among the compared methods in eight, with task-dependent return trade-offs.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs
Wenyu Chen, Li Wang, Chuanchao Zang et al. (+5 more)
Video Multimodal Large
Language Models (
Video-MLLMs) support
reasoning over
video inputs, yet remain vulnerable to jailbreak attacks that elicit policy-violating responses. Existing
video jailbreaks primarily manipulate how harmful queries are visually presented, thereby treating
video merely as a carrier. Consequently, the surrounding
video scenario remains unexplored as a contextual attack surface. In this paper, we show that the same harmful query can elicit different safety responses when placed in different
video scenarios. To systematically exploit this vulnerability, we propose SceneJail, an adaptive black-box jailbreak framework with two coordinated components. Adaptive Scenario Construction dynamically searches for a surrounding scenario that is contextually compatible with the harmful query. Scenario-aware
Prompt Search uses black-box response feedback to search for textual guidance tailored to the selected scenario. Extensive evaluations on the HADES and SafeBench
datasets across eight
Video-MLLMs, including two proprietary models, GPT-4.1 and Gemini3.5-Flash, demonstrate the effectiveness of SceneJail. SceneJail-F, which presents the complete query persistently, achieves average attack success rates (ASR) up to 91.5%, outperforming the strongest baselines by 29.1 percentage points. Furthermore, SceneJail-S, which distributes the query across successive frames, remains highly robust against current defenses, retaining a 72.3% ASR even under strict image filtering.
Read the full abstract ▾
All authors Wenyu Chen, Li Wang, Chuanchao Zang, Xiangtao Meng, Xinyu Gao, Jianing Wang, Zheng Li, Shanqing Guo
Artificial Intelligence · Cross-listed from cs.SD
FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs
Shivam Saini, Eric Bezzam, Georg Götz et al. (+5 more)
Far-field automatic
speech recognition(ASR) degrades under reverberation, noise, and talker motion, yet the
benchmarks that drive model selection emphasize close-microphone
speech. We present FFASR, a held-out corpus of 15,637 utterances and an open leaderboard spanning nine conditions, each varying a single acoustic factor: anechoic near-field
speech, a measured-versus-simulated office-lab pair, static far-field mixtures at high/mid/low signal-to-noise ratio(SNR), and moving-talker variants at matched SNR. Dry
speech from 15 talkers is convolved with hybrid wave/geometrical-acoustics room impulse responses from 14 furnished rooms; because the
speech is newly recorded and the test waveforms are never released, the corpus resists training-data contamination. Across contemporary systems, mean word error rate (WER) rises from 4.4% near-field to 41.3% in the static low-SNR condition; a moving talker adds a small but consistent penalty at matched SNR; and on the office-lab pair, measured and simulated WER agree to within about 1.7 pp on average. These results support high-fidelity simulation as a scalable proxy for measured far-field evaluation under the conditions we test.
Read the full abstract ▾
All authors Shivam Saini, Eric Bezzam, Georg Götz, Alessia Milo, Steinar Gu{\dh}jónsson, Konstantinos Gkanos, Finnur Pind, Daniel Gert Nielsen
Artificial Intelligence · Cross-listed from cs.LG
Unmerge: Efficient Machine Unlearning via Task Arithmetic
Haoran Tang, Andrew Tan and Rajiv Khanna
Approximate machine unlearning seeks to remove the influence of a forget set from a trained model without full retraining. Existing gradient-based methods require data-dependent hyperparameter search, struggle when forget and retain knowledge are entangled, and offer little insight into where unlearning actually happens inside the network. We recast unlearning through the lens of task arithmetic: if finetuning produces a merged task vector $\tau_m$ that combines learning on forget and retain sets, unlearning is the inverse operation that subtracts a learned forget component $\tau_F$ to recover the retain task vector $\tau_R$. The forget signal is concentrated: at every layer, forget activations lie in a subspace spanned by a handful of dominant directions, so we factorize $\tau_F$ in a low-rank forget basis, which is faithful up to a small tail-
eigenvalue residual and limits how far the correction can perturb retain. We then optimize three intuitive goals (match the merged vector inside the forget span, suppress leakage into the retain span, and bound the correction size) that provably bound forget leakage and retain damage in activation space. The resulting
algorithm, Unmerge, is fast and powerful: on class-level unlearning with ResNet-50 on CIFAR-100 and Tiny ImageNet, it improves Tug-of-War by up to ~24% over a baseline of comparable runtime and by up to ~18% over stronger baselines that run ~5x slower, keeps membership-inference exposure at the level of retraining, and shrinks the feature-distribution gap to the retrained model, where relabeling methods leave forget features cleanly separable. Further studies show that Unmerge also applies to ViT-S/16 and scales to Llama-3.2-3B. The per-layer basis geometry that drives the
algorithm also serves as a layerwise diagnostic for when and where unlearning becomes structurally hard.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Learning Continuous Neural Representation of Stochastic Hybrid Systems
Sangli Teng, Hang Liu and Koushil Sreenath
A
stochastic hybrid system (SHS) is governed by a
stochastic differential equation (SDE) describing the continuous dynamics and a Markov reset kernel triggered on the guard surface. Its probability
evolution can be described by a hybrid Fokker-Planck (HFP) equation with a partial differential term corresponding to the SDE and an integral term arising from the reset kernel. This work shows that such an SHS can be approximated by an SDE in a higher-dimensional latent space where the sample paths are continuous. The key to this result is to encode different branches of the reset kernel using auxiliary variables, transforming the resets into deterministic ones that enable topological gluing. By the
embedding theorem, the glued
manifold can then be embedded into a higher-dimensional Euclidean space. We show that the probability
evolution on the embedded image no longer requires explicit reset terms in the HFP equation. Building on this
theorem, we design a loss that matches the evolving state distributions, enabling a single latent SDE to recover the probability
evolution of the SHS without mode labeling, trajectory segmentation, or event-based simulations.
Read the full abstract ▾
Artificial Intelligence
Consistent Plan-Act for Long-Horizon Agentic Tasks
Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang et al. (+4 more)
Long-horizon agentic tasks demand strong
reasoning and efficient execution across successive interactions with dynamic environments. A common approach decouples high-level planning from low-level execution through separate planner and actor roles. To investigate coordination failures in these tasks, we
prompt both
agents for structured state assertions and compare their reports programmatically to detect explicit contradictions. Our analyses reveal systematic disagreement about the same task-relevant state facts, a phenomenon we term planner-actor state mismatch. We further find that providing
agents with task-relevant state information reduces mismatch and improves coordination and task performance. Based on the systematic analysis of the state mismatch, we propose Consistent Plan-Act (ConPAct), which feeds detected contradictions back to both
agents to form consistent state interpretations and fine-tunes them on curated consistent interactions for better coordination. ConPAct improves performance across various environments and model configurations, e.g., increasing MiniGrid success rate from 38.6% to 54.4% with GPT-5.6-sol/terra as planner and actor respectively, demonstrating that state consistency can guide both inference-time correction and coordination training.
Read the full abstract ▾
All authors Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang, Yueqing Sun, Jiayuan Zhang, Qi Gu, Han-Jia Ye
Artificial Intelligence · Cross-listed from cs.LG
Right Answers, Costly Models: The Efficiency Gap in LLM-based Optimization Modeling
Zhong Li, Xin Huang, Jinhui Wan et al. (+6 more)
Optimization modeling formulates real-world decision problems as mathematical programs that solvers can use to find optimal decisions. Large
language models (LLMs) can automate this process, but the resulting correct formulations can require substantial time and
memory to construct and solve, limiting practical scalability. Therefore, we systematically investigate whether LLMs can identify problem structure from natural-
language descriptions and apply suitable optimization modeling techniques to generate mathematical models and solver code that solve the problems correctly and efficiently. To this end, we first curate OptTips, a knowledge base of 50 expert modeling techniques in eight families. Using this knowledge, we develop OptDachshund, a multi-
agent framework that transforms problems from existing optimization
benchmarks into new tasks for evaluating LLMs' use of modeling techniques. It constructs conventional and expert mathematical models with solver code for the same task and data, providing baselines for correctness and computational cost. The resulting EfficientOpt
benchmark contains 561 expert-reviewed tasks with paired reference implementations. Evaluation of 11 representative LLMs reveals an efficiency gap on correctly solved tasks with comparable measurements: for every LLM, most generated programs take longer to solve than their expert counterparts. Within the comparable reference-size subset, 57% of programs with correct objective values and fewer variables and linear constraints have longer recorded solver times. Case studies show that different modeling techniques can achieve the same optimal value at similar recorded cost. Faster solving may not reduce execution time if the code takes longer to prepare data and build the model. LLM optimization modeling should therefore be evaluated for both correctness and computational efficiency.
Read the full abstract ▾
All authors Zhong Li, Xin Huang, Jinhui Wan, Xiangyi Wang, Shenkai Zhang, Ruiqi Chen, Wenyu Liu, Zaiwen Wen, Ziyan Luo
Artificial Intelligence
STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy Games
Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang et al. (+4 more)
Real-time strategy (RTS) games require
agents to coordinate economic development, production and construction, base defense, unit organization, and attack timing over long matches. Existing studies have applied large
language models to command decision-making in RTS games, enabling
agents to read textual game states and generate high-level plans. However, long inference latency can cause them to miss critical tactical events. The complexity and tactical diversity of full RTS matches also leave existing systems heavily dependent on manually written experience-based
prompts, with limited ability to learn continuously from past games. We present STRATA, a role-aligned hierarchical system with cross-game self-learning for Red Alert. STRATA assigns in-game strategic, logistical, and tactical decisions to a Strategic
Agent (SA), Logistics
Agent (LA), and Tactical
Agent (TA), respectively. The SA generates high-level directives based on the global game state and relevant experience cards, while the LA and TA handle logistics and tactical execution. After each match, a Review
Agent (RA) derives candidate experience from game traces, validates and revises it using evidence from subsequent matches, and compresses strategic experience supported across multiple games into concise experience cards for SA
retrieval. We evaluate STRATA through the formation of experience cards, full-match comparisons before and after learning, and experience learning against AI opponents with different play styles. Under a fixed scenario, using the learned experience cards increases the observed win rate from 30% to 100%. Sequential learning against AI opponents with different play styles also produces distinct long-term strategic experience.
Read the full abstract ▾
All authors Xinhe Tian, Xiaoyue Zhang, Ziyou Zhang, Jiacheng Li, Xiaoqiang Jin, Qianchuan Zhao, Gaochen Cui
Artificial Intelligence · Cross-listed from cs.LG
Does Learning Protein Folding Generalize to Broader Reasoning?
Yong Liu, Zhanpeng Shi, Yizhou Dang et al. (+4 more)
Large
language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them.
Protein folding is a natural testbed, because one solved structure yields thousands of exactly checkable spatial and topological statements. We ask: can learning to fold
proteins teach general models reusable
reasoning capabilities? To answer this, we build FoldingCorpus, a
protein-derived question-answer
dataset, and Fold2Reason, a recipe that post-trains on it through two complementary signals: discrete structural answers predicted via the model's native
language head, and continuous 3D geometry decoded from the same shared representations. On FoldBench, Fold2Reason achieves structure prediction scores 2.7 to 3.5 times those of Qwen3.5-9B. Beyond
protein structure prediction, it improves performance on all 10
benchmarks spanning spatial, graph, scientific, and general
reasoning, raising macro-average accuracy from 45.09% to 48.33% (+3.23 pp), with positive gains on all 10
benchmarks, while matched controls built from random, synthetic, and shuffled structure yield substantially smaller or negative gains. Our work shows that non-linguistic, structure-dense scientific data can systematically improve broad
reasoning in
language models, making a solved scientific problem a practical source of post-training supervision.
Read the full abstract ▾
All authors Yong Liu, Zhanpeng Shi, Yizhou Dang, Zhongyue Zhang, Xiaoliang Shi, Zhijian Wei, Shuangjia Zheng
Artificial Intelligence · Cross-listed from cs.SD
Audio Token Attention Is Predictable Before the Language Model Runs
Kyoungjun Park, Yunzhe Li and Lili Qiu
A large audio
language model (LALM) turns a minute of
speech into 750-1,500
tokens and prefills every one. Image-
token pruning often cuts after the
language model's first layers, where image
tokens draw little
attention. Audio
tokens draw much more
attention there, and their ranking is still far from final, so audio needs a ranking before the
language model runs. Surprisingly, the
attention an audio
token will receive across the
language model is already linearly predictable from its encoder output, before the
language model runs. A linear map, fitted in closed form without labels, predicts this all-layer
attention ranking at $\rho \geq .69$ on eleven of thirteen LALMs. Our method, Triage, cuts audio
tokens by this prediction and, on multiple choice, cuts again at layer 2, correcting the prediction with the
attention observed there. Triage sets its compression without labels, under two budgets that limit how far its output may differ from the model's own full-audio output. At the conservative budget, its word error rate and accuracy stay within .04 of full audio. At the aggressive budget, Triage beats every baseline in all twelve transcription cases. On multiple choice, at 2.2-5x compression, it outperforms DART, the strongest baseline on average, by .043 in mean accuracy. Because it cuts before the
language model, it raises the audio that fits in Qwen2.5-Omni-3B's context window from 21.8 to about 62 minutes. At its most compressive point, Triage lets one GPU serve 4x as many concurrent 5-minute streams of that model. Project page: https://audio-triage.github.io
Read the full abstract ▾
Artificial Intelligence
Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions
Sujung Kim, Seung Hwan Cho, Sangjin Park et al. (+1 more)
In finance, interpreting machine learning predictions is essential, yet the numerical outputs of explainable AI can be difficult for non-experts to understand. While large
language models (LLMs) can translate these outputs into natural
language, they may produce errors when inferring numerical changes and feature relations. We propose an LLM narrative framework for cross-sectional stock return prediction that combines temporal Shapley additive explanations (SHAP) evidence with historical regime analogs. Temporal evidence tracks changes in the normalized global SHAP importance of an XGBoost model over six months. Historical analogs are past periods with similar changes in SHAP importance, their model performance and subsequent
market returns are provided as comparative context. Using this framework, we conduct a controlled study of progressive
reasoning externalization, sequentially providing raw SHAP sequences, deterministic temporal descriptors, and feature relations. Each generated claim is verified against provenance-linked evidence. Across Qwen3, externalizing numerical and relational
reasoning improved evidence faithfulness as well as temporal and relational accuracy. Evidence faithfulness increased from 0.696 to 0.996 for Qwen3-32B-Instruct. While historical analogs did not improve structured automatic faithfulness, they received higher human-rated usefulness scores. These results suggest that externalizing verifiable
reasoning enhances narrative faithfulness and that historical context adds interpretive value.
Read the full abstract ▾
All authors Sujung Kim, Seung Hwan Cho, Sangjin Park, Young-Min Kim
Artificial Intelligence
Talk2Agent: Benchmarking Voice Interfaces for Text Agents
Terumi Chiba, Guangzhi Sun, Zheqi Yuan et al. (+1 more)
Large
language model (LLM) computer-use
agents are typically evaluated with clean written instructions, despite
speech being an increasingly popular interface for interacting with such systems.
Speech input introduces an additional failure point: transcription errors can alter task-critical entities, constraints, or targets before the
agent begins
reasoning, while conventional ASR metrics do not directly measure whether the information required for successful execution has been preserved. We introduce Talk2
Agent, a
benchmark for evaluating how effectively voice interfaces convey human-spoken instructions to LLM-based computer-use
agents. Talk2
Agent builds human-spoken versions of tasks from WildClawBench and OSWorld and evaluates a range of voice interfaces, including dedicated ASR models, audio-capable LLMs, contextual biasing, and LLM-based ontology repair. Because repeatedly executing long-horizon computer-use tasks is costly and
stochastic, we further propose an execution-free, task-conditioned evaluation framework that projects the original task grader onto
prompt-addressable intentions and measures how much task-relevant information is retained after the voice interface. On WildClawBench, Talk2
Agent's execution-free native projection provides a practical, execution-grounded measure of voice-interface quality, correlating with downstream task completion and improving Pearson correlation by 0.246 over WER/CER on 32 hours of real human
speech.
Read the full abstract ▾
All authors Terumi Chiba, Guangzhi Sun, Zheqi Yuan, Chao Zhang