Multiagent Systems
Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning
Amit Thakur and Mukesh Singhal
Open-team multi-
agent reinforcement learning studies cooperative systems in which
agents may join, leave, or be replaced during an episode. In such settings, the team return changes both because
agents choose useful actions and because the active population itself changes. Standard centralized critics and shared advantages often mix these two effects into one scalar credit signal, allowing surviving
agents to be rewarded or penalized for exogenous turnover events outside their control. We introduce turnover-orthogonal credit assignment (TOCA), a value decomposition for open teams that separates action effects, pure turnover effects, and action–turnover interactions. Under exogenous turnover, the event-conditioned value admits a centered decomposition whose event-conditioned baseline removes the pure turnover component while preserving credit for actions that make the team robust to future replacements. We instantiate this idea with a permutation-invariant centralized critic over variable-size
agent sets and event
tokens, and derive both a counterfactual per-
agent credit signal and a softly weighted interaction variant, TOCA-$\beta$, for high-variance control environments. Controlled diagnostic experiments show that TOCA improves return over event-aware MAPPO-style critics and that removing interaction credit substantially hurts performance. In a replacement-only Dynamic Spread
benchmark, TOCA-$\beta$ achieves the best mean return at high turnover rates and improves over its no-interaction ablation. These results suggest that explicitly separating turnover from action credit is a useful principle for robust learning in dynamic cooperative teams.
Read the full abstract ▾
Machine Learning
Understanding Enrichment in Reinforcement Learning
Jinwoo Kim and Shraddha Barke
When rewards are sparse, reinforcement learning with verifiable rewards (RLVR) often uses hints or intermediate guidance to generate more successful rollouts. This enrichment biases policy-gradient updates unless corrected via importance weights, but existing methods omit correction or truncate importance weights in order to avoid the high variance of correction. It thus remains unclear what exactly is gained or lost in RLVR by correcting enriched rollouts. We show, mathematically, that omitted or truncated correction implicitly reweights the defined reward, and we decompose the resulting gradient error into scale, rotation, and variance to explain their distinct effects on learning. To make correction practical, we develop a novel sequential Monte Carlo (SMC) weight correction mechanism that, under stability and particle-order assumptions, tempers the exponential compounding of standard correction variance over the length of a sample to an additive accumulation. We then apply our analysis of enrichment to interpreting the results of a fine-tune of Qwen3-1.7B on a sparse band of OpenMathReasoning, establishing a concrete mechanism of how enrichment, both corrected and uncorrected, helps avoid collapse in sparse domains. Our main contribution is to understand, in general, how enrichment and correction can affect training, as opposed to claiming that either mode of operation is superior to unenriched RL.
Read the full abstract ▾
Artificial Intelligence
DNAlign: Dynamic Null-Space Safe Alignment for LLMs
Jisheng Dang, Yushuo Zhao, Dewei Liu et al. (+6 more)
Ensuring the safe and reliable deployment of large
language models (LLMs) remains a fundamental challenge. Existing safety
alignment approaches either incur high computational cost or unintentionally disrupt the model's core knowledge, leading to degraded fluency and factual accuracy on benign tasks. This reveals a persistent trade-off between safety and utility. We propose DNAlign, a lightweight
alignment framework that integrates control-theoretic optimization with null-space projection. By treating the LLM as a dynamic system, the proposed framework introduces controllable perturbations to steer generation toward safe behavior. A key component is the projection module, which restricts these perturbations to the harmful-related subspace derived from neutral hidden states, thereby preserving general knowledge and response quality. A value function trained on human preference data adaptively optimizes the control signals to align with human safety preferences. Extensive evaluations across multiple LLM backbones demonstrate that our framework consistently reduces harmful outputs while maintaining fluency, coherence, and factual utility. It achieves superior overall performance compared to prior
alignment baselines without sacrificing generation diversity. These results indicate that the proposed framework provides an effective and practically deployable solution for safe LLM
alignment. Code is available at https://anonymous.4open.science/r/DNAlign.
Read the full abstract ▾
All authors Jisheng Dang, Yushuo Zhao, Dewei Liu, Junfeng Fang, Bimei Wang, Tiantian Rao, Hong Peng, Bin Hu, Tat-Seng Chua
Information Theory · Cross-listed from eess.SP
On the Optimality of OFDM for Aperiodic Ranging
Yifeng Xiong, Fan Liu, Ya-Feng Liu et al. (+2 more)
We study the expected aperiodic autocorrelation sidelobes of random communication symbols transmitted through a
unitary modulation
matrix. We consider proper sub-Gaussian constellations, namely those with fourth absolute moment $\mu_4<2$ and zero pseudo-variance, including the commonly used uniform square quadrature amplitude modulation (QAM) and uniform phase-shift keying (PSK) constellations. For every prescribed lag, we determine the exact minimum expected sidelobe level (ESL) and a
unitary modulation attaining it by applying a normalized inverse discrete
Fourier transform (IDFT) separately on each chain of sample indices spaced by that lag. The full orthogonal frequency division modulation (OFDM) modulation attains this minimum if and only if the lag divides the block length $N$. Combining this criterion with the complete characterization of the minimizers at lag one, we show that a
unitary modulation minimizes the ESL simultaneously over the first $r$ positive lags, called the prefix $\{1,\ldots,r\}$ with $1\le r<N$, if and only if every lag in that prefix divides $N$. In particular, simultaneous optimality over all positive lags is impossible for $N\ge 3$. We also prove that OFDM globally minimizes the partial expected integrated sidelobe level (EISL), defined as the sum of the ESLs over a selected subset of positive lags, for every such prefix. This also resolves the full EISL
conjecture when $r=N-1$.
Read the full abstract ▾
All authors Yifeng Xiong, Fan Liu, Ya-Feng Liu, Shi Jin, Jianhua Zhang
Computation and Language
How Robust Is Multimodal Claim Verification to LLM Rewriting?
Yun-Ang Wu, Xanh Ho, Andre Greiner-Petter et al. (+4 more)
LLMs are known to introduce stylistic changes into generated text, yet how these stylistic shifts affect model decisions on scientific tasks remains underexplored. In this paper, we focus on
multimodal claim verification, where the goal is to determine whether a textual claim is grounded in a given piece of evidence. We apply two rewriting strategies: natural rewriting, which simulates how researchers routinely use LLMs to polish academic text, and controlled injection, which inserts a single LLM-associated word to isolate the effect of vocabulary choice. We evaluate 11 open-weight models spanning five VLM families and ranging from 2B to 38B parameters. We find that models are robust to these modifications: most show no significant drop in accuracy, and compared to prior work on review-score manipulation, verification appears far more stable. However, consistent probability shifts do occur. Hedging-oriented conditions produce significant shifts across nearly all models, while boosting conditions show a weaker effect and general polishing conditions (e.g., grammar correction, fluency improvement) have little effect.
Read the full abstract ▾
All authors Yun-Ang Wu, Xanh Ho, Andre Greiner-Petter, Sunisth Kumar, Tian Cheng Xia, Florian Boudin, Akiko Aizawa
Robotics
PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation
Chunghyun Park, Beomjun Kim, Seungcheol Park et al. (+5 more)
World action models jointly learn to forecast world dynamics and predict
robot actions, such that the learned internal world dynamics guide accurate actions. Existing approaches typically represent the world as RGB frames or latent counterparts while predicting actions as end-effector poses or joint angles, but they often struggle to capture the 3D spatial structure and contact geometry central to dexterous manipulation. We introduce Point World Action Model (PointWAM), a 3D world action model that decomposes the world into a scene (i.e., environment) and hands (i.e., actor), and jointly forecasts both as 3D point trajectories within a shared space-time coordinate frame. This explicit, disentangled representation enables effective pre-training on large-scale human demonstration
videos without requiring any task-specific object or keypoint selection. Given a colored point cloud and a
language instruction, PointWAM predicts how the scene and hands co-evolve in 3D space over time, then retargets the forecast hand motion to
robot actions. Pre-training on human
videos improves average DexJoCo success by 56.9 percentage points, and scene-trajectory supervision adds 10.9 points over
forecasting the hands alone. With both, PointWAM surpasses the prior state of the art on ten DexJoCo tasks by 11.7 points and outperforms strong VLAs on a real
robot.
Read the full abstract ▾
All authors Chunghyun Park, Beomjun Kim, Seungcheol Park, Heeseung Kwon, Yashu Shukla, Seunghoon Sim, Jinwoo Shin, Minsu Cho
Machine Learning
To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model
Xianzhi Zeng, Jiangneng Li and Gao Cong
We show that the causality of
language models (LMs) may not be necessary nor optimal. This is the case when system behavior (denoted as $S$) is incorporated as a first-principle
Bayesian feature. Here, $S$ refers to extra dominant factors beyond the data space, and they involve coupled effects. Despite being the de facto foundation of modern architecture, recent studies indicate persistent mismatches and contradictions with causality. These issues largely stem from system behavior rather than the data distribution. We therefore propose the SBD framework, which incorporates $S$ as an irreducible component of the evidence lower bound (ELBO). SBD theoretically reveals a counter-intuitive Causality Tax phenomenon, where causality emerges as a suboptimal approximation with an additional structural error, due to the obliviousness to $S$. To address the challenge of latent variable analysis, we validate the SBD-predicted impact of $S$ via implicit measurements, theoretical-bound-guided controls, and Neural Tangent Kernel (NTK) evaluations. In particular, we construct Green Shell (GSH) to show the possibility of reducing Causality Tax. GSH is a non-causal variational family, and it replaces the sequential dependency chain of $S$ components with a divide-and-conquer partition. NTK spectra in the lazy-training regime confirm that GSH always achieves significantly tighter error bounds than causality, with $7dB+$ improvement in signal-to-noise ratio. In the relatively later stage of lazy-training, GSH further leads to superior generalization (up to $20\%$ richer multi-scale fitting capabilities). Taken together, SBD establishes system behavior as a complementary theoretical abstraction besides causality and distribution fitting, opening new research avenues such as designing and optimizing LM base models.
Read the full abstract ▾
Databases · Cross-listed from q-fin.TR
Axient: Manifest-Bound Evidence for On-Chain Financial Protocols: Seven-Layer Derivation, Correlation, Tamper Rejection, and Reproducible Claim Promotion
Maksym Nechepurenko
Hybrid on-chain financial protocols are frequently evaluated with evidence that is individually useful but collectively insufficient: a unit test, transaction receipt, screenshot, service response, or several matching hashes may be presented as proof of a complete workflow even when the layers share one generated source or omit the financial authority that matters. This paper develops a manifest-bound evidence architecture for such systems. A sealed execution manifest binds declared system identities, roles, schemas, and release identity. Seven evidence layers are retained with registered derivations and linked by a common correlation identity. A conjunctive claim-promotion rule requires provenance, predicate-specific root conditions, negative controls, reproducible packaging, historical replay, and independent review in addition to hash equality. We formalize the evidence graph, prove that copied hashes cannot establish independent derivation, show how collision-resistant commitments make specified tampering detectable, define exactly-once financial-effect evidence, and distinguish original historical identities from later reproducibility attestations. The registered local case study records twelve parent Financial Interaction Assertions in one accepted cohort: 84 retained ACTUAL_EVIDENCE positions, two clean materializations with one byte-identical file index, a deterministic strict archive accepted by a separate verifier, and a selected ordered replay bound to that archive. FIA-011 is conjunctive and retains both stale-before-admission and book-epoch-change-mid-position subcases. The result demonstrates a reviewable chain of custody from financial assertion to replay-bound package while preserving the difference between observed evidence, interpretation, and future hypotheses.
Read the full abstract ▾
Sound
How Far Back Should a Transformer Look? Repetition and Copying in Music Sequence Models
Amir Fathi
We investigate how predictive performance depends on the maximum context available to an autoregressive model of symbolic music, and what information long-context models exploit. A small causal
Transformer is trained separately at each context length T in {6, 18, 48, 96, 192, 336} and evaluated on the same target positions, both over raw
tokens and over non-overlapping binary latent codes. On Nottingham folk tunes, the
token predictor's test NLL decreases by 71% (0.986 bits per
token) between 6 and 336
tokens, and by 71% on the O'Neill's tunes long enough for the same sweep (129 of 302 test tunes). Most of the long-context gain is explained by exact copying: the improvement appears when an earlier occurrence of the target's 16-
token history enters the available context; overwriting that occurrence removes the gain, whereas equally large unrelated corruption does not; and a simple copy baseline recovers 94% of the reduction. A trained 336-
token model likewise loses most of this gain when its history is restricted to recent
tokens at test time. Because many repeats arise from written repeat signs expanded in the score, this result pertains specifically to these rendered score representations. By contrast, on MAESTRO performances and MusicNet scores, where exact repeats are substantially less frequent, the reduction is smaller (9% and 18%) and is largely attained by 96
tokens. Finally, an audit of an earlier draft that reported saturation at 16
tokens identified split leakage, overlapping latent receptive fields, an averaging predictor, and a per-file tempo grid; we present these as methodological checks for context-length measurements.
Read the full abstract ▾
Sound
Correlation-Based Distillation Yields More Mergeable Speech-Music Encoders
Fabian Ritter-Gutierrez
A single compact encoder for both
speech and music removes the need to maintain a separate model per domain. A practical recipe distils a
speech teacher and a music teacher into two small students, then merges them into one model. Two merging
algorithms exist: interpolating the student weights from a shared initialisation, or permuting their channels into
alignment before averaging. Prior work fixed the
distillation loss in both, leaving open whether the loss itself affects how well the students merge. We show that it does. Holding architecture and evaluation fixed, we replace the DistilHuBERT loss \Lkd{} with a correlation-based loss \Lcl{}. Under weight interpolation, \Lcl{} students stay closer to their own better endpoint in $17$ of $18$ comparisons and lead on the
speech tasks at every interpolated weight. Under activation permutation, they need fewer channels rearranged at three layers, their matched channels correlate more strongly, and they again lead on
speech. The two merging
algorithms share no mechanism, yet both improve under the same loss substitution. This suggests that the gain lies in the representation \Lcl{} produces rather than in either
algorithm.
Read the full abstract ▾
Machine Learning
All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR
Qiyuan Huang, Tianshi Xu and Meng Li
During post-training of large
language models (LLMs) with Reinforcement Learning with Verifiable Rewards (RLVR), GRPO-style
algorithms can exhibit severe late-stage collapse.
Prompt-based probing reveals that this is not benign strategic
pruning, but a harmful contraction of effective strategy capacity that makes distinct
reasoning strategies increasingly inaccessible. To characterize this phenomenon, we define strategies through trajectory-level policy-update interactions and develop a unified theoretical framework combining optimization dynamics and information theory. We prove that major RLVR objectives progressively concentrate probability mass onto a single strategy, while sustaining nontrivial task accuracy requires a minimum strategy capacity. The conflict between these two results provides a mechanistic explanation for catastrophic collapse. We further derive the {Mirrored
Entanglement Index (MEI)} as a lightweight online warning signal. To prevent collapse, we propose Mesh Learning, which exposes multiple
reasoning strategies and prevents any single strategy from dominating optimization. Across AIME26, AIME25, MATH-500, GPQA, and LiveCodeBench, Mesh Learning consistently outperforms strong baselines across Qwen and Phi model families, with gains of up to 13.4 pp and 11.5 pp, respectively. These results establish strategy preservation as a key principle for stable RLVR. Code is available at https://github.com/Ayanami-0123/Open-Mesh-Learning.
Read the full abstract ▾
Robotics
FastOPD: On-Policy Distillation for Lightweight VLA Deployment
Yoojin Oh, Jeongsol Kim, Yeonwoo Seo et al. (+7 more)
Vision-
Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that render real-world deployment increasingly challenging. Existing approaches typically mitigate this issue by designing smaller architectures or reducing the iterative denoising steps in flow-based policies. In this work, we propose FastOPD, a foundation-to-lightweight VLA framework that enables the practical deployment of large-scale VLAs through efficient on-policy
distillation. Specifically, FastOPD adapts a flow map for single-state teacher supervision and combines it with a self-consistency objective to construct a compact student that learns the teacher dynamics. Furthermore, we theoretically demonstrate that minimizing this objective allows the distilled student to recover a distribution on par with that induced by an ideal few-step teacher model. We evaluate FastOPD across diverse foundation policies in simulation and real-world experiments. On LIBERO, FastOPD retains 84% of the performance of $\pi_{0.5}$ with only two inference steps, reducing inference latency by 78.1% while outperforming existing few-step
distillation baselines in average success rate. With LingBot-VLA as the teacher, FastOPD improves the single-step success rate over the base student by 15.9 percentage points on RoboTwin 2.0. We further demonstrate its applicability to a World Action Model (WAM) and deploy a compact student distilled from MolmoAct2 on a real
robot.
Read the full abstract ▾
All authors Yoojin Oh, Jeongsol Kim, Yeonwoo Seo, Jangho Park, Seonghyun Jin, Sunwoo Park, Youngmin Kim, Youngjun Jun, Kyumin Choi, Jong Chul Ye
Artificial Intelligence
AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language Reranking
Wenteng Chen, Jiachen Zhu, Rong Shan et al. (+10 more)
Vision-
language models (VLMs) are powerful listwise rerankers for
multimodal retrieval, but high inference costs restrict them to evaluating small local candidate views. Existing multi-call strategies rely on fixed schedules, wasting expensive VLM calls on uninformative candidate pairs and easy queries. To address this, we propose Adaptive Multi-view Budgeted Elo Reranking (AMBER), an online, budgeted multi-view reranking framework that dynamically optimizes global resource allocation. AMBER treats fragmented listwise VLM outputs as local tournaments, using continuous Elo updates to maintain a lightweight global ranking state. Building on this, it allocates computation at two levels: dynamically constructing candidate views with high score ambiguity, and scheduling queries to maximize expected information gain. We show that each Elo update corresponds to a
stochastic gradient ascent step on the Bradley-Terry log-likelihood, and provide a submodular information-theoretic motivation for the query-level allocation strategy. Experiments on CIRR, CIRCO, and PhotoBench demonstrate that AMBER achieves the strongest overall performance among the compared multi-call VLM reranking methods under comparable VLM-call budgets, while remaining effective in lower-budget settings. Our code is publicly available at https://github.com/wnlfc/AMBER.
Read the full abstract ▾
All authors Wenteng Chen, Jiachen Zhu, Rong Shan, Tianyi Xu, Yuxiang Chen, Congmin Zheng, Teng Wang, Junjie Wu, Weiwen Liu, Changwang Zhang, Weinan Zhang, Jun Wang, Jianghao Lin
Systems and Control
On BESS-Backed Trading on the Continuous Intraday Electricity Market
Leo Semmelmann, Runyao Yu, Joseph Cary et al. (+1 more)
Battery energy storage systems (BESS) on the continuous intraday
market (IDC) often trade according to a rolling intrinsic
algorithm, a myopic strategy which repeatedly opens and unwinds positions according to current prices throughout the trading session, before dispatching as delivery approaches. This paper introduces a novel trading strategy for storage, in which forecast-driven round trip trading takes priority and the BESS supplies a second route for closing out positions that the
market would otherwise close at a distressed price. The
agent uses price
quantile forecasts to open positions on the IDC, and closes these positions closer to delivery. The
market can move against these trades, and the BESS intervenes only when a position would have to be settled at a price that the forecast predicts to be highly improbable, absorbing or serving that volume physically and restoring its state of charge at ordinary prices afterwards. The position itself remains loss-making; what the asset changes is the price at which it is closed, by transferring the terminal settlement price through time. Four
quantile forecasting models of increasing complexity supply the thresholds, and all strategies are backtested on realised EPEX SPOT transactions for the German
market area in 2024. A 40 MWh BESS in this role earns EUR 2.06m against EUR 1.77m for a rolling intrinsic
benchmark and EUR 1.37m for a perfect-foresight day-ahead
benchmark, while consuming 167 instead of 365 available equivalent full cycles. Hence, the novel backstop strategy yields higher profits, while using the underlying BESS less, leaving capacity for other trading opportunities.
Read the full abstract ▾
All authors Leo Semmelmann, Runyao Yu, Joseph Cary, Derek Bunn
Computation and Language
Clinical Concept Centers in LLMs
Aishik Nagar, Abhishek Vaidyanathan, Arun-Kumar Kaliya-Perumal et al. (+2 more)
Large
language models are increasingly used in clinical settings. However, research into the reliability and performance of these models has focused almost entirely on the
language substrate, scoring what the model says. Mechanistic interpretability has found that the latent space carries a higher fidelity of representation than the text: internal representations not only encode substantially more than the output verbalizes, but the stated
reasoning also systematically omits features that causally drive the answer. An evaluation of model behavior in terms of mechanistic interpretability has not been explored in clinical decision support. In this work, we extend behavioral evaluation into the latent space and ask whether clinical concepts exist as locatable, causally used representations inside open-weight LLMs. We find dedicated clinical concept centers in the latent space of all eleven open models we test. These concept centers are interpretable, firing only on their aligned clinical narratives, and meaningfully and causally drive model behavior in both constrained and open-ended settings. They are not just analytical representations, but
circuits that can be utilized in clinical practice, and we explore their use from the perspective of both evaluation and performance. From the evaluation standpoint, models stay internally coherent and keep using the relevant concept centers even under
adversarial role-based priming, while aligned priming improves downstream clinical performance. From a performance perspective, we simulate realistic deployment settings and find that steering models along these centers leads to meaningful downstream improvements. Finally, we conduct a blinded clinician validation and find the activation and usage of these concept centers predicts clinicians preferences.
Read the full abstract ▾
All authors Aishik Nagar, Abhishek Vaidyanathan, Arun-Kumar Kaliya-Perumal, Elijah Tzen Hsuen Boey, Stefan Winkler
Artificial Intelligence
FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+3 more)
Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier allocation, and update budget. Three coupled issues remain unresolved. A future-risk model trained from behavior trajectories need not estimate the risk induced by the controller that will be deployed; a score calibrated on logged state-action pairs can become miscalibrated after selective action choice; and independent per-resource minimum costs do not in general certify a feasible multi-resource continuation. We introduce FSPO, a feedback-state controller for budgeted LLM RL post-training that addresses these issues jointly. FSPO learns a policy-consistent risk-to-go model whose Bellman target follows the same frozen controller used for future decisions, together with a long-horizon utility model. Decision-conditioned trajectory calibration (DCTC) calibrates risk on cross-fitted trajectories generated by actions selected by provisional controllers. A Pareto resource continuation certificate (PRCC) admits an action only when a non-dominated cumulative reservation remains feasible over the residual horizon. Under a matched GRPO resource envelope, FSPO reaches 66.11% held-out and 59.43% OOD accuracy, compared with 64.47% and 57.03% for PB2, the strongest evaluated adaptive baseline. Three paired training seeds give gains of +2.42 and +3.19 percentage points over the contextual bandit on held-out and OOD evaluation. Under high behavior-deployment mismatch, policy-consistent risk lowers selected-decision ECE from 0.108 to 0.053; DCTC lowers it from 0.039 to 0.022 at matched acceptance; PRCC removes false-feasible admissions on an 18-action catalog ($0.197\rightarrow0.000$); and enabling all three components reduces trajectory failure from 0.181 to 0.083 in a factorial ablation.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Daren Zha
Artificial Intelligence
MLCommons Jailbreak Benchmark v1.0
Carsten Maple, Cagatay Yucel, Isaac Holeman et al. (+34 more)
Modern AI systems are designed to refuse hazardous requests. A jailbreak is a
prompt crafted to bypass those safeguards and elicit outputs that the system would normally refuse to provide. The MLCommons Jailbreak
Benchmark v1.0 provides an end-to-end methodology for evaluating the robustness of large
language models to single-turn, text-based jailbreak attacks. It combines criteria-driven system and attack selection, paired baseline and
adversarial evaluation, human annotation, automated evaluator calibration, scoring, grading, and risk-calibrated disclosure within a single benchmarking pipeline. The
benchmark evaluates eight open-weight systems using 264 seed
prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy. Responses are assessed using the AILuminate Assessment Standard v1.4, and robustness is measured through the Resilience Gap: the change in safety performance between baseline and
adversarial conditions. Across all evaluated systems and attacks, the unsafe-response rate increased from 11.08% under baseline conditions to 18.65% under jailbreak conditions, producing an average Resilience Gap of 7.57%. Accessible systems showed a larger mean gap, while attack effectiveness varied substantially across attack categories and hazards. The
benchmark also examines evaluator reliability and sources of measurement error. Beyond reporting results, Jailbreak
Benchmark v1.0 establishes a reproducible methodological foundation for comparative jailbreak evaluation and for future expansion across systems, attacks, hazards, and evaluation methods.
Read the full abstract ▾
All authors Carsten Maple, Cagatay Yucel, Isaac Holeman, Chris Knotz, Peter Mattson, James Goel, Jonathan Petit, Sean McGregor, James Ezick, Abhishek Kumar, Alicia Parrish, Murali Emani, Kashyap Iyer, Faiza Khan Khattak, Washington Mbonu, Daniel Machlab, Eileen Long, Shaona Ghosh, Jibin Varghese, Roman Lutz, Andrew Gruen, Bennett Hillenbrand, Prabal Gupta, Mohammed Serrhini, Dhivya Nagasubramanian, Aakash Gupta, Jun Lu, Kurt Bollacker, Chang Liu, Jonathan Petit, Cong Chen, Jean-Philippe Monteuuis, Brent Miller, Apurv Verma, Roman Eng, Armstrong Foundjem, Mohammed Serrhini
Artificial Intelligence
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite
Zongxia Li, Yucheng Shi, Zhongzhi Li et al. (+7 more)
Successful trajectories on difficult tasks provide valuable supervision for model improvement, but specialized harnesses introduce interventions that may be unavailable during deployment. We propose Recursive Self-Rewrite (RSR), a framework that uses one base model, Qwen-3.8-27B, to discover successful solutions under diverse harnesses and reconstruct them as training trajectories under a general harness. A planner extracts procedures into runbooks, a critic screens for verifier and solution leakage and guides recursive revision, and an executor follows qualified runbooks in fresh sandboxes. Across approximately 3K self-curated terminal tasks, three harnesses jointly solve 759 tasks, 34.3% more than the strongest individual harness in the recorded pool. RSR expands 2,001 successful source trajectories into 11,094 rewritten trajectories for supervised finetuning. Training on these trajectories outperforms both the base model and direct trajectory SFT. Compared with the base model, pass@3 increases from 57.0% to 74.2% on Terminal-Bench 2, from 1.5% to 9.1% on Terminal-Bench 4, from 39.0% to 63.0% on our self-curated Terminal-Bench Hard, and from 3.0% to 6.0% on our Software Terminal-Bench. Process reward on Long-Horizon Terminal-Bench rises from 0.21 to 0.29. These results show how diverse harness-assisted experiences can be reconstructed into reusable capabilities for a model operating under a general harness.
Read the full abstract ▾
All authors Zongxia Li, Yucheng Shi, Zhongzhi Li, Junyao Yang, Ruhan Wang, Chengsong Huang, Fuxiao Liu, Haitao Mi, Jordan Boyd-Graber, LeoweiLiang
Computer Vision
TerrainForge: Physics-Grounded Road Geometry Editing for Counterfactual Autonomous Driving
Yang Chen, Yicheng Zhu, zhenning Li et al. (+2 more)
Road geometry (e.g., crests, sags, and speed humps) and surface conditions (e.g., wet or icy pavement) affect how vehicles move, what drivers and onboard cameras observe, and how much clearance remains between vehicles. Editing these properties in a driving scene therefore requires corresponding changes in vehicle motion. Capturing these differences in a driving
video requires a road edit to propagate to vehicle motion, camera viewpoint, and the clearance between vehicles. We present TerrainForge, a framework for generating road geometry-focused counterfactuals from reconstructed multi-vehicle driving episodes. A unified road model connects scene deformation with four-wheel vehicle dynamics, allowing crests, sags, speed humps, and friction changes to propagate through vehicle motion, camera viewpoint, and inter-vehicle clearance. Vehicle dynamics are evaluated against CarSim, and prescribed road geometry is verified in reconstructed Waymo scenes. Across 18 episodes, leaving surrounding vehicles on their recorded trajectories instead of recomputing their responses produces median peak differences in predicted ego-lead distance of 1.52 m for crests and 1.41 m for sags. We further simulate the ego response to 15,758 road edits across 983 braking episodes, pairing each edit with its safety outcomes relative to an unedited replay. These pairs train a first-stage screening surrogate that takes the original driving context and candidate road-edit parameters as input and predicts the resulting change in the ego's terminal gap. On held-out scenes, this prediction achieves 22-40% lower mean absolute error than predicting no change, so candidates can be screened cheaply before the full multi-vehicle rollout.
Read the full abstract ▾
All authors Yang Chen, Yicheng Zhu, zhenning Li, Tao Li, Zilin Bian
Artificial Intelligence
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
Yuxuan Fan and Jaehong Yoon
Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requirements. However, rubric judges can assign a high criterion score even when the information or action it requires is absent from the response, a failure mode we term Vacuous Credit. Such awards persist after the required information is removed and can reverse the sign of a response's GRPO advantage. To address this problem, we introduce MetaRubric, which alternates evidence-aware policy optimization with response-guided rubric adaptation. We construct counterfactual counterparts by changing one task-relevant fact in each
prompt. During policy optimization, credit is assigned only when the response contains sufficient evidence to satisfy the required rubric criterion. After each policy-optimization stage, current policy responses guide revisions to original and counterfactual criteria while preserving the meaning of the original
prompt's initial rubric as interpreted under each
prompt's facts. We also adapt criterion weights at stage boundaries to better address observed policy errors. Across multiple backbones, MetaRubric improves PubMedQA accuracy by 6.00–20.40 percentage points over static-judge GRPO, with further gains on HealthBench-Hard and two
multimodal medical
benchmarks.
Read the full abstract ▾
Sound
What Actually Makes Correlation-Based SSL Distillation Noise-Robust? A Mechanistic Correction
Fabian Ritter-Gutierrez, Nancy F. Chen and Eng Siong Chng
Self-supervised learning (SSL)
speech models are accurate but large. Knowledge
distillation compresses them, but the student loses the teacher's noise robustness. Correlation-based
distillation addresses this with two terms: cross-correlation aligning student and teacher's representations, and self-correlation decorrelating the student's features. Both the original method and De'HuBERT credited the self-correlation term without isolating it. We show the opposite. On LibriSpeech-100
distillation with held-out CHiME-3 noise at 10\,dB, an unbiased full-dimensional probe, a Pearson-variance decomposition, a same-noise causal control, and a per-dimension analysis identify the cross-correlation diagonal as the mechanism that encourages noise invariance, lowering noise-classification accuracy from 76.98% to 55.02%, whereas adding the self-correlation term back leaves it at 55.55%. The self-correlation term instead reorganises the feature space and improves accuracy on the clean downstream tasks, but removes essentially no noise. Across nine
speech and music tasks this yields a concrete design rule for
distillation: weight the cross-correlation term for noise robustness, tune the self-correlation term for better downstream performance, and sample teacher and student noise independently.
Read the full abstract ▾
Machine Learning
Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization
Tengxue Zhang, Yu Ke, Yang Shu et al. (+4 more)
Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods are either prone to overfitting to domain-specific noise in the data space or become overly complex and less interpretable in the parameter space. To bridge these gaps, we propose AdaSpecK, a spectral-Koopman framework with adaptive context extraction for TDG. To mitigate noise fitting to irregularly sampled domains, we introduce spectral-regularized Koopman dynamics modeling, which applies spectral-aware filtering in the latent space to extract denoised low-frequency trajectories and learn a Koopman operator to model the system dynamics in a linearized space. To model complex historical environments under non-stationarity, we design a context-informed heterogeneous pattern extraction mechanism. Specifically, we employ a target-conditioned
attention module to attend to distinct past windows, producing a dynamic, target-specific historical summary. By constructing an environmental signature from the current evolutionary pattern, our model adaptively perceives which aspects of the past context are most informative for future prediction via a learned router. Extensive experiments on eight diverse classification and regression
benchmarks demonstrate that AdaSpecK achieves state-of-the-art performance. The code and
datasets are available at \href{}{https://anonymous.4open.science/r/Ada-Spec-K}.
Read the full abstract ▾
All authors Tengxue Zhang, Yu Ke, Yang Shu, Chenchen Sun, Yisheng An, Chenjuan Guo, Bin Yang
Numerical Analysis · Cross-listed from physics.optics
Fast Nanophotonic Inverse Design using Precomputed Numerical Green Functions
Thi Phuong Thao Nguyen, James Wang and Constantine Sideris
Inverse design has been transformative in nanophotonics, providing an automated means of realizing high-performance, non-intuitive devices. However, the primary bottleneck of existing inverse design approaches is their reliance on time-consuming and computationally expensive full-wave electromagnetic simulations. In this work, we extend the Precomputed Numerical Green Function (PNGF) method for the first time to nanophotonic inverse design, accelerating evaluation of the forward problem by multiple orders of magnitude with no loss in accuracy compared to the full-wave solution. After a single, fully parallelizable precomputation step, both the objective function and its gradient can be evaluated through simple calculations whose cost scales linearly with the size of the design region. A low-rank
matrix update technique further reduces the cost of objective function evaluation, yielding sub-millisecond computation times per iteration. Design examples using both gradient-based level-set optimization and tile-flipping direct binary search often achieve more than three orders of magnitude speedup in design time, resulting in an ultrafast photonic inverse design platform that can design new devices from scratch in seconds.
Read the full abstract ▾
Computation and Language
Text-Centric Post-Training for Omni-Modal Reasoning
Ziyang Cheng, Yuhao Wang, Hongcheng Liu et al. (+5 more)
Improving joint audio-visual
reasoning in Omni Large
Language Models typically incurs substantial data construction and training costs. Our diagnostics reveal multi-hop
reasoning difficulties despite correct answers to all corresponding single-hop questions and suggest partial decoupling in the local optimization of perception and
reasoning objectives. This motivates post-training with different emphases on these capabilities. Text-only
reasoning training yields gains across data sources, model scales, and families. With the best-performing text-only configuration, supervised fine-tuning followed by reinforcement learning (RL) raises Qwen2.5-Omni-7B's
geometric mean of nine
reasoning scores by 25.83% over the base model, outperforming the complete native audio-visual route with 56.6% fewer GPU-hours. Training on data synthesized entirely by a text-only LLM raises this
geometric mean by 21.01% without audio-visual data in construction or training. However, text-only training degrades perception. We therefore propose a text-centric post-training paradigm: text-only training provides the main
reasoning optimization, and reduced-data native audio-visual RL then refines perception. Refinement uses about 90% fewer input
tokens than full-data audio-visual RL, restores perception above the base level, and retains 93.5% of the best-performing text-only pipeline's
reasoning gain.
Read the full abstract ▾
All authors Ziyang Cheng, Yuhao Wang, Hongcheng Liu, Qimin Wu, Jingru Fan, Chen Qian, Yanfeng Wang, Yu Wang
Cryptography and Security
RMCW: A Deletion-Robust Watermark Based on Reed–Muller Codes for Language Models
Yi Wang, Baicheng Chen, Yu Wang et al. (+3 more)
Large
Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remains fragile under post-processing attacks. Deletion attacks are particularly challenging because they shift
token positions and break the
alignment between observed
tokens and their original watermark positions. We propose Reed–Muller Code Watermarking (RMCW), an LLM watermarking method based on Reed–Muller codes. In contrast to global codeword recovery, RMCW searches for surviving local algebraic structure, leveraging the Reed–Solomon consistency induced by affine-line restrictions of Reed–Muller codewords. During generation, RMCW injects a Reed–Muller structure into the sequence via a secret-keyed vocabulary partition. During detection, it maps the given text to keyed vocabulary bins and tests local subsequences for low-degree Reed–Solomon consistency using Berlekamp–Welch tests. Experiments on C4 and ELI5
datasets with OPT-1.3B and Llama-3.1-8B-Instruct show that RMCW preserves strong clean-text detectability and outperforms or matches the baseline methods under several deletion and rewriting attacks. Our code is available at https://github.com/BaichengDanny/RMCW.
Read the full abstract ▾
All authors Yi Wang, Baicheng Chen, Yu Wang, Jian Zhao, Yilei Chen, Tianxing He
Machine Learning
Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear Attention
Ruijie Li, Shengnan Ding, Weimin Zhang et al. (+6 more)
Linear
attention models have emerged as efficient alternatives to standard
attention, but effectively managing their fixed-size recurrent
memory remains challenging. To improve
memory, recent work has explored two distinct directions: delta-rule variants for precise correction of values associated with keys, and slot-based architectures such as Gated Slot
Attention for modeling key and value
memories in two stages. We observe that these directions are complementary–the delta rule provides effective
memory correction, while the two-stage structure provides a natural way to operate on both sides of an association. Building on this insight, we introduce a new Gated Oja Rule for key-side correction and extend it with decoupled erase and write control to obtain Gated Oja Rule-2. We then introduce Gated Slot
Attention-2 (GSA2), which combines Gated Oja Rule-2 for key-side correction with Gated Delta Rule-2 for value-side correction through shared latent slots. We further derive a hardware-efficient chunkwise
algorithm for parallel training. Experiments demonstrate that GSA2 consistently improves over strong linear-
attention baselines across
benchmarks while retaining linear-time sequence modeling and constant-
memory recurrent decoding.
Read the full abstract ▾
All authors Ruijie Li, Shengnan Ding, Weimin Zhang, Derick Tang, Zhanpeng Zeng, Qinsong Zeng, Ming Chen, Jiaxi Hu, Yuxuan Liang
Artificial Intelligence
iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVD
Yiren Zhao, Guanghui Song, Tianrui Qin et al. (+3 more)
Long chain-of-thought
reasoning substantially increases KV-cache
memory during autoregressive decoding, as every generated
token introduces new key and value states and causes the cache to grow linearly with decoding length. Existing KV-cache compression methods typically control this growth through
token eviction, but irreversible deletion can remove historical states that later
reasoning may need to revisit. SVD-based low-rank compression provides an alternative by retaining all positions with a more compact representation. However, extending it from a fixed
prompt cache to online decoding is non-trivial. Through our investigation, we find that if the basis is updated for new
tokens while old
tokens keep their coordinates in the old basis, the stored history drifts substantially. Based on this observation, we propose iS-KV, an online low-rank KV-cache compression method for long-horizon
reasoning. iS-KV keeps a recent window exact while incrementally folding older states into bounded-rank representations. As the low-rank basis evolves, it synchronizes historical coordinates with the updated basis to maintain representation consistency. On DeepSeek-R1-Distill-Llama-8B, iS-KV achieves 82.6% accuracy at 4.06-fold persistent-KV compression, close to the original model's 83.6%. On Qwen3-8B, it achieves 89.2% accuracy at 5.64-fold compression. Under matched
memory budgets, iS-KV consistently outperforms
token-eviction baselines.
Read the full abstract ▾
All authors Yiren Zhao, Guanghui Song, Tianrui Qin, Kejiang Ye, Cheng-zhong Xu, Xitong Gao
Software Engineering
VeriPy Source-Preserving Verification and Compatibility Checking for Python Components
Naing Oo Lwin
Keeping a Python program and its formal guarantees aligned is a continuing maintenance problem. Specifications must describe the implementation that actually runs, and updates must preserve the behavior on which existing callers depend. VeriPy brings these obligations into a common workflow for annotated Python components. Developers and
agents express contracts, invariants, and proof hooks as Python comments, then refine checked auxiliary lemmas using source-located diagnostics. Direct encoders produce Dafny or Lean artifacts while retaining admitted executable bodies and explicit models of their dependencies. A relational product checks whether an updated component still admits old inputs and preserves returned values and modeled exceptions. The resulting workflow connects source-level proof development with functional verification and backward compatibility, recording the assumptions under which each guarantee applies. The code is available at https://github.com/astrio-labs/veripy.
Read the full abstract ▾
Robotics
Register-Routed Delayed Fusion: Rewiring Shortcut-Prone Observation Fusion in Visuomotor Imitation
Jieting Long, Weidong Cai and Weiming Zhi
Visuomotor imitation policies combine high-dimensional visual observations with compact signals such as proprioception, and their fusion
topology determines when and through which
tokens these streams interact. In dense
token fusion, visual
tokens may attend directly to compact
tokens from the first encoder layer, allowing action-predictive compact cues to influence spatial visual representations early in their formation. We ask whether controlling this route improves visual responsiveness and policy behavior. We introduce Register-Routed Delayed Fusion (RRDF), which masks direct compact-visual
attention and stages cross-modal interaction through a learned register workspace. Its isolate-collect-route schedule protects an early stream-separated prefix and later permits only register-mediated exchange, while compact conditioning remains available to the native action generator. Across five simulation tasks and three real-
robot tasks, RRDF matches or improves dense ACT under nominal conditions. Appearance-shift evaluations on four simulation tasks and held-out-position evaluations on three real-
robot tasks also favor RRDF. Phase-matched input probes show lower measured state-to-image sensitivity, while ablations indicate that adding registers alone does not reproduce the full performance gain. These results support controlling cross-modal propagation while retaining compact action conditioning.
Read the full abstract ▾
Human-Computer Interaction
Co-Designing AI For Mental Health Support With Young Adults of Color (YOC): Needs, Expectations, and Implications for AI Literacy
Elaine Dabin Jeon, John Bosco S. Bunyi, Hannah Kim et al. (+7 more)
Young adults of color (YOC) face heightened mental health challenges and barriers to care while navigating developmental and life transitions. Situated between youth-oriented safeguards and adult-oriented AI systems, little is known about how they use AI chatbots for mental health and well-being support or how sociocultural contexts shape their expectations, concerns, and design preferences. We conducted a two-day co-design workshop with 13 Asian, Black, and Hispanic/Latino/a young adults aged 18–24. Participants found generic chatbot advice to flatten their lived experiences; rather than making incorrect assumptions, they wanted more opportunities for identity-informed disclosure. Preferences for YOC-centered personalization also revealed gaps in
privacy and AI literacy. Participants negotiated different therapeutic roles for chatbots and sought greater AI accountability and user agency, highlighting blurred boundaries between clinical and non-clinical AI-mediated support. Findings suggest directions for integrating AI literacy with mental health literacy and centering YOC's experiences in the
privacy calculus.
Read the full abstract ▾
All authors Elaine Dabin Jeon, John Bosco S. Bunyi, Hannah Kim, Renkai Ma, Yaman Yu, Michal Luria, Jason Yip, Alexis Hiniker, Katie Davis, Angel Hsing-Chi Hwang