Optimization
-
CuPIQP: A Batched and Differentiable QP Solver on GPUs for Robot Learning and Control
2026-10-29 22:04:05Fenglong Song, Roland Schwan, Yuwen Chen, Yuning Jiang, Colin N. JonesAbstract
Quadratic programs (QPs) are fundamental building blocks of many robotic tasks such as inverse kinematics, whole-body control, and model predictive control. Extending these methods to large-scale robot learning and control requires solving many QPs concurrently and, for end-to-end learning, differentiating through their solutions. Efficient batched optimization is therefore essential to bringing established model-based methods into GPU-based robotics pipelines. We present \textsc{cuPIQP}, a batched and differentiable QP solver on GPUs based on a proximal interior-point method, with unified support for dense, sparse, and multistage problems. The solver exploits parallelism across independent QPs and their internal structure while preserving per-problem numerical updates and termination decisions. Benchmarks with up to 16384 QPs per batch demonstrate solve-time speedups of up to $18.8\times$ over \textsc{Moreau} and $4.26\times$ over eight-core \textsc{PIQP}. In an end-to-end learning task, \textsc{cuPIQP} accelerates training by $4.6\times$ over \textsc{QPAX} and $7.8\times$ over \textsc{Moreau}. By reducing the computational cost, \textsc{cuPIQP} provides efficient, reusable infrastructure for integrating model-based optimization into large-scale robot learning and control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41021
PDF
-
CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak
2026-10-29 19:51:36Jialin Song, Xiaodong Liu, Weiwei Yang, Mingqian Feng, Chengquan Guo, Qiyao Ma, Carolyn Buractaon, Anson Ho, Wuyang Chen, Christopher WhiteAbstract
Automated red teaming trains an attacker large language model (LLM) to elicit harmful responses from a victim LLM, but reinforcement learning can collapse attackers onto a narrow set of prompts when attack success is the only reward. Such a collapse of attack diversity can bias safety evaluation toward repeatedly testing near-duplicate attack patterns rather than the underlying harmful intents. Existing methods often trade off attack success or inference cost for greater content or strategy diversity. We propose CoFiBreak, a coarse-to-fine diversity reward for Group Relative Policy Optimization (GRPO) that improves attack diversity while preserving strong attack effectiveness and low inference cost. The coarse reward broadens which strategies the attacker uses by encouraging strategies underrepresented within each GRPO group, while the fine reward broadens how those strategies are realized by discouraging reuse of the same personas, framings, and output formats after harmful-intent information is removed from prompt embeddings. Diversity rewards apply only to attacks that already exceed an effectiveness threshold, so diversity cannot be gained through ineffective attacks. Since both rewards are computed only during training, CoFiBreak also retains inference efficiency. Trained with Llama3.1-8B-Instruct as the victim, CoFiBreak discovers 1.6-2.0x as many distinct successful fine-grained strategies as the strongest baseline across frontier victims on HarmBench. It reaches 98.8% ASR@10 (attack success rate with 10 generations per intent) on AdvBench with the highest diversity score among all compared methods, which is 2.1x that of the strongest-attacking baseline. The resulting attacks transfer to unseen frontier LLMs, reaching 71.0% ASR@10 on AdvBench with the unseen victim Claude-Opus-4.6. The code will be released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40926
PDF
-
FARO: Function-Space Adaptive Return-to-Risk Optimization via Cross-Block Equal-Risk-Contribution Budget Allocation
2026-10-29 18:37:04Xiaojun Wu, Cehao Yang, Xuhui Jiang, Chengjin Xu, Jia Li, Jian GuoAbstract
Training a large language model is compute-bound, and current recipes divide the work between optimizers by hand: orthogonalized momentum for attention and MLP matrices, Adam-style updates for the rest. This division rests on human priors about which layer type deserves which geometry, and it fixes a single global update budget that every parameter block shares. We introduce FARO, a function-space adaptive optimizer that makes the partition of parameters into blocks the unit of decision. FARO gives each block a geometry by its realized counterfactual return, then freezes the routes and reallocates the frozen per-block budget by cross-block equal risk contribution (ERC), the risk-parity principle from portfolio theory. On a GPT-style model trained on FineWeb, the framework gives two results. First, its FARO-Adaptive arm reaches 3.2780 nats at the full schedule, matching NorMuonAndAdam (3.2794), the best hand-designed recipe: it recovers the human prior without hand-setting per-layer geometry. Second, FARO-ERC improves on that arm: it lowers the clean-data loss at every one of 6 seeds, by 0.0136 nats on average, a modest but robust gain. Its sign test, paired test, and confidence interval all agree, and it exceeds the measured run-to-run noise at no added time or memory. It works by trimming the riskiest blocks rather than expanding the safest, and it holds up under a corrupted stream, still lowering the mean loss and winning the seed majority. The source code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40858
PDF
-
EgoHSI3R: Online 4D Hand-Scene Interaction Reconstruction from Egocentric Video
2026-10-29 18:14:06Mingzhi Pei, Zhangchen Ye, Ruoqu Chen, Liu Cao, Mengdi XuAbstract
Egocentric videos offer an abundant source of hand-scene interactions for embodied learning, which requires recovering hands, camera, and scene consistently in a shared 3D world. Existing methods focus on either camera-frame hands or world-space hand trajectories, without jointly recovering the scene pointmaps or interaction information. Building a complete reconstruction from such specialized predictions therefore typically requires per-sequence optimization. We propose EgoHSI3R, a unified feed-forward framework for online 4D hand-scene interaction reconstruction from egocentric monocular video. To jointly recover these components, it maintains a recurrent scene representation that accumulates geometric evidence over time and provides a shared world space and scale. We introduce hand-centric prompts that fuse pretrained hand priors and local scene context, while MANO vertex queries attend to scene features to predict dense per-vertex contact. These designs enable a single network to jointly estimate camera motion, dense scene geometry, world-space bilateral MANO hands, and per-vertex hand contact. Despite operating causally, EgoHSI3R achieves the lowest world-space hand joint error on ARCTIC among the evaluated methods, while offering faster inference than existing world-space hand reconstruction pipelines and competitive camera and scene reconstruction accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40832
PDF
-
From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation
2026-10-29 18:07:37Ammar N. Abbas, Aayush Jain, Prashanth Viswanath, Nivesh Gadipudi, Giulia Vilone, Jim GibbonsAbstract
Imitation learning policies are intended to make robotic manipulation robust to variations in object pose, appearance, and environment that challenge pre-programmed motion. However, real-world performance remains difficult to predict, as conventional optimization signals such as validation loss show no consistent relationship with robot success. To identify the design choices that govern real-world performance, 281 imitation-learning policies spanning seven policy families were evaluated in approximately 1,700 real-robot trials of RJ45 connector grasping and insertion using a five-fingered robotic hand. Controlled ablations showed that observation and action representations dominated conventional optimizer and sampling choices. For point-cloud policies, region-of-interest cropping, representation in the robot-base frame, and normalization within the point encoder each improved success by 70-100 percentage points. For the vision-language-action policy, absolute rather than relative action prediction improved insertion success by up to 70 percentage points. Skill decomposition, multi-view perception, and recovery demonstrations were associated with the strongest-performing systems, although their effects were not independently isolated. Of 67 offline metrics evaluated, only five measures of predicted-motion smoothness and directness reliably correlated with insertion success (r = -0.70 to -0.80), and only within a single policy family. These results identify representation choices as key determinants of real-world imitation-learning performance and show that offline metrics can shortlist policies, but cannot replace real-robot evaluation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40828
PDF
-
TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
2026-10-29 17:54:12Tom Sander, Pierre Fernandez, Itai Gat, Haiming Bao, Jiaxin Shi, Jason Park, Valeriu Lacatusu, Sylvestre-Alvise Rebuffi, Hongyan Chang, Hady Elsahar, Tom\'{a}\v{s} Sou\v{c}ek, Tuan Tran, Surya Parimi, Alexandre MourachkoAbstract
We present TextSeal2, a distortion-free watermark for large language models that keeps its signal under speculative decoding: tokens that replace rejected drafts remain watermarked with the same keys, and the acceptance rate is unchanged. It also preserves output diversity and adds no measurable inference latency. Its predecessor, TextSeal, restores diversity in the Gumbel-max scheme by routing each token to one of two keys via a coin flip. This is suboptimal because the detector averages the scores from both keys without knowing which key was used. TextSeal2 instead merges two or more keys into a single virtual key and couples it to fresh noise through AutoMark's Gaussian copula. Any number of keys, including publicly shared keys, can be merged this way without diluting detection. Under speculative decoding, TextSeal2 verifies keyed drafts with one more exponential race, run on the leftovers of the draft races. By memorylessness, this race reproduces block verification, so the output follows the target model exactly. We evaluate TextSeal2 on three LLMs. At equal output token diversity, TextSeal2 detects 8 to 22 percentage points more 100-token answers than TextSeal at a false-positive rate of $10^{-3}$, and is comparable to textGrain while requiring no post-logits optimization. Under speculative decoding, it detects 18 and 22 percentage points more 200-token answers than TextSeal and textGrain, respectively, at the same acceptance rate.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40613
PDF
-
A Unified Hessian-Guided Framework for Post-Training Quantization
2026-10-29 16:06:01Mads Toftrup, Marco Federici, Boris van Breugel, Paul Whatmough, Markus NagelAbstract
Low-bit quantization enables efficient deployment of large language models by reducing memory footprint and computational cost. Achieving high accuracy at low precision requires selecting quantization ranges, linear transformations, and weight rounding decisions. Existing approaches typically optimize these components independently using local reconstruction objectives, which fail to account for the varying impact of quantization errors on downstream predictions. Direct optimization of task-level metrics would provide a more faithful objective, but is challenging due to the discontinuous nature of quantization operations and the high computational cost of evaluating their downstream effects. In this work, we derive a Hessian-guided approximation of the output change induced by joint weight and activation quantization. Based on a tractable Fisher approximation, we formulate a unified post-training quantization framework that enables the joint optimization of quantization ranges, linear transformations, and weight rounding under a common output-sensitivity objective. The resulting method remains practical for modern large language models and consistently outperforms state-of-the-art transformation and rounding methods across both channel-wise and block-wise quantization settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40345
PDF
-
Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR
2026-10-29 15:20:12Lang Chen, Zongxin Xu, Borui Wang, Anran Liu, Shitong ChenAbstract
We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-level baselining} step that converts scalar verifier rewards into a comparable sequence-level signal, and a \emph{token-level credit assignment} step that distributes that signal over the trajectory. Existing estimators typically address only one of these stages: affine baselines preserve the shape of each task's reward law, so heavy tails and binary cliffs propagate into the gradient, while token-level credit rules tie the size of each token's update to raw confidence scales and need not conserve the total credit issued by the verifier. We propose \textbf{TACE} (Two-stage Advantage and Credit Estimation), a two-stage estimator that addresses both stages. At stage~(S1), we replace linear standardization with a one-dimensional optimal-transport map to a standard normal, which gives a common population reward law across tasks and caps finite-sample outliers deterministically. At stage~(S2), we rank-calibrate a stop-gradient evidence contrast within each trajectory and renormalize the clipped token weights to have mean one, so credit is redistributed across tokens while its total mass and sign are conserved. We prove population-level inter-task moment equity, a deterministic tail bound, and mass-conservation, boundedness, and sign-anchoring properties that affine baselines and unnormalized token weights do not satisfy. On a multimodal reasoning suite, TACE obtains the strongest results on a majority of the benchmarks but does not dominate every setting.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40250
PDF
-
EpiAgent: Epistemic Self-Play for LLM Agents
2026-10-29 15:05:08Xuanfa Jin, Xinyu Cui, Zhijian Ma, Xue Yan, Jian Zhao, Haifeng Zhang, Jun WangAbstract
Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-based agents, however, often lack an explicit mechanism for learning and updating such beliefs to guide decisions under incomplete information. To bridge this gap, we propose EpiAgent, a framework that equips LLM-based agents with an explicit, learnable epistemic layer, which maintains beliefs over others' private information and combines these beliefs with the agent's available information into an epistemic state for action selection. Concretely, the agent's policy is decomposed into two coupled stages: Epistemic Update, which updates these beliefs from interaction histories, and Action Planning, which selects actions conditioned on the updated epistemic state. By formulating their dependency as a bi-level optimization problem, we introduce Epistemic Self-Play, an algorithm that alternately optimizes the two stages through self-play, utilizing an intrinsic prediction reward to evaluate how well inferred beliefs predict subsequent observations. Empirical results across both mixed and competitive scenarios show that EpiAgent consistently outperforms prompting-based and RL-based baselines. Further analyses reveal the benefits of dedicated epistemic training, improvements in belief inference accuracy, and the contribution of learned beliefs to action planning. These results demonstrate the value of an explicit, learnable epistemic layer for effective multi-agent interactions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40227
PDF
-
Reinforcement learning to improve large language model-based automated code compliance systems
2026-10-29 14:37:41Jack Wei Lun Shi, Minghao Dang, Wawan Solihin, Justin K. W. YeohAbstract
Large language model (LLM)-based approaches for automated code compliance (ACC) of building regulations are prone to generating incorrect and hallucinated computer-processable rules. This paper introduces P4IR, a two-stage framework that uses supervised fine-tuning (SFT) to instill domain knowledge in an LLM, followed by Group Relative Policy Optimization (GRPO) to improve the accuracy of the generated intermediate representations in the form of high-level code skeletons. The framework achieved final reductions of up to 21.3% and 41.0% in tree edit distance and token-level Levenshtein distance respectively, relative to the SFT baselines. Comparative analysis demonstrates that this approach in a zero-shot setting outperforms leading LLMs in both code structure and semantics, evaluated via few-shot prompting. Additionally, the GRPO stage produced a statistically significant reduction in false positives. By combining SFT with GRPO to optimize directly for domain-specific objectives, this approach offers a path toward more accurate and reliable LLM-based ACC systems.
Abstract (translated)
URL
https://arxiv.org/abs/2606.22402
PDF
-
Reward-Adaptive Co-Evolution of Policy and Rubric
2026-10-29 14:00:07Yizhu Chen, Jianguang Jiang, Jiameng Huang, Chuyu Fang, Bojun Zhang, Zhenyu Jiao, Xing Yuan, Tong LinAbstract
Rubric-based rewards provide fine-grained, interpretable supervision for open-ended reinforcement learning, where holistic scalar rewards struggle to capture multidimensional response quality. Static rubrics can lose discriminative power as the policy distribution evolves, while existing policy--rubric co-evolution methods rely on globally prescribed update schedules that ignore heterogeneous reward informativeness. We introduce RACE, a Reward-Adaptive Co-Evolution framework. At the group level, per-rollout-group training-signal routing classifies groups as informative, diversity-collapsed, or rubric-failed, updating the policy only with informative groups while caching rubric failures. At the phase level, event-triggered phase switching enters rubric optimization upon persistent reward saturation and returns when rubric-reward improvement plateaus. Rubric phases train the generator on cached pairs using a frozen judge and a scale-normalized pairwise-margin reward. Across both levels, online threshold adaptation adjusts routing and switching thresholds through proportional control. Under a unified evaluation protocol, RACE achieves the highest average performance and outperforms the strongest fixed-alternation baseline on all eight tasks, while improving rubric discrimination.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40096
PDF
-
HEMO: Harness Self-Evolution for Multi-Objective Combinatorial Optimization
2026-10-29 13:32:00Jianghan Zhu, Cong Zhang, Ni Zhang, Yifan Yang, Yew Soon Ong, Zhiguang CaoAbstract
Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization (MOCO). Yet most methods evolve the operators while leaving the process that discovers them fixed. This limits adaptation as new Pareto trade-offs and operator interactions change where and how the search should proceed. We introduce HEMO, which makes the AOD harness itself a self-evolving optimization target. HEMO maintains a persistent harness state and updates one module at a time, revising the logic that determines which experience to retrieve, which operators to improve, which parents to select, and how to formulate the orchestration of search steps. Downstream solution quality and runtime guide these updates, while a discounted UCB scheduler directs adaptation toward promising modules as their utility changes. A persistent memory filesystem preserves candidate outcomes and diagnostic feedback across harness states, enabling successive states to build on accumulated optimization experience. Experiments across eight MOCO tasks and two structurally distinct evolutionary backbones demonstrate strong performance against conventional evolutionary, neural, and LLM-based AOD baselines, together with effective transfer to related tasks. HEMO extends automatic operator design beyond evolving individual operators to improving the search process that discovers them.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40023
PDF
-
When to spend privacy: optimal allocation in private learning
2026-10-29 12:51:07Umberto Biccari, Yongcun SongAbstract
Privacy accounting bounds the cumulative privacy cost of Differentially Private Stochastic Gradient Descent but does not determine how to allocate a fixed budget across iterations. We formulate the complete Gaussian noise-variance schedule as an open-loop control under a composed zero-Concentrated Differential Privacy constraint, explicitly accounting for schedule selection. For expected quadratic terminal tracking, we prove that every local minimizer exhausts the certified budget, yielding an exact-budget simplex formulation. We introduce Privacy-Budget Adjoint Mirror Descent (PB-AMD), combining pathwise adjoint gradients with entropic updates that preserve positivity, charge floors, and the prescribed budget. Under regularity and coercivity assumptions, we establish existence and budget stability of optimal schedules, design-to-training utility stability, and deterministic, stochastic, and sample-average stationarity guarantees. A linear-quadratic reduction yields an explicit square-root allocation law. Experiments demonstrate tracking improvements over several allocation rules and predictive improvements over uniform allocation in a learning-rate restart setting, where learning-rate allocation performs similarly. Comparisons at a common stationarity tolerance show lower schedule-optimization times than projected gradient descent on the tested problems. The framework connects certified privacy accounting with optimization through nonlinear training dynamics.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39954
PDF
-
CovFedAvg: Local Low-Loss Curves and Federated Model Selection
2026-10-29 12:12:55Federico Lucchetti, Marcus V\"olpAbstract
Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support. We study whether redundant models permit local low-loss paths toward a compatible shared model. CovFedAvg retains local models and curve controls on clients, fits a common endpoint through aggregated gradient contributions, and selects an actual candidate model using distributed training losses. No centralized calibration examples or client-to-client sample exchange are required. Exact selection guarantees no higher evaluated training loss than the previous model and the current-round FedAvg candidate; this is not a global-optimality, stationarity, generalization, or differential-privacy guarantee. We state conditional client-compatibility and approximate-selection bounds and retain corrected transformation identities and a separate full-gradient safeguard theorem for reference algorithms. A complementary input-support example recovers the shared absolute-value regression, while matched direct fine-tuning also solves it. Across a synthetic support task, recorded activity-recognition subjects, and participating and future gas-sensor batches, we evaluate five methods, five seeds, two network widths, and 20 rounds without calibration data. At width 16, CovFedAvg raises participating-Gas macro balanced accuracy from FedAvg's 88.88% to 89.84%; matched distributed fine-tuning reaches 91.65%. Results support feasibility and modest gains over FedAvg, but do not establish a curve-specific advantage over equally costly optimization. Exact-sum numerical experiments establish data flow; end-to-end privacy requires additional mechanisms and analysis.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39902
PDF
-
Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding
2026-10-29 11:15:12Hongyu Bai, Jiaqi Zeng, Chunzheng ZhuAbstract
Medical diagnostic reasoning requires verifiable links between visual evidence and clinical knowledge, yet current medical vision language models are aligned with objectives that reward the wrong behavior. Uniform supervised fine tuning lets easy cases dominate updates while clinically critical boundary cases saturate prematurely. Sparse rewards based only on final-answer correctness cannot assess anatomical grounding or clinical logic, inviting reward hacking through answer shortcuts. We propose MedCBR, a two-stage alignment framework coupling boundary-aware preference optimization with rubric-grounded reinforcement learning. First, we construct counterfactual boundary preferences at the model's capability frontier using empirical pass rates and preference pairs that share reasoning prefixes but diverge at decisive diagnostic branches. Difficulty Weighted Boundary Preference Optimization (DBPO) concentrates learning on this calibrated boundary region. Second, we distill reusable clinical rubrics from boundary trajectories and activate them according to prediction entropy. Entropy Gated Grounded Policy Optimization (EGPO) rewards answer correctness, anatomical grounding, and reasoning fidelity while suppressing rubric noise on reliable samples. A reference policy anchored to the boundary-aligned model couples population-level boundary priors with instance-level uncertainty, making diagnostic reasoning more accurate and clinically grounded. Experiments on six medical benchmarks show consistent improvements over strong general, specialized, and reinforcement learning baselines, reaching 61.2% average accuracy with the largest gains on challenging differential diagnosis tasks. Ablations show super-additive gains: combining the two stages exceeds the sum of their individual improvements.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39835
PDF
-
Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective
2026-10-29 10:47:57Chao Chen, Pengyang Shao, Wei Qin, Shijie Hao, Fei Shen, Richang HongAbstract
Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Despite the effectiveness of existing mitigation methods, why safety-aligned LLMs may still reject harmless queries under correct safety supervision remains insufficiently understood. To address this gap, we analyze over-refusal through the lens of representation and optimization. We make two observations: 1) the representations of harmful and over-refusal samples are visually distinguishable at certain intermediate layers but increasingly overlap in deeper layers; and 2) harmful-sample gradients exhibit high intra-class similarity and concentrate in a low-rank subspace. Moreover, they are more strongly aligned with refusal-target gradients than with correct helpful-target gradients on over-refusal prompts. This imbalanced gradient coupling can bias over-refusal samples toward refusal, while the reduced apparent representational separation in deeper layers may make it more difficult for the model to maintain a clear boundary between harmful and over-refusal samples. To this end, we propose GOAL (Gradient Orthogonalization with contrAstive Learning), a safety-alignment framework for mitigating over-refusal. Specifically, GOAL consists of two components: 1) to prevent imbalanced gradient coupling from biasing the optimization of over-refusal samples toward refusal, we orthogonalize over-refusal gradients against the low-rank refusal subspace extracted from harmful gradients; and 2) to explicitly enhance the separation between harmful and over-refusal representations, we introduce a contrastive learning objective. Extensive experiments across multiple models and benchmarks demonstrate that GOAL effectively mitigates over-refusal while preserving safety performance and general capabilities.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39802
PDF
-
PACE: Pareto-Adaptive Compression for Efficient Native MLLMs
2026-10-29 10:08:02Lei Tian, Chunzheng Zhu, Kai Wu, Yifan Zhang, Haihua YangAbstract
Native multimodal large language models (native MLLMs) jointly encode visual and linguistic sequences within a unified autoregressive Transformer, emerging as a promising paradigm for multimodal understanding. Unlike conventional ViT-based MLLMs relying on external vision encoders, ViT-free native MLLMs tokenize pixel patches directly, potentially suffering severe visual token redundancy. A pilot study confirms this: unlike ViT-based models that degrade under compression, ViT-free MLLMs tolerate aggressive compression with near-lossless or even improved performance. Yet existing compression methods target ViT-based settings, leaving native MLLMs, which stand to gain the most, unexplored. To close this gap, we introduce an analysis pipeline centered on token discriminability and cross-dimensional heterogeneous redundancy, revealing that (i) redundancy is distributed independently and heterogeneously along height and width axes, and (ii) early-layer visual tokens are indiscriminable and uniformly redundant. Guided by these findings, we propose PACE (Pareto-Adaptive Compression for Efficient Native MLLMs), the first visual token compression framework tailored for native MLLMs with Multimodal-RoPE. Leveraging dimensional decoupling of positional encoding, PACE decomposes attention into two orthogonal spatial saliency estimates along height and width, gated by a positional attention signal, yielding direction-aware importance with negligible overhead. It further casts token budget allocation as Pareto optimization over performance preservation, inference efficiency, and spatial coverage, jointly identifying optimal compression depths and retention ratios. Experiments show PACE maintains near-lossless performance at only 25%-50% visual token retention, even improving several benchmarks, while delivering over 2x FLOPs reduction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.24005
PDF
-
MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery
2026-10-29 09:46:50Yikun Zhang, Xiwei Cheng, Mingze Yuan, Yu Zhang, Brian Shim, Aarti Krishnan, Daniel Rosen, Kunyang Sun, Yingze Wang, Zhenfeng Deng, Botao Yu, Bingxu Liu, David Liu, Tianyu Liu, Yuanqi Du, Nir Hacohen, James J. Collins, Wengong JinAbstract
Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but automation alone does not address how to optimize workflows for new tasks or improve their development through experience. Here we introduce MoLRSI, an AI agent that combines systematic optimization of workflows and model architectures with persistent cross-task memory to recursively improve its search policy for molecular discovery. Workflow performance, refinement outcomes, and execution feedback guide subsequent searches, allowing the agent to improve both its workflows and its strategy for developing them. We evaluate MoLRSI in two challenging molecular discovery settings that require balancing competing properties. In antibiotic discovery, MoLRSI developed a screening workflow balancing antibacterial activity, cytotoxicity and structural novelty, achieving an experimental hit rate of 15.9%, compared with 8.7% for a previous expert-led workflow using the same training data and screening library. In de novo peptide-MHC binder design, MoLRSI developed workflows that jointly consider target binding and specificity, producing eight experimentally validated hits against MART-1 and SARS-CoV-1 pMHCs with preferential binding over tested off-targets while Claude Science completely failed. These findings demonstrate how experience-guided workflow optimization can address competing discovery objectives while improving the search strategies used in subsequent campaigns.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39714
PDF
-
Practical Assessment of Agentic Systems in Acoustics
2026-10-29 09:29:07Arne Hildenbrand, Philipp Diel, Zhuo Cao, Hanno Scharr, Stefan Pischinger, Steffen MarburgAbstract
In engineering, applications of artificial intelligence have so far been largely limited to surrogate models and optimization tasks. Large language models changed this, as they can write software from a task given in words. Placed inside a harness, a system of components that lets it search for information and execute software, such a model becomes an agent that can take over recurring engineering tasks. This work measures how the model and the elements of the harness shape the performance and behavior of the agent in two common acoustic applications. In the first, the agent detects and locates faults in audio recordings from a vehicle interior with near-perfect accuracy. A benchmark on this task shows that a weak model sets a limit that no harness design can overcome, and that design choices take effect only once the model is capable enough to use them. In the second, a case study on the design of a metamaterial unit cell, the agent reliably finds designs that achieve a specified insertion loss over a given frequency range. The results aim to help the reader understand what each element of an agent contributes and how to design an agent for acoustic tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39685
PDF
-
Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels
2026-10-29 09:28:19Qin-Wen Luo, Sheng Ren, Xiang Chen, Rui Liu, Jun Fang, Naiqiang Tan, Jun Wang, Hua Chai, Sheng-Jun HuangAbstract
Deep search agents extend language models by interleaving reasoning with external retrieval. However, effective search-agent training requires addressing two challenges beyond final-answer optimization. First, the capability frontier of agents is largely determined by training questions, whereas fixed or labeled task collections cannot adapt as agents improve. Second, outcome-only reinforcement learning treats all successful trajectories equally, even when some correct answers rely on redundant searches, creating an inherent tension between answer accuracy and tool efficiency. To address these issues, we introduce \textsc{ZEST-Search}, a zero-label and tool-efficient framework for search-agent training via heterogeneous co-evolution. Starting from unlabeled reference questions, \textsc{ZEST-Search} constructs validated search tasks online through an answer-first and evidence-path-guided generation process. A heterogeneous proposer adaptively constructs training tasks around the solver's evolving capability boundary, while the solver learns search-augmented reasoning through reinforcement learning. To jointly optimize task difficulty and search efficiency, \textsc{ZEST-Search} employs an intermediate-difficulty reward for the proposer and a task-local tool-aware reward for the solver, encouraging informative tasks and correct answers with fewer redundant searches. Experiments on seven general-domain and multi-hop question answering benchmarks demonstrate that \textsc{ZEST-Search} consistently improves search-agent performance while achieving higher tool efficiency without labeled search-training data or expert search trajectories. Further analyses show that heterogeneous generation, adaptive difficulty control, and tool-aware optimization enable more effective search-agent training.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39682
PDF
