arXiv:2607.14118v1 Announce Type: new
Abstract: Large language models (LLMs) can generate research ideas that appear novel to expert reviewers, but recent work also shows that such ideas often lack diversity, are difficult for LLMs to evaluate reliably, and may fail to translate into strong executed projects. This paper evaluates a controlled proxy benchmark for a pre-execution scaffolding problem: given a noisy pool of LLM-generated research ideas, how should a system allocate limited refinement effort to construct a stronger, more diverse, more execution-aware portfolio for human researchers under a fixed rubric? We introduce Budgeted Subset Refinement, a family of strategies that refine only a selected subset of candidates rather than refining all candidates uniformly. In a unified shared-candidate-pool evaluation across 10 random seeds and 10 research-ideation environments, raw generation and reranking alone produce no research-strong nonduplicate ideas under the benchmark rubric, while refinement is necessary for strong proxy-rated portfolios. Uniform refinement produces strong individual ideas but is not the best portfolio-level allocation of compute. Random-k refinement is a strong low-cost baseline, while diversity-aware MMR-k refinement gives the best overall proxy tradeoff: the highest research-strong nonduplicate yield, the lowest duplicate rate among successful methods, and the best cost per research-strong nonduplicate idea. A blinded external-judge robustness check on a balanced 72-item sample supports the broad refinement effect across independent model families, while showing that per-item rankings among refined strategies vary by judge. These results suggest that LLM research ideation systems should be evaluated not only as idea generators, but as budgeted support-allocation systems. The claims are scoped to proxy-rated portfolio quality and do not substitute for expert review or execution-grounded validation.
Science Journals
arXiv:2410.03057v3 Announce Type: replace
Abstract: Cross-subject Electroencephalography (EEG) classification typically achieves significantly lower performance than subject-dependent settings. Although this phenomenon has been widely observed in the literature, the underlying causes have not been systematically studied. In this paper, we design a series of controlled experiments to investigate the mechanisms behind the performance drop in cross-subject EEG classification across different EEG tasks. We show that the performance degradation can generally be attributed to two factors: inter-subject variability and shortcut learning. Specifically, multi-class-per-subject EEG classification tasks, such as motor imagery, emotion recognition, and ERP stimulus classification, are mainly affected by inter-subject variability, whereas single-class-per-subject EEG classification tasks, such as brain disease detection, are primarily influenced by shortcut learning based on subject-specific features. These findings provide new insights into the challenges of cross-subject EEG classification and emphasize the importance of appropriate evaluation protocols in EEG research. The code is available at https://github.com/DL4mHealth/EEG-Cross-Subject.
arXiv:2410.13508v2 Announce Type: replace
Abstract: Building on our prior work on axiomatization of exact real computation by formalizing nondeterministic first-order partial computations over real and complex numbers in a constructive dependent type theory, we present a framework for certified computation on hyperspaces of subsets by formalizing various higher-order data types and operations. We first define open, closed, compact and overt subsets for generic spaces in an abstract topological way that allows short and elegant proofs with computational content coinciding with standard definitions in computable analysis and constructive mathematics. From these proofs we can extract programs for testing inclusion, overlapping of sets, et cetera. To enhance the efficiency of the extracted programs, we then focus on Polish spaces, where we give more efficient encodings based on metric properties of the space. As various computational properties depend on the continuity of the encoding functions, we introduce a nondeterministic version of a continuity principle which is natural in our formalization and valid under the standard type-2 realizability interpretation. Using this principle we further derive the computational equivalence between the generic and the metric encodings. Our theory is fully implemented in the Coq proof assistant. From proofs in this Coq formalization, we can extract certified programs for error-free operations on subsets. As an application, we provide a function that constructs fractals in Euclidean space, such as the Sierpinski triangle, from iterated function systems using the limit operation. The resulting programs can be used to draw such fractals up to any desired resolution.
arXiv:2411.03747v4 Announce Type: replace
Abstract: Cooperative Localization is a promising approach to achieving safe quadrotor formation flight through precise positioning via low-cost inter-drone sensors. This paper develops an observability-aware control principle tailored to quadrotor formation flight with range-only inter-drone measurements. The control principle is based on a novel approximation of the local observability Gramian (LOG), which we name the Short-Term Local Observability Gramian (STLOG). The validity of STLOG is established by proving its link to directional estimation precision in nonlinear systems. We propose the Observability Predictive Controller (OPC), a receding-horizon controller that generates optimal inputs to enhance information gain in weakly observable state directions by maximizing the minimum eigenvalue of the STLOG. This reduces the risk of estimator divergence due to the unbounded growth of uncertainty in weakly observed state components. Monte Carlo simulations and flight experiments are conducted with quadrotors in a GNSS-denied ferrying mission, showing that the OPC improves positioning confidence and estimator robustness.
arXiv:2411.14802v4 Announce Type: replace
Abstract: Hierarchical graph rewriting is a highly expressive computational formalism that manipulates graphs enhanced with box structures for representing hierarchies. It has provided the foundations of various graph-based modeling tools, but the design of high-level declarative languages based on hierarchical graph rewriting is still a challenge. For a solid design choice, well-established formalisms with backgrounds other than graph rewriting would provide useful guidelines. Proof nets of Multiplicative Exponential Linear Logic (MELL) is such a framework because its original formulation of cut elimination is essentially graph rewriting involving box structures, where the so-called promotion boxes with an indefinite number of non-local edges may be cloned, migrated and deleted. This work builds on LMNtal (pronounced "elemental") as a declarative language based on hierarchical (port) graph rewriting, and discusses how it can be extended to support the above operations on promotion boxes of MELL proof nets. LMNtal thus extended turns out to be a practical graph rewriting language that has a strong affinity with MELL proof nets. The language features provided are general enough to encode other well-established models of concurrency. Using the toolchain of LMNtal that provides state-space search and model checking, we implemented cut elimination rules of MELL proof nets in extended LMNtal and demonstrated that the platform could serve as a useful workbench for proof nets.
arXiv:2412.03230v3 Announce Type: replace
Abstract: Chinese ASR correction is challenging because errors are often \emph{phonetic} (many characters share similar Pinyin) while the correction model must also obey a \emph{length constraint} under noisy N-best hypotheses. Existing approaches either exploit Pinyin only at the prompt/feature level without integrating it into model representations or rely on generative decoding that can drift in length. We propose \textbf{PERL}, a \textbf{constrained rephrasing pipeline} for Chinese N-best ASR correction that (i) predicts the target length and enforces it via mask budgeting, and (ii) fuses \emph{semantic} and \emph{phonetic} (Pinyin) representations through token-wise gates conditioned on sentence semantics. Experiments on Aishell-1 and our new domain N-best benchmark \textbf{DoAD} show that PERL consistently reduces CER (29.11\% on Aishell-1 and up to $\sim$70\% on DoAD) while maintaining low latency. We also provide analyzes of length generalization and phonetic--semantic interactions, showing when PERL relies on phonetic cues versus semantic constraints.
arXiv:2607.14494v1 Announce Type: new
Abstract: Complex knowledge base question answering (KBQA) is commonly approached through either information retrieval over a question-specific subgraph or semantic parsing into an executable logical form. We study the latter paradigm. Recent large language model agents make semantic parsing interactive: they alternate between reasoning, querying the knowledge base, and extending a partial SPARQL query. This interleaving reduces reliance on one-shot generation, but makes the quality of \emph{KB grounding} depend on what the interaction tools expose. Existing agents retrieve or prune candidate properties mainly through lexical relevance and instance-level observations, without systematically conditioning on entity types, property domains and ranges, or the expected answer type. We call this failure mode \emph{type-blind grounding}. It enlarges the grounding search space and often produces plausible-looking but semantically incompatible triple patterns that execute to empty results. We propose SAGA (\underline{S}chema-\underline{A}ware \underline{G}rounding for \underline{A}gentic Text-to-SPARQL Generation), a training-free framework that turns property exploration into a schema-constrained grounding operation. SAGA maintains a persistent bidirectional type state, filters known-incompatible property candidates at construction time, presents the remaining graph patterns in a compact schema-annotated format, and handles missing schema information permissively through empirical and trace-local evidence. Across nine benchmark settings over Wikidata and Freebase, SAGA achieves the highest F1 on all nine settings and the highest exact-match accuracy on eight, while reducing empty-result queries across all reported Wikidata settings.
arXiv:2607.14158v1 Announce Type: new
Abstract: This position paper explores how Agentic AI and Model Context Protocol (MCP) can support power-grid studies in a Transmission System Operator (TSO) context. We focus on integrating Large Language Models with numerical simulation tools, structured workflows, and human supervision. We identify key industrial requirements for agent assisted grid studies and introduce pypowsybl-mcp, an MCP-based interface exposing selected capabilities of our simulation tool, pypowsybl to AI agents. This first step provides a testbed to study how agents can setup simulations, execute analyses, retrieve results, and interact with power-system simulators through standardized tool calls. We also discuss principles for human-in-the-loop, multi-agent workflows and outline an evaluation strategy combining technical metrics and practitioner feedback. The paper positions MCP-based tool integration as a step toward more interactive, auditable, and scalable grid-study environments.
arXiv:2607.14159v1 Announce Type: new
Abstract: An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling. While harness design strongly affects agent behavior, most automatic improvement methods optimize narrower artifacts such as prompts, pipelines, or workflows, and deployed agents usually reuse a single global harness for all cases. We introduce MemoHarness, an adaptive harness optimization framework that learns from its own executions. MemoHarness decomposes the harness into six editable control dimensions, stores per-case diagnoses and distilled global patterns in a dual-layer experience bank, and adapts the learned harness to each test case using retrieved experience without test-time labels, feedback, or additional search. In our evaluation across shell-agent, code-generation, and analytical-reasoning benchmarks, MemoHarness improves over the fixed harnesses we compare against and shows selective transfer to unseen suites and base models. Its additional context can also remain cost-competitive when much of the retrieved experience is cacheable. These results provide evidence that execution experience is a practical substrate for building agent harnesses that are more adaptive than a single static configuration, while leaving broader claims about statistical robustness and component attribution to future work.
arXiv:2501.04016v4 Announce Type: replace
Abstract: Wasserstein barycentres represent average distributions between multiple probability measures for the Wasserstein distance. The numerical computation of Wasserstein barycentres is notoriously challenging. A common approach is to use Sinkhorn iterations, where an entropic regularisation term is introduced to make the problem more manageable. Another approach involves using fixed-point methods, akin to those employed for computing Fr\'echet means on manifolds. The convergence of such methods for 2-Wasserstein barycentres, specifically with a quadratic cost function and absolutely continuous measures, was studied by Alvarez-Esteban et al. (2016). In this paper, we delve into the main ideas behind this fixed-point method and explore how it can be generalised to accommodate more diverse transport costs and generic probability measures, thereby extending its applicability to a broader range of problems. We show convergence results for this approach and illustrate its numerical behaviour on several barycentre problems.
arXiv:2607.14936v1 Announce Type: new
Abstract: Real-world optimization problems often involve black-box functions and uncertainties in their evaluation, widely referred to as noisy optimization problems (NOPs). Evolutionary algorithms (EA), including Evolutionary Strategies (ES) and genetic algorithms (GA) have been commonly adopted to solve these problems in the contemporary literature. An ongoing challenge is the computational expense involved, given the number of evaluations required for good fitness estimation and ranking. Two fundamental methods commonly used for fitness estimation for NOPs are implicit averaging and explicit averaging. Explicit averaging uses resampling of solutions to improve the estimates, while implicit averaging typically uses a large population size with low resampling. Implicit averaging has been shown to have theoretical advantages for certain cases, which has motivated some recent approaches to use them. However, a recent study demonstrated that its performance is highly dependent on certain assumptions about the function, such as steepness and constant noise level, which may not apply for majority of the real world problems. Moreover, most existing algorithms have only considered homoscedastic noise, where the amplitude of variation is uniform across the entire search space, as opposed to more generic case of heteroscedastic noise. To address these issues, we introduce a set of heteroscedastic test problems and propose a novel confidence ranking method that employs a computationally efficient explicit averaging strategy with sampling budget adaptation. It is implemented within the Covariance Matrix Adaptation ES (CMA-ES) and GA frameworks to demonstrate its effectiveness and versatility. The resulting algorithm is evaluated on a range of problems with both homoscedastic and heteroscedastic noise, and it demonstrates superior performance compared to state-of-the-art approaches.
arXiv:2607.14983v1 Announce Type: new
Abstract: A VASS can be viewed as a finite-state automaton manipulating a fixed number (called its dimension) of counters holding non-negative values. The reachability problem, asking whether there is a run from one configuration, defined by a state and values of the counters, to another configuration, has been a long-standing algorithmic challenge in theoretical computer science. When the dimension is part of the input, the problem has been shown to be ACKERMANN-complete in 2021. For fixed dimension greater than 2, and in particular for dimension 3, the exact complexity of the reachability problem remains unclear. For a long time the known algorithms for the 3-dimensional VASS reachability problem had been non-elementary, while the best known lower bound is merely PSPACE hardness inherited from dimension 2. A recent breakthrough in (Czerwi\'nski, Jecker, Lasota, Orlikowski, ICALP 2025) gave the first elementary upper bound for the problem, namely 2-EXPSPACE. In this paper it is shown that the reachability problem in 3-VASS belongs to EXPSPACE. The proof is based on a hierarchical pumpability analysis, yielding a doubly-exponential length bound on the shortest runs between two configurations.
arXiv:2607.14303v1 Announce Type: new
Abstract: Reasoning or inference-scaling models are the new generation of Large Language Models (LLMs) capable of complex problem solving. To investigate their problem-solving capability in physics, we evaluated model o4-mini by OpenAI on solving traditional, end-of-chapter problems from Halliday and Resnick's "Fundamentals of Physics," spanning core topics in the undergraduate physics curriculum. Performance was analyzed across modality and problem difficulty. The model solved the problems with overall accuracy of about 90%, but performance depended strongly on representation: accuracy was much higher on text-only problems (96%) than on problems requiring coordinated interpretation of text and images (79%). Accuracy also declined significantly as the problem difficulty increased from low to medium to high. These results show that state-of-the-art LLMs can solve much of the standard introductory physics problems, but that their performance remains uneven and constrained by problem modality and problem difficulty.
arXiv:2505.04757v2 Announce Type: replace
Abstract: This paper introduces a novel approach to contextual stochastic optimization, integrating operations research and machine learning to address decision-making under uncertainty. Traditional methods often fail to leverage contextual information, which underscores the necessity for new algorithms. In this study, we utilize neural networks with combinatorial optimization layers to encode policies. Our goal is to minimize the empirical cost, which is estimated from past data on uncertain parameters and contexts. To that end, we present a surrogate learning problem and a generic primal-dual algorithm that is applicable to various combinatorial settings in stochastic optimization. Our approach extends classic Fenchel--Young loss results and introduces a new regularization method using sparse perturbations on the distribution simplex. This allows for tractable updates in the original space and can accommodate diverse objective functions. We establish sublinear convergence for the exact linear-parametric version and provide a bound on the non-optimality of the resulting policy in terms of the empirical cost. Experiments on three contextual stochastic optimization problems show that our algorithm is efficient and scalable, achieving performance comparable to state-of-the-art baselines with significantly reduced computational requirements.
arXiv:2505.22442v3 Announce Type: replace
Abstract: Offline RL (ORL) promises safe and sample-efficient deployment but existing methods rely on undocumented online interactions for hyperparameter tuning and lack reliable fully offline estimates of initial online performance. We introduce SOReL, a fully offline Bayesian model-based RL method that learns a posterior over dynamics, estimates policy value via predictive uncertainty, and enables complete offline hyperparameter selection. We further propose TOReL, which extends this tuning framework to arbitrary model-free and model-based ORL algorithms. We provide a regret analysis showing that Bayesian offline RL achieves the minimax-optimal parametric rate under standard regularity conditions. Together, our methods establish a practical and theoretically grounded framework for fully offline RL.
arXiv:2507.14316v5 Announce Type: replace
Abstract: Artificial Intelligence (AI) and indoor sensing increasingly support decision-making in spatial environments. However, traditional visualization methods impose a substantial mental workload when viewers translate this digital information into real-world spaces, leading to inappropriate reliance on AI. Embedded visualizations in Augmented Reality (AR), by integrating information into physical environments, may reduce this workload and foster more appropriate reliance on AI. To assess this, we conducted an empirical study (N = 32) comparing an AR embedded visualization (X-ray) and 2D Minimap in AI-assisted, time-critical spatial target selection tasks. Surprisingly, evidence shows that the embedded visualization led to greater inappropriate reliance on AI, primarily as over-reliance, due to factors like perceptual challenges, visual proximity illusions, and highly realistic visual representations. Nonetheless, the embedded visualization demonstrated benefits in spatial mapping. We conclude by discussing empirical insights, design implications, and directions for future research on human-AI collaborative decision in AR.
arXiv:2507.19474v2 Announce Type: replace
Abstract: This paper presents DINO-SLAM, a DINO-informed design strategy to enhance implicit (Neural Radiance Field -- NeRF) and explicit representations (Gaussian Splatting -- GS) in SLAM systems through the more comprehensive semantics understanding enabled by DINO. This latter alone, however, lacks proper 3D geometry understanding, allowing only for marginal improvements. Therefore, we rely on a Scene Geometry Encoder (SGE) to enrich DINO features into geometry-aware DINO features (geoDINO), to better understand those geometric relationships that vanilla DINO features fail to capture. Building upon it, we propose two foundational paradigms for NeRF and GS SLAM systems integrating geoDINO features. Compared to state-of-the-art methods, our DINO-informed pipelines achieve superior performance on the Replica, ScanNet, and TUM datasets.
arXiv:2607.14280v1 Announce Type: new
Abstract: Flow-matching-based vision-language-action (VLA) models have emerged as powerful policies for robotic manipulation, yet a critical capability remains underexplored: fine-grained behavioral control, the ability to govern how a robot performs a task by intervening on its internal representations. Representation steering is a well-established interpretability tool for language and vision-language models, where behavioral features are typically encoded as linear directions, but we show that these classic methods fall short in VLAs. We propose DiMaS, a Distribution-Matching Steering strategy tailored to flow-matching VLAs, which transports between representation distributions rather than shifting along a fixed direction, and show that it effectively controls behavior across two state-of-the-art VLAs. We further examine the generalizability of this strategy as the tasks it is learned from and evaluated on grow increasingly dissimilar, characterizing where behavioral control transfers and where it weakens. Finally, through an analysis of the representation structure of the action expert, we explain why classical linear steering falls short in the visuomotor setting: behavioral features are linearly decodable but not linearly steerable, which motivates the distribution-matching design of DiMaS. Our code is publicly available at https://github.com/pegah-kh/dimas, with additional results and videos at https://pegah-kh.github.io/dimas/
arXiv:2607.14286v1 Announce Type: new
Abstract: In this paper, we present a structure-preserving method for the compressible resistive Hall-magnetohydrodynamics (MHD) model. The differential operator is split into two parts: a hydrodynamic part consisting of the compressible Euler equations, and a magnetic part consisting of a system coupling the Lorentz force and the induction equation. The method uses continuous Lagrange elements for the Euler part and a curl-conforming finite element space for the magnetic part. The hydrodynamic part preserves the positivity of the density and internal energy, the conservation of total energy, and the minimum principle for the specific entropy. Owing to the choice of finite elements, the magnetic part preserves the divergence involution constraint. The fluid part is solved using explicit strong-stability-preserving Runge-Kutta (SSP-RK) methods, whereas the magnetic part is solved by Crank-Nicholson method, which requires using Newton's method. Coercivity estimates for the Jacobian of the corresponding Newton iteration are presented. We introduce a high-order artificial resistivity to improve the conditioning of the nonlinear residual and the invertibility of the Jacobian. Several challenging benchmarks, including a smooth whistler wave, the Orszag-Tang vortex for comparing resistive MHD with resistive Hall-MHD, and a magnetic reconnection problem, are solved to validate the robustness and accuracy of the method.
arXiv:2607.14250v1 Announce Type: new
Abstract: Personal AI assistants have attracted significant interest for their potential to enhance everyday life by automating routine tasks, supporting consequential decisions, and assisting with everyday personal matters. Yet despite rapid recent technical advances, these assistants continue to exhibit undesirable behaviors, such as sycophancy, overconfidence, and hallucination. We argue that these failures stem from a fundamental limitation: language models lack an explicit representation of the person beyond the context they are given, which we term as the \textbf{Severance Problem}. Even with rich personal context and strong commonsense reasoning capabilities from the backbone model, current AI assistants fail to represent what remains unknown about the user. We propose a simple solution: incorporating structured ignorance into the language model context via the \textbf{Severance Schema}, which explicitly outlines dimensions along which the model lacks knowledge about the user, including physicality, temporality, consequences, continuity, multiplicity, and interiority. Empirically, across five model families, with the Severance Schema, the assistant consistently reduces sycophancy, harmful advice, and hallucination. Notably, models with the schema ask clarifying questions when information about the user is missing, rather than confidently extrapolating from incomplete user information.
arXiv:2607.14353v1 Announce Type: new
Abstract: As automated decision-making and data-driven technologies pervade society and are used to manage consequential outcomes, understanding the technology's capabilities, limitations, and attendant risks in context requires analysis of full sociotechnical systems. Sociotechnical analysis of risks in highly complex systems provides clear lessons for the design and evaluation of AI systems, transcending a technical focus on reliable or "responsibly designed" components to understand risks at a systems level.
Human-made catastrophes have been studied for decades because of the severity of these events: consider Chernobyl, Three Mile Island, Fukushima-Daiichi, Bhopal, the Challenger disaster. A common misconception is that these kinds of events are freak accidents, resulting from the inherently unforeseeable interactions in complex systems. Closer examination reveals that the risks and hazards were well-known beforehand but not acted upon due to social structural, political and economic factors.
We outline several areas where the development and use of AI can benefit from learning these unlearned lessons: improved risk perception, communication, and analysis at the organizational level; traceability of requirements and responsibilities; and holistic approaches to responsibility and safety that include social and organizational dynamics as first-order engineering concerns. For each area, we offer concrete unlearned lessons and exemplify how they led to failure in prior accidents as well as examples of how these lessons remain unlearned for modern computing systems, particularly AI.
arXiv:2607.15027v1 Announce Type: new
Abstract: The integration of AI-driven systems in creative work has sparked debates among artists and legal communities about notions of ownership. Yet there remains little consensus on how ownership should be defined and attributed when human and AI contributions are intertwined. To provoke critical reflection on these tensions, we designed ArtSplit, a provotype that explicitly quantifies human and AI contributions across different stages of creative work. Rather than aiming to resolve ownership, the provotype was used to elicit artists' responses to the idea of attributing ownership through measurable actions in the creative workflow. We argue that quantification fails to align with artists' understandings of creative intent and agency, and that efforts to measure ownership risk diluting long-standing assumptions through which artists understand and practice creative work. This critique challenges the impulse to transform a historically and socially situated relation into a technical problem.
arXiv:2607.15003v1 Announce Type: new
Abstract: The deployment of autonomous cyber-physical systems in safety-critical environments requires closed-loop control strategies (i.e., policies) that are not only performant but also provably safe and robust. While learning-based methodologies such as Reinforcement Learning offer flexible and scalable approaches to automatically synthesize such controllers, they typically lack the formal guarantees necessary for safe deployment. To bridge this gap, we propose a novel simulation-based methodology to automatically synthesize policies with formal guarantees regarding performance, safety, and robustness specifications. Specifically, given a set of properties to verify, a confidence parameter $\delta$ and an allowable failure probability $\varepsilon$, our method guarantees that the synthesized policy comes with a certificate: with confidence at least $1 - \delta$, the probability of encountering a scenario where the given properties are violated is at most $\varepsilon$. We demonstrate the feasibility of our approach by developing SMC-ES, an algorithm that integrates Evolutionary Strategies with Statistical Model Checking-based verification. We evaluate SMC-ES on a suite of continuous control tasks using Gymnasium and Safety Gymnasium testbeds. Results show that, at the price of a sustainable increase in computational cost, our algorithm provides formal guarantees regarding performance, safety, and robustness specifications, while performing competitively against leading model-free Deep Reinforcement Learning (DRL) and Safe-DRL baselines.
arXiv:2607.14488v1 Announce Type: new
Abstract: Reinforcement Learning (RL) has demonstrated remarkable capabilities for solving complex robotic control problems, but its lack of safety guarantees severely limits deployment on hardware. In particular, as legged robots and manipulators often operate near safety-critical boundaries, out-of-distribution states can lead to failure upon deployment. To address this, we introduce Acc-CBF-QP, an acceleration-based Quadratic Program (QP) safety filter using Control Barrier Functions (CBFs) that constrains any RL policy onto a safe set at runtime without modifying training. The method applies to unconstrained and Safe-RL policies, and enforces joint position, velocity, torque, and collision constraints within a unified optimization framework. A key contribution is the formulation of RL+QP tasks that regulate deviation from the RL command when constraints would otherwise be violated. We introduce a TorqueTask, minimizing torque deviation, and a Forward Dynamics Task, minimizing induced acceleration deviation, thus providing principled control over safety-performance trade-offs. Experiments on a 7-DoF Kinova Gen3 manipulator and a 19-DoF Unitree H1 humanoid, both in simulation and on hardware, highlight substantial reductions in constraint violations. On the real H1 hardware, a Safe-RL policy alone yielded 10.04 violations/s, which were reduced by 92% to 0.80 violations/s when augmented with Acc-CBF-QP. On the Kinova Gen3, Acc-CBF-QP fully eliminated violations. Nominal task performance of the RL objective is preserved in violation-free regimes. Under aggressive velocity commands on H1, Acc-CBF-QP improves execution by preventing constraint-induced shutdowns, yielding longer survival times. The full pipeline is open-source.
arXiv:2607.14413v1 Announce Type: new
Abstract: We prove that every randomized synchronous Byzantine Agreement protocol in the full-information, strongly adaptive adversary model, secure against $t$ corrupt parties, has worst-case expected round complexity \[
\Omega\!\left(\frac{t^2}{n\log(n+1)}\right). \] This improves upon the seminal $\Omega(\frac{t}{\sqrt{n\log n}})$ bound of [Bar-Joseph, Ben-Or 98]. Our result matches the recent upper bound of $O\left(\min\left\{\frac{t^2\log n}{n},\frac{t}{\log n}\right\}\right)$ of [Dufoulon, Pandurangan 25], up to a $\log^2 n$ factor in the $t\ll n$ regime. Our proof takes inspiration from the recent works of [Etesami, Mahloujifar, Mahmoody 20] and [Haitner, Karidi-Heller 26]. Specifically, we prove a multi-round concentration lemma showing that any transcript event of probability $p$ can be forced with probability one by corrupting $O(\sqrt{n\log(\frac1p)})$ parties in expectation. From there, tools from [Chor, Merritt, Shmoys 89] allow us to lower-bound the probability of the protocol not concluding in $R$ rounds by $\frac{1}{n^{O(R)}}$, using a crash schedule involving at most $R$ parties. The combination of these techniques yields the desired bound.