Academic Intelligence · Curated Daily

探索全球前沿学术脉络

AcademicHub 汇聚顶级期刊与预印本平台的实时文献。定制您的专属科研雷达,利用大语言模型自动生成交叉领域文献分析简报。

01.
arXiv (math.PR) 2026-06-15

The 1/4-phenomenon of placement probabilities of tilings in the Aztec diamond

arXiv:2512.08377v2 Announce Type: replace-cross Abstract: We consider domino tilings of the Aztec diamond. Using the Domino Shuffling algorithm introduced by Elkies, Kuperberg, Larsen, and Propp in arXiv:math/9201305, we are able to generate domino tilings uniformly at random. In this paper, we investigate the probability of finding a domino at a specific position in such a random tiling. We prove that this placement probability is always equal to $1/4$ plus a rational function, whose shape depends on the location of the domino, multiplied by a position-independent factor that involves only the size of the diamond. This result leads to significantly more compact explicit counting formulas compared to previous findings. As a direct application, we derive explicit counting formulas for the domino tilings of Aztec diamonds with $2\times 2$-square holes at arbitrary positions.

02.
arXiv (CS.CL) 2026-06-11

DEFINED: A Data-Efficient Computational Framework for Fine-Grained Creativity Assessment in Debate Scenarios

Human creativity has emerged as a critical competency in the era of large language models. Assessing creativity in complex, open-ended environments is a grand challenge in data mining, currently hindered by a reliance on standardized simple tasks and the scarcity of fine-grained expert data. As an ecologically valid assessment context, debate reflects multiple dimensions of creativity, encompassing both divergent thinking and convergent thinking. Moreover, debate is a data-rich domain, with a large volume of publicly accessible materials. Current mainstream automated scoring methods are poorly suited to complex settings such as debate, and therefore still rely on costly human evaluation. To this end, this paper proposes DEFINED, a data-efficient computational framework for fine-grained creativity assessment in debate scenarios. DEFINED operationalizes debate creativity through a hierarchical eight-dimensional metric system, implemented via a pre-trained autoregressive language model with a hierarchical scoring head that supports both fine-grained and coarse-grained evaluation. Statements and their associated expert scores were obtained from authentic debate competitions, and a constrained data augmentation strategy was employed to address the elite bias inherent in the original data. DEFINED adopts a mixed-granularity training strategy enabling robust learning from limited fine-grained supervision annotated by trained graduate experts. To rigorously validate ecological validity beyond synthetic benchmarks, we incorporate an empirical study with debate-naive participants, utilizing these authentic data to serve as a qualitative case study for mid-to-low proficiency populations. Across our evaluation protocol, our scoring model achieves accurate and stable scoring, outperforming prompt-based large language model evaluators and existing debate scoring methods.

03.
arXiv (CS.AI) 2026-06-24

FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning

arXiv:2606.24231v1 Announce Type: new Abstract: Multimodal driving planning faces a long-standing tension between two paradigms: scoring-based methods benefit from dense reward supervision but are confined to a fixed action vocabulary, while anchor-based methods generate proposals dynamically yet suffer from sparse supervision constrained to a single ground-truth trajectory. In this work, we propose FlowR2A, which resolves this tension by reframing simulation-based rewards from discriminative targets into generative conditions. By learning the reward-conditioned action distribution from dense trajectory-reward pairs with a flow-matching decoder, FlowR2A unifies the dense supervision of scoring-based methods with the proposal generation of anchor-based methods in a single generative model, forcing the model to internalize the correlation between an action and its outcomes in safety, progress, comfort, and rule compliance. To balance hard safety constraints against soft progress objectives, we introduce fine-grained per-timestep reward conditioning and reward noise augmentation. The generative formulation naturally supports controllable test-time sampling via reward guidance and anchored sampling, producing high-quality proposals. FlowR2A achieves state-of-the-art results on the NAVSIM v1 and v2 benchmarks, with multimodal proposals of substantially higher quality than prior methods.

04.
arXiv (CS.CL) 2026-06-19

TSAssistant: A Human-in-the-Loop Agentic Framework for Automated Target Safety Assessment

Target Safety Assessment (TSA) requires systematic integration of genetic, transcriptomic, target homology, pharmacological, and clinical data to evaluate potential safety liabilities of therapeutic targets. This process is labor-intensive and expert-dependent, posing challenges in scalability and reproducibility. We present TSAssistant, a human-in-the-loop multi-agent framework that decomposes TSA report generation into a workflow of specialized subagents: Research Subagents that each ground and cite a single TSA domain, and Synthesis Subagents that integrate findings across domains. Subagents retrieve and synthesize evidence from curated biomedical sources through standardized tool interfaces and produce individually citable, evidence-grounded sections, with behavior shaped by a hierarchical instruction architecture that separates coordination logic from domain expertise and user intent. To complement these soft constraints, programmatic execution hooks and persistent memory stores enforce hard constraints across the workflow, while an interactive refinement loop allows experts to review and revise individual sections with full conversational context preserved across iterations. Rather than a single holistic comparison, we decompose report quality into reproducibility, evidential grounding, task-level accuracy, and controllability under expert oversight, finding high reproducibility and grounding, substantial agreement with the human reference, and net-positive expert-driven refinement.

05.
arXiv (CS.CV) 2026-06-18

SAMA: Semantic Anchor-aligned Augmentation for Unified Low-Resource Multimodal Information Extraction

Multimodal Information Extraction (MIE)-covering tasks such as Multimodal Named Entity Recognition (MNER), Relation Extraction (MRE), and Event Extraction (MEE)-is essential for understanding multimedia content but remains constrained by severe data scarcity. Although data augmentation is a promising remedy, existing approaches are impeded by coarse cross-modal alignment and fragmented, task-specific designs that fail to exploit shared semantic knowledge. To overcome these limitations, we introduce Semantic Anchor-aligned Multimodal Augmentation (SAMA), a unified framework for generating high-fidelity, task-aware synthetic data. SAMA constructs structured semantic anchors from ground-truth labels to guide a Collaborative Multi-Experts Multimodal Large Language Model (CME-MLLM), which integrates a Universal Adapter for shared semantics with Task-Specific Adapters to produce diverse yet constraint-compliant textual samples. For image synthesis, SAMA employs an Anchor-Preserving Diffusion mechanism that uses anchor-weighted prompts and latent conditioning to maintain critical semantic anchors while diversifying visual contexts. To eliminate the need for manual verification, SAMA further introduces a Dual-Constraint Filtering module that selects synthetic samples based on both cross-modal consistency and anchor fidelity. Extensive experiments across benchmark datasets for MNER, MRE, and MEE demonstrate that SAMA consistently outperforms state-of-the-art augmentation baselines under both fully supervised and low-resource settings, underscoring its versatility, robustness, and effectiveness.

06.
arXiv (quant-ph) 2026-06-19

Many-body chirality of topological stabilizer states

arXiv:2606.20472v1 Announce Type: new Abstract: A defining feature of chirality is the distinction between a system and its mirror image. Despite extensive experimental observations of chiral phases and theoretical advances, a quantum-information theoretic characterization of chirality based solely on the entanglement structure of many-body quantum states remains elusive. Here, we introduce the notion of many-body chirality by formulating it as an obstruction to transforming a quantum state into its complex conjugate through finite-depth local operations. We rigorously establish many-body chirality for stabilizer realizations of $\mathbb{Z}_d^{(k)}$ anyon theories, proving that complex conjugation can be implemented by local quantum channels if and only if the underlying anyon data are mirror invariant. This reveals forms of chirality that evade conventional diagnostics, including examples with vanishing modular commutator, vanishing chiral central charge, and commuting-projector realizations. We further show that this obstruction is intrinsically four-partite, while invisible to tripartite entanglement structure. Finally, we prove that $\mathbb{Z}_d^{(k)}$ states with $d>2$ possess intrinsic many-body imaginarity: their complex phase structure cannot be removed by finite-depth local unitaries. Remarkably, this includes states that are not many-body chiral.

07.
arXiv (quant-ph) 2026-06-16

Decoherence-free algebras in quantum dynamics

arXiv:2403.12926v2 Announce Type: replace Abstract: In this Article we analyze the algebraic properties of the asymptotic dynamics of finite-dimensional open quantum systems in the Heisenberg picture. In particular, a natural product (Choi-Effros product) can be defined in the asymptotic regime. Motivated by this structure, we introduce a new space called the Choi-Effros decoherence-free algebra. Interestingly, this space is both a C*-algebra with respect to the composition product, and a B*-algebra with respect to the Choi-Effros product. Moreover, such space admits a direct-sum decomposition revealing a clear relationship with the attractor subspace of the dynamics. In particular, the equality between the attractor subspace and the Choi-Effros decoherence-free algebra is a necessary and sufficient condition for a faithful dynamics. Finally, we show how all the findings do not rely on complete positivity but on the much weaker Schwarz property.

08.
PLOS Computational Biology 2026-06-09

Multi-stable oscillations in cortical networks with two classes of inhibition

by Arnab Dey Sarkar, Bard Ermentrout In the classical view of cortical rhythms, interactions between excitatory pyramidal neurons (E) and inhibitory parvalbumin-expressing interneurons (I) are sufficient to generate gamma- and beta-band oscillations. However, it is now well established that multiple inhibitory interneuron subtypes exist and that they play important roles in the generation and modulation of these rhythms. In this paper, we develop a spiking network model consisting of populations of E, I, and an additional interneuron type, somatostatin-expressing neurons (S), which receive excitation from the E cells and inhibit both the E and I populations. The S cells are further modulated by a third inhibitory subtype, vasoactive intestinal peptide (VIP) neurons, which receive inputs from other cortical areas. We reduce the spiking network to a system of nine differential equations that describe the mean membrane potential, firing rate, and synaptic conductance for each population. Using this reduced model, we identify a wide range of parameters that exhibit multiple coexisting rhythms. Employing tools from nonlinear dynamics, we then explore the roles of the two classes of inhibition, as well as VIP modulation, in shaping the properties of these rhythms.

09.
arXiv (CS.LG) 2026-06-17

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

arXiv:2606.18089v1 Announce Type: new Abstract: Post-training pipelines that combine supervised fine-tuning (SFT) with reinforcement learning (RL) have emerged as the key recipe for transforming large language models (LLMs) into robust reasoners. We argue that this combined success is driven by compositional generalization, which we formalize through a hierarchical latent selection model. In this framework, reasoning traces are generated by a cascade of discrete latent selection variables corresponding to reusable atomic modules, including both skills (local operations) and routing mechanisms (how intermediate information is selected, reused, and composed). Within this model, we theoretically show that SFT and RL play asymmetric, complementary roles: SFT supplies the raw module materials in compositional traces, and RL decomposes those traces to identify the latent atomic modules and enable compositional generalization. We design controlled experiments to validate this theory. Our results demonstrate that RL can extract atomic modules from compound traces supplied by SFT and recombine them to solve new configurations. Moreover, we find that training on compound traces yields stronger generalization than training on isolated atomic modules. Finally, we investigate the relationship between SFT and RL data and identify an effective protocol in which SFT ensures coverage of all atomic modules through compositional traces, while RL focuses on novel compositions outside the SFT support to drive exploration.

10.
arXiv (CS.AI) 2026-06-18

Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents

arXiv:2606.19319v1 Announce Type: cross Abstract: Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively discover, structure, and query enterprise data. We present Data Intelligence Agents (DIA), a system of three agents (Data Interpreter, Schema Creator, and Query Generator) that compresses this workflow by treating autonomous coding agents (ACAs) as a first-class abstraction: rather than emitting text, the agents generate, execute, validate, and repair concrete artifacts, draw on a shared memory for experience reuse, and surface each for review by domain experts. DIA is deployed in production for enterprise customers. We study the Query Generator in depth and evaluate it in fully autonomous mode across seven SQL benchmarks spanning four task categories and four dialects. It matches or surpasses the best published results on all seven, demonstrating that an architecture grounded in execution, built on ACAs and a shared memory, generalizes across the data intelligence workload with adaptation confined to natural-language instructions.

11.
arXiv (quant-ph) 2026-06-19

Topological Codes Based on Space Groups

arXiv:2606.20548v1 Announce Type: new Abstract: Topological codes form one of the most important classes of stabilizer codes. Most existing algebraic constructions and analyses of topological codes assume translation invariance. Here we show that topological codes can arise in more general settings by incorporating point group operations. The central construction is a class of Calderbank-Shor-Steane (CSS) codes called space-group codes, whose check operators are built from group-algebra templates over space groups that combine translations with point-group operations. We develop methods for analyzing topological properties of space-group codes using ring-modules and their invariant theory. At first glance, space-group codes might appear to complicate practical implementation; however, we find that they can exhibit greater locality than previous codes based purely on translations. Our framework thus extends the landscape of topological codes and opens up a broader design space for the co-design of topological codes with quantum computing platforms.

12.
arXiv (CS.AI) 2026-06-16

From Tokens to Regions: CUDA-Sensitive Instruction Tuning for GPU Kernel Generation

arXiv:2606.16231v1 Announce Type: cross Abstract: High-performance CUDA kernels are essential for scalable AI systems, while Large Language Models (LLMs) still struggle to generate correct kernels due to strict and implicit execution constraints. Existing LLM-based approaches either rely on costly agentic or reinforcement-learning (RL) pipelines, or adopt supervised fine-tuning (SFT) objectives that fail to explicitly model CUDA sensitivity, namely code tokens or regions tightly coupled with execution constraints. In this work, we investigate CUDA sensitivity from the perspective of token confidence patterns, showing that CUDA sensitivity appears at both token and region levels, where most CUDA-sensitive tokens are predicted with high confidence, while a smaller low-confidence subset forms regions corresponding to execution-critical structures. These findings suggest that effective CUDA kernel generation should both leverage high-confidence CUDA-sensitive tokens and preserve low-confidence CUDA-sensitive regions. Building on these insights, we propose \underline{CUDA-\underline{Se}nsitive Instruction \underline{T}uning (CuSeT)}, a low-cost post-training method within a simple SFT framework. CuSeT follows the principle of ``from tokens to regions'' by combining adaptive token-level masking with region-aware sample reweighting. Experiments show that CuSeT consistently improves functional correctness across multiple model families and scales, outperforming standard SFT and advanced SFT variants, while achieving competitive performance against frontier CUDA kernel generation models with substantially lower inference cost.

13.
arXiv (CS.LG) 2026-06-11

Deep Learning of Solver-Aware Turbulence Closures from Nudged LES Dynamics

arXiv:2604.23874v3 Announce Type: replace-cross Abstract: The differentiable physics paradigm may be leveraged as an a-posteriori approach for discovering turbulence closure models by embedding a neural network parameterization directly inside the solver and optimizing it given potentially sparse target data. This addresses a key limitation of a-priori learning where direct numerical simulation (DNS) data is used to approximate the subgrid stress with the assumption of a low-pass filter. Closures trained in this a-priori manner frequently lead to unstable deployments due to the mismatch between the assumed filter and the effect of numerical discretizations and coarse-graining. In comparison, while typically stable during deployment, a-posteriori learning incurs high computational costs due to the need to backpropagate through a large eddy simulation (LES) solver. Furthermore, a-posteriori methods are challenging to apply broadly since they require significant modification of existing solvers. Finally, both approaches are limited when generalization is desired across different numerical schemes with their implicit filtering characteristics. In this work, we present a deep-learning approach for turbulence closure modeling built on the continuous data assimilation framework. Our approach enables the a-priori training of closures using sparsely observed DNS data without modifying or differentiating through the LES solver, while preserving stability during deployment for the recovery of invariant statistics. We focus on the model's ability to adapt to different discretizations by explicitly conditioning it on the numerical scheme. We use two- and three-dimensional canonical cases to test our framework and show that the learned correction systematically tracks the discretization error of the coarse solver.

14.
arXiv (CS.LG) 2026-06-16

Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation

作者:

arXiv:2605.04998v2 Announce Type: replace-cross Abstract: This revision updates a pop-to-jazz chord-generation rehearsal study. Best-epoch metrics still show that modest pop rehearsal preserves pop accuracy while improving jazz prediction, but v2 corrects released-checkpoint selection: the released F1 equals Phase 0, F2 had a transcription error, and ft-pop80-v2 restores a hash-distinct jazz-adapted F1 across 3 seeds.

16.
arXiv (CS.AI) 2026-06-19

Emergent Alignment

arXiv:2606.19527v1 Announce Type: new Abstract: Can Large Language Models (LLMs) discern when their own outputs are misaligned with human ethics? And can they self-correct? We endow an LLM with a conscience step that reviews its own reasoning and outputs, and we extend the training loss with an alignment component using Direct Preference Optimization (DPO) to steer the model away from non-ethical outputs. The result is an online technique to align models in a wide range of applications: training, fine-tuning, adversarial prompting, and zero-shot learning. It does not require a weaker or stronger judge, relying instead on a frozen copy of itself. In previous work, the Emergent Misalignment scenario showed a range of emergent unethical behaviors from fine-tuning the model to hack code. Instead, we empirically show how to achieve Emergent Alignment: a single high-level introspective question steers training toward an ethical model under the same code hacking scenario.

17.
arXiv (CS.LG) 2026-06-18

Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting

arXiv:2606.18367v1 Announce Type: new Abstract: Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes. We introduce regime-stratified evaluation and apply it to three TSFMs on two standard traffic speed benchmarks. Traffic exhibits abrupt regime switching between free-flow and congested states, producing bimodal speed distributions during transitions. When we stratify by traffic regime, both accuracy and prediction-interval coverage degrade sharply during transitions: transition-regime MAE reaches 11 mph (versus 3 mph overall), and empirical coverage of 90% prediction intervals drops as low as 55%. These failures are invisible in aggregate metrics because free-flow observations dominate the sample. A simple historical conditional baseline (sampling from per-sensor training distributions) achieves better transition coverage than any TSFM, but has far worse overall accuracy. We propose bimodal mixture augmentation (BMA), a post-hoc method that combines TSFM forecasts with historical distributional knowledge, approaching the historical baseline's transition coverage while preserving the TSFM's accuracy. Our results suggest that TSFM benchmarks should incorporate regime-aware evaluation to surface failures that aggregate metrics hide.

18.
arXiv (CS.AI) 2026-06-24

Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context

arXiv:2605.07565v2 Announce Type: replace-cross Abstract: We study Bayesian Optimisation (BO) in settings where the objective function is influenced by uncontrollable environmental contexts governed by an unknown probability distribution. In practice, the contextual distribution must be estimated from empirical data, a process that inherently introduces distributional mismatch, producing sub-optimal results. While Distributionally Robust Optimisation (DRO) provides a framework to mitigate these risks, existing robust BO methods frequently suffer from high computational complexity, rely on discretisation of continuous context spaces, or impose restrictive assumptions on the structure of the ambiguity set. To overcome these limitations, we propose Ensemble Distributionally Robust Bayesian Optimisation (EDRBO). Our framework leverages the expressive power of ensemble surrogate models to approximate the black-box function while simultaneously accounting for contextual uncertainty. By utilising Wasserstein ball as ambiguity sets, EDRBO provides a robustified acquisition function that remains computationally tractable and natively handles continuous context spaces. We establish a rigorous theoretical foundation for our approach by proving sublinear cumulative regret guarantees of order $\mathcal{O}(\gamma_T \sqrt{T})$, where $\gamma_T$ represents the maximum information gain within the ensemble. Finally, we provide extensive empirical evaluations that corroborate our theory and demonstrate the state-of-the-art performance of EDRBO.

19.
bioRxiv (Bioinfo) 2026-06-11

OMIO: A policy-driven Python library for reproducible microscopy image I/O

Modern fluorescence and multiphoton microscopy workflows operate within a heterogeneous ecosystem of file formats, partially overlapping metadata standards, and reader-specific conventions. In practice, this frequently leads to silent axis misinterpretations, loss or corruption of physical voxel size information, and laboratory-specific glue code that is fragile, poorly documented, and difficult to reproduce. OMIO, short for Open Microscopy Image I/O, addresses these issues by providing a lightweight, policy-driven image I/O layer for Python that enforces a canonical, OME-compatible data representation at the API boundary. The central contribution of OMIO is the explicit separation of low-level format access from semantic normalization. Existing reader libraries are used as interchangeable backends for extracting pixel data and available metadata, while OMIO enforces axis conventions, metadata interpretation, and fallback decisions in a centralized and auditable policy layer. This design allows heterogeneous microscopy inputs to be converted into a stable representation without propagating backend-specific assumptions into downstream analysis code. The core design principles of OMIO include canonical axis semantics (TZCYX), robust metadata normalization with explicit and auditable fallbacks, memory-aware operation via optional Zarr-based backends, and workflow-level semantics that extend beyond individual files to folder stacks and BIDS-like project structures. This architecture allows OMIO to orchestrate existing reader libraries into a coherent and reproducible I/O pipeline without replacing or duplicating their functionality. OMIO is implemented as an open-source and community-oriented system in which support for additional file formats and metadata conventions can be added incrementally through modular reader backends. By encouraging the contribution of example datasets, backend extensions, and feature requests, OMIO is designed to evolve alongside emerging acquisition systems while preserving strict semantic guarantees at the interface level. The resulting standardized OME-TIFF outputs are immediately suitable for downstream quantitative analysis and interactive inspection in scientific Python workflows, including workflows based on ImageJ and Napari.

20.
arXiv (CS.AI) 2026-06-16

BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks

arXiv:2606.14734v1 Announce Type: cross Abstract: Motivation: Gene regulatory network inference from single-cell RNA sequencing (scRNA-seq) data is important for uncovering cell-state-specific transcriptional programs. However, scRNA-seq measurements are sparse and noisy, and experimentally validated TF-target interactions remain limited, making reliable inference challenging. Although graph neural networks have advanced GRN prediction, existing methods often rely on biologically unconstrained graph augmentation, such as random edge perturbation, and insufficiently control information transfer between genes and cells. These limitations may distort regulatory structures and weaken robustness under noisy and weakly supervised settings. Results: To address these issues, we propose an innovative framework named Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks (BRIDGE). BRIDGE extracts gene and cell representations from the expression matrix and its matrix dual, and performs contrastive learning in the gene space and cell space between self and neighbors across the co-expression-refined regulatory view and the original graph. It then applies heterogeneous gated encoding to adaptively regulate information transfer between genes and cells, enabling robust transcription factor-to-target gene prediction. Experiments on benchmark datasets spanning three network types and seven cell types show that BRIDGE achieves state-of-the-art AUROC and AUPRC in most settings. In particular, on Specific networks, BRIDGE improves average AUPRC by 5% over the second-best baseline, GCLink. In cross-cell-type few-shot transfer, BRIDGE consistently outperforms GCLink and GENELink across all six target cell types. A case study on hESC further supports the biological relevance of the predictions, with 9 of the top 10 and 46 of the top 100 novel TF-target interactions validated by ChIPBase.

21.
arXiv (CS.CL) 2026-06-11

PRInTS: Reward Modeling for Long-Horizon Information Seeking

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can guide agents by ranking candidate steps at test-time, existing PRMs - designed for short reasoning with binary judgment - cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs, nor handle the rapidly growing context in long-horizon tasks. To address these limitations, we introduce PRInTS, a generative PRM trained with dual capabilities: (1) dense scoring based on the PRM's reasoning across multiple dimensions of step quality (e.g., interpretation of tool outputs, tool call informativeness) and (2) trajectory summarization that compresses the growing context while preserving essential information for step evaluation. Extensive evaluations across FRAMES, GAIA (levels 1-3), and WebWalkerQA (easy-hard) benchmarks on multiple models reveal that best-of-n sampling with PRInTS enhances information-seeking in open-source models as well as specialized agents, matching or surpassing frontier models with a much smaller backbone agent and outperforming other strong reward modeling baselines.

22.
arXiv (CS.AI) 2026-06-12

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

arXiv:2603.21563v5 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce two optimizer-agnostic credit assignment methods for converting joint outcomes into agent-specific learning signals. Counterfactual Credit for Policy Optimization (CCPO) estimates an agent's marginal contribution by comparing the realized joint outcome with a counterfactual outcome where that agent is removed. Self-Evaluated Credit for Policy Optimization (SEPO) uses constrained self- and peer-evaluations as a verifier-anchored credit signal while keeping the external task outcome dominant. Both operate at the reward-construction layer rather than as policy optimizers, producing role-specific rewards or advantages for GRPO, GSPO, or REINFORCE++. We instantiate these credit signals in a sequential Think–Solve setting and evaluate them on mathematical reasoning benchmarks. Results show that explicit credit assignment often improves dual-agent reasoning, especially on MATH500 and several out-of-distribution settings, while gains vary across models and datasets. Our code is available at: https://github.com/bhai114/ccpo.

23.
arXiv (CS.AI) 2026-06-24

Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles

arXiv:2505.02281v3 Announce Type: replace-cross Abstract: This paper explores the performance of a random Gaussian smoothing zeroth-order (ZO) scheme for minimising quasar-convex (QC) and strongly quasar-convex (SQC) functions in both unconstrained and constrained settings. For the unconstrained problem, we establish the ZO algorithm's convergence to a global minimum along with its complexity when applied to both QC and SQC functions. For the constrained problem, we introduce the new notion of proximal-quasar-convexity and prove analogous results to the unconstrained case. Specifically, we derive complexity bounds and prove convergence of the algorithm to a neighbourhood of a global minimum whose size can be controlled under a variance reduction scheme. Beyond the theoretical guarantees, we demonstrate the practical implications of our results on several machine learning problems where quasar-convexity naturally arises, including linear dynamical system identification and generalised linear models.

24.
arXiv (CS.AI) 2026-06-11

From Consumption to Reflection: Designing Human-AI Relations for Stable Reasoning

arXiv:2606.11195v1 Announce Type: cross Abstract: Large language models (LLMs) have transformed how humans access information, but not how we reason with it. Their fluency accelerates consumption while bypassing the slow, reflective processes that underpin sound judgment. This paper introduces Relational Reflective Intelligence (RRI), an inference-time governance layer that operationalizes reflection through auditable reasoning loops. RRI operates not inside the model but around it, providing a practical structure for stable, auditable reasoning between humans and LLMs. The core premise is that LLMs inherit cognitive vulnerabilities similar to those that shape human thought: reliance on intuitive shortcuts, confusion between representation and reality, and a preference for coherence over falsification. When humans and models share these tendencies, their errors compound. We refer to this as relational drift, a failure that arises from interaction rather than from the model alone. Addressing this requires a shift from modeling relations between words to structuring relations between model outputs and human reasoning. RRI provides this missing layer through three components: the Rose-Frame, which identifies likely breakdowns in reasoning; the Architect's Pen, which introduces targeted reflection steps at critical moments; and an inference-time workflow that embeds these steps without retraining the model. Together, these elements transform human-AI interaction into a joint reasoning system with explicit checkpoints, conflict surfacing, and an auditable trail of assumptions. Rather than making machines think like humans or forcing humans to reason like machines, RRI creates a structured interaction in which both compensate for each other's limitations. It reframes AI safety as a cognitive architecture problem, where reliable decisions depend on embedding reflection directly into the interaction process.

25.
arXiv (CS.LG) 2026-06-19

Learning universal approximations for partial differential equations with Physics-Informed Broad Learning System

arXiv:2606.19754v1 Announce Type: new Abstract: Partial differential equations (PDEs) play a central role in modeling complex physical, biological, and engineering systems. While traditional numerical solvers are robust, they often incur prohibitive computational costs due to mesh dependencies, whereas recent Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative but frequently suffer from slow convergence and optimization instability. To bridge this gap, this article proposes the Physics-Informed Broad Learning System (PIBLS), a novel backpropagation-free framework that reformulates PDE solving as a direct least-squares optimization. We improved an algorithm within this framework to handle nonlinear PDEs efficiently and provide a rigorous mathematical proof establishing the universal approximation property of PIBLS for these equations. Experiments on linear and nonlinear PDEs demonstrate that PIBLS is one to three orders of magnitude faster than conventional PINNs while achieving significantly higher solution accuracy. This framework provides a computationally efficient paradigm for scientific machine learning, offering a practical, high-speed alternative for real-time simulation and design optimization tasks.