arXiv:2605.05652v2 Announce Type: replace Abstract: Simulation-based inference (SBI) provides amortized Bayesian parameter inference from simulator-generated data without requiring explicit likelihood evaluation. Its reliability can degrade under model misspecification, where real-world observations are not well represented by the simulator used for training. Existing methods using unlabeled real-world data often align simulated and real-world data distributions, but marginal alignment alone does not directly preserve parameter-relevant information needed for posterior inference. We propose SPIN, an SBI framework with parameter-relevant information-preserving domain transfer using unlabeled, unpaired real-world observations. During training, SPIN translates labeled simulator observations toward the real-world domain and back to the simulator domain, using the original simulator labels to encourage domain transfer that preserves parameter-relevant mutual information. At test time, the learned real-to-simulator transport maps real-world observations into the simulator domain for posterior inference, without requiring real-world parameter labels or paired real--simulator observations. Across controlled synthetic and physical real-world benchmarks, SPIN improves real-world posterior inference, with the improvement becoming clearer as misspecification increases.
Science Journals
arXiv:2509.23352v3 Announce Type: replace Abstract: The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in generation quality. However, these gains often come at the cost of exhaustive exploration and inefficient sampling strategies due to slight variation in the sampling group. Building on this insight, we propose Dynamic-TreeRPO, which implements the sliding-window sampling strategy as a tree-structured search with dynamic noise intensities along depth. We perform GRPO-guided optimization and constrained Stochastic Differential Equation (SDE) sampling within this tree structure. By sharing prefix paths of the tree, our design effectively amortizes the computational overhead of trajectory search. With well-designed noise intensities for each tree layer, Dynamic-TreeRPO can enhance the variation of exploration without any extra computational cost. Furthermore, we seamlessly integrate Supervised Fine-Tuning (SFT) and RL paradigm within Dynamic-TreeRPO to construct our proposed LayerTuning-RL, reformulating the loss function of SFT as a dynamically weighted Progress Reward Model (PRM) rather than a separate pretraining method. By associating this weighted PRM with dynamic-adaptive clipping bounds, the disruption of exploration process in Dynamic-TreeRPO is avoided. Benefiting from the tree-structured sampling and the LayerTuning-RL paradigm, our model dynamically explores a diverse search space along effective directions. Compared to existing baselines, our approach demonstrates significant superiority in terms of semantic consistency, visual fidelity, and human preference alignment on established benchmarks, including HPS-v2.1, PickScore, and ImageReward. In particular, our model outperforms SoTA by $4.9\%$, $5.91\%$, and $8.66\%$ on those benchmarks, respectively, while improving the training efficiency by nearly $50\%$.
arXiv:2604.09173v2 Announce Type: replace Abstract: Managing large-scale vector datasets with disk-resident graph approximate nearest neighbor search (ANNS) systems incurs substantial storage overhead due to the co-location of vector data and auxiliary index metadata, which prevents the storage layer from exploiting their distinct compressibility. We present COMPASS, a component-aware compressed storage framework for disk-resident graph vector search. Leveraging data-index decoupling as a foundation, COMPASS losslessly compresses each component according to its distinct compressibility characteristics, thereby significantly reducing storage space. It further adapts the search and update paths to preserve their performance under compressed storage layouts. Evaluation on real-world public and proprietary billion-scale datasets shows that COMPASS reduces storage space by up to 58.7%, while delivering improved or competitive search and update performance compared to state-of-the-art disk-resident graph ANNS systems.
arXiv:2605.15925v1 Announce Type: new Abstract: Let $\mathbb{F}_{p^m}$ be the field containing $p^m$ elements where $p$ is an odd prime and $m \in \mathbb{N}$. In this article, we propose a unified approach to the study of skew constacyclic codes of length $np^s$ over the ring $R_k = \mathbb{F}_{p^m}[u]/\langle u^k \rangle,$ where $n, s, k \in \mathbb{N}$ and $\gcd(n, p)=1$. Consider the skew polynomial ring $R_k[x;\Theta]$, where $\Theta$ is an automorphism of $R_k$ such that $xa = \Theta(a)x$ for all $a \in R_k$. Let $f(x)$ be a central irreducible divisor of $x^{np^s} - \lambda$ of degree $l$ and multiplicity $j$ in $R_k[x;\Theta]$, where $\lambda $ is an invertible element in $R_k$. In this article, we study skew constacyclic codes of length \(np^s\) over \(R_k\), which reduces to the study of skew polycyclic codes of length $jl$ associated with a polynomial \(f(x)^j\). Using the fact that skew polycyclic codes associated with a polynomial \(f(x)^j\) can be described by the left ideal structure of the quotient ring $R_k[x;\Theta]/\langle f(x)^{j}\rangle$, we investigate this class of codes for specific choices of $\Theta$. In particular, if $\lambda$ is an invertible element of $\mathbb{F}_{p^m}$, we classify all left ideals and establish an isomorphism between skew cyclic and skew constacyclic codes, under suitable conditions. Furthermore, we provide a comprehensive analysis of skew constacyclic codes of length $3p^s$ over $R_k$. Finally, we examine skew cyclic and skew negacyclic codes of length $6p^s$ over $R_k$ using the factorization of $x^{6p^s} - 1$ and $x^{6p^s} + 1$, respectively; with a complete case-by-case analysis. Examples demonstrating codes with optimal parameters are also included.
arXiv:2507.00275v2 Announce Type: replace Abstract: Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection and action-evaluation when computing bootstrap targets. Double DQN adapts target bootstrap decoupling to deep reinforcement learning (RL), but explicitly trains only a single action-value function and does not fully decouple its estimators. Consequently, the two estimators remain correlated, and overestimation persists. In this paper, we introduce Deep Double Q-learning (DDQL), a deep RL algorithm that explicitly trains two Q-functions through Double Q-learning. DDQL stabilizes training through a combination of techniques, including lower replay ratios, longer target network update intervals, and shared layers. Across 57 Atari 2600 games, DDQL improves aggregate performance over Double DQN, outperforming it on 47 games while further reducing overestimation. In addition, we study key design choices when adapting Double Q-learning to deep RL, including the network architecture, replay ratio, and minibatch sampling strategies.
arXiv:2602.16274v2 Announce Type: replace Abstract: We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature and show that its regret depends critically on the suboptimality gap of the MDP: for sufficiently large gaps, the regret is sublinear, while for small gaps it deteriorates and can approach linear growth. To address this limitation, we study a Smoothed $\epsilon_n$-Greedy exploration scheme that combines $\epsilon_n$-greedy and Boltzmann exploration, for which we prove a gap-robust regret bound of near-$\tilde{O}(N^{9/10})$. We also obtain sample complexity guarantees, with both regret and sample complexity bounds holding with high probability. To analyze these algorithms, we develop a high-probability concentration bound for contractive Markovian stochastic approximation with iterate- and time-dependent transition dynamics. This bound may be of independent interest as the contraction factor in our framework is allowed to converge to one asymptotically.
arXiv:2605.16113v1 Announce Type: new Abstract: Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinations, stereotypes, and socially biased content. In particular, LLMs are prone to prejudiced responses involving race, gender, and age, which are collectively referred to as social biases. Prior studies have used fine-tuning and prompt engineering to mitigate such biases in LLMs, but these methods require additional training resources or domain knowledge to design the framework. Moreover, they may degrade the original capabilities of LLMs and often overlook the need for dynamic debiasing contexts for fairer inference. In this paper, we propose DebiasRAG, a novel tuning-free and dynamic query-specific debiasing framework based on retrieval-augmented generation (RAG). DebiasRAG improves fairness while preserving the intrinsic properties of LLMs, such as representation ability. DebiasRAG consists of three stages: (1) query-specific debiasing candidate generation; (2) context candidate pool construction; and (3) gradient-updated debiasing-guided context piece reranking. First, DebiasRAG leverages self-diagnosed bias contexts relevant to the query through regular retrieval, where the bias contexts are prepared offline by the DebiasRAG provider. Given the query-specific bias contexts, DebiasRAG reversely produces debiasing contexts, which are provided as additional fairness constraints for LLM outputs. Second, a regular RAG retrieval process produces query-related contexts from the regular RAG document database, such as a chunked Wikipedia dataset.
arXiv:2604.20127v2 Announce Type: replace Abstract: Failures in complex systems often emerge through gradual degradation and the propagation of stress across interacting components rather than through isolated shocks. Democratic systems exhibit similar dynamics, where weakening institutions can trigger cascading deterioration in related institutional structures. Traditional reliability and survival models typically estimate failure risk based on the current system state but do not explicitly capture how degradation propagates through institutional networks over time. This paper introduces a trajectory-aware reliability modeling framework based on Dynamic Causal Neural Autoregression (DCNAR). The framework first estimates a causal interaction structure among institutional indicators and then models their joint temporal evolution to generate forward trajectories of system states. Failure risk is defined as the probability that predicted trajectories cross predefined degradation thresholds within a fixed horizon. Using longitudinal institutional indicators, we compare DCNAR-based trajectory risk models with discrete-time hazard and Cox proportional hazards models. Results show that trajectory-aware modeling consistently outperforms Cox models and improves risk prediction for several propagation-driven institutional failures. These findings highlight the importance of modeling dynamic system interactions for reliability analysis and early detection of systemic degradation.
arXiv:2603.29617v2 Announce Type: replace-cross Abstract: Understanding how the brain processes linguistic constructions is a central challenge in cognitive neuroscience and linguistics. Recent computational studies show that artificial neural language models spontaneously develop differentiated representations of Argument Structure Constructions (ASCs), generating predictions about when and how construction-level information emerges during processing. The present study tests these predictions in human neural activity using electroencephalography (EEG). Ten native English speakers listened to 200 synthetically generated sentences across four construction types (transitive, ditransitive, caused-motion, resultative) while neural responses were recorded. Analyses using time-frequency methods, feature extraction, and machine learning classification revealed construction-specific neural signatures emerging primarily at sentence-final positions, where argument structure becomes fully disambiguated, and most prominently in the alpha band. Pairwise classification showed reliable differentiation, especially between ditransitive and resultative constructions, while other pairs overlapped. Crucially, the temporal emergence and similarity structure of these effects mirror patterns in recurrent and transformer-based language models, where constructional representations arise during integrative processing stages. These findings support the view that linguistic constructions are neurally encoded as distinct form-meaning mappings, in line with Construction Grammar, and suggest convergence between biological and artificial systems on similar representational solutions. More broadly, this convergence is consistent with the idea that learning systems discover stable regions within an underlying representational landscape - recently termed a Platonic representational space - that constrains the emergence of efficient linguistic abstractions.
arXiv:2412.06853v4 Announce Type: replace Abstract: This paper proposes a novel loss function, called 'Tube Loss', for simultaneous estimation of bounds of a Prediction Interval (PI) in the regression setup. The PIs obtained by minimizing the empirical risk based on the Tube Loss are shown to be of better quality than the PIs obtained by the existing methods in the following sense. First, it yields intervals that attain the prespecified confidence level t $\in$ (0,1) asymptotically. A theoretical proof of this fact is given. Secondly, the user is allowed to move the interval up or down by controlling the value of a parameter. This helps the user to choose a PI capturing denser regions of the probability distribution of the response variable inside the interval, and thus, sharpening its width. This is shown to be especially useful when the conditional distribution of the response variable is skewed. Further, the Tube Loss based PI estimation method can trade-off between the coverage and the average width by solving a single optimization problem. It enables further reduction of the average width of PI through re-calibration. Also, unlike a few existing PI estimation methods the gradient descent (GD) method can be used for minimization of empirical risk. Through extensive experiments, we demonstrate the effectiveness of Tube Loss-based PI estimation in both kernel machines and neural networks. Additionally, we show that Tube Loss-based deep probabilistic forecasting models achieve superior performance compared to existing probabilistic forecasting techniques across several benchmark and wind datasets. Finally, we empirically validate the advantages of the Tube loss approach within the conformal prediction framework. Codes are available at https://github.com/ltpritamanand/Tube$\_$loss.
arXiv:2506.23552v2 Announce Type: replace Abstract: The intrinsic link between facial motion and speech is often overlooked in generative modeling, where talking head synthesis and text-to-speech (TTS) are typically addressed as separate tasks. This paper introduces JAM-Flow, a unified framework to simultaneously synthesize and condition on both facial motion and speech. Our approach leverages flow matching and a novel Multi-Modal Diffusion Transformer (MM-DiT) architecture, integrating specialized Motion-DiT and Audio-DiT modules. These are coupled via selective joint attention layers and incorporate key architectural choices, such as temporally aligned positional embeddings and localized joint attention masking, to enable effective cross-modal interaction while preserving modality-specific strengths. Trained with an inpainting-style objective, JAM-Flow supports a wide array of conditioning inputs-including text, reference audio, and reference motion-facilitating tasks such as synchronized talking head generation from text, audio-driven animation, and much more, within a single, coherent model. JAM-Flow significantly advances multi-modal generative modeling by providing a practical solution for holistic audio-visual synthesis. project page: https://joonghyuk.com/jamflow-web
arXiv:2602.08141v2 Announce Type: replace Abstract: Two parameters scale factor leading to bouncing cosmology is considered. We show that at some model parameters we obtain the deceleration parameter $q_0\approx -0.535$ at the current epoch which is in agreement with the Planck data. The equation for the transition point when the universe expands from acceleration to deceleration phases is obtained. We find the equation for the function $F(T)$ within the teleparallel gravity with torsion field $T$ which provides bouncing cosmology. For some parameters of the model the function $F(T)$ was computed. At the same time, in the framework of entropic cosmology, the associated entropy was obtained for particular model parameters. The equation of state for dark energy was obtained.
arXiv:2511.22279v3 Announce Type: replace Abstract: Radiation forces and torques enable the manipulation of objects with acoustic and electromagnetic waves. Yet, harnessing them in complex scattering media remains a formidable challenge, especially when multiple objects must be controlled under competing objectives. Here, we demonstrate that sound or light can be shaped to tailor momentum transfer to multiple objects simultaneously in a complex scattering medium. For a single object, our theory yields the maximal achievable force or torque; for multiple objects, it produces Pareto-optimal actuation and exact bounds on the simultaneous realization of incompatible objectives. This opens new applications for wave tweezers, enabling selective and precise manipulation of objects within complex media, ranging from the handling of cells, organoids, or microrobots, to targeted drug delivery in biological media.
arXiv:2605.15805v1 Announce Type: cross Abstract: In typical single-molecule force spectroscopy experiments the mechanical unfolding of molecular complexes or biomolecules is studied applying a force ramp to one end of the system while the other end is kept fixed in space. The computational counterpart of this type of experiments can routinely be performed using molecular dynamics simulations with atomistic resolution. However, due to the large difference in time scales often coarse graining procedures are applied in the simulations. Most of the applied techniques do not allow to follow the atomistic details of the relevant conformational transitions due to the structural simplifications used to speed up the simulations. Here, we apply an earlier developed dynamic coarse graining technique based on Markov state modeling to a model peptidic system that does not unfold in a simple two-state manner. Using the donor-acceptor distances of the helical hydrogen bonds as collective variables and performing a dimension reduction technique allows us to construct a Markov model of the unfolding process that correctly represents the microscopic behavior of the system. The chosen example shows that the method can be used to mimick the mechanical unfolding process of systems for which the end-to-end distance does not provide a sufficient order parameter and that do not unfold in a simple cooperative manner.
arXiv:2311.14344v3 Announce Type: replace-cross Abstract: This work presents a tensor-network formulation of the Traveling Salesman Problem (TSP) and several of its variants. The approach represents candidate tours with tensor-network layers, weights them by Boltzmann factors, and enforces constraints through explicit counting filters. This formalism also yields an explicit tensor-network marginal formula whose zero-temperature, exact-arithmetic limit identifies an optimal feasible tour through a sequential marginal rule. At finite $\tau$ and finite precision, the implemented extraction is a heuristic whose behavior depends on numerical contrast, calibration, and near-degeneracies. We adapt the construction to several generalizations of the TSP and apply it to the Job Reassignment Problem, as a representative industrial integration. The experiments are deliberately small and illustrative; they contextualize the method against exact and heuristic references but do not establish general computational superiority over specialized classical solvers.
arXiv:2512.15693v2 Announce Type: replace Abstract: The misuse of AI-driven video generation technologies has raised serious social concerns, highlighting the urgent need for reliable AI-generated video detectors. However, most existing methods are limited to binary classification and lack the necessary explanations for human interpretation. In this paper, we present Skyra, a specialized multimodal large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos and leverages them as grounded evidence for both detection and explanation. To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video artifact dataset with fine-grained human annotations. We then develop a two-stage training strategy that systematically enhances our model's spatio-temporal artifact perception, explanation capability, and detection accuracy. To comprehensively evaluate Skyra, we introduce ViF-Bench, a benchmark comprising 3K high-quality samples generated by over ten state-of-the-art video generators. Extensive experiments demonstrate that Skyra surpasses existing methods across multiple benchmarks, while our evaluation yields valuable insights for advancing explainable AI-generated video detection.
arXiv:2602.22918v3 Announce Type: replace Abstract: Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language processing stream? We investigate the OCR routing mechanism across three architecture families (Qwen3-VL, Phi-4, InternVL3.5) using causal interventions. By computing activation differences between original images and text-inpainted versions, we identify architecture-specific OCR bottlenecks whose dominant location depends on the vision-language integration strategy: DeepStack models (Qwen) show peak sensitivity at mid-depth (about 50%) for scene text, while single-stage projection models (Phi-4, InternVL) peak at early layers (6-25%), though the exact layer of maximum effect varies across datasets. The OCR signal is remarkably low-dimensional: PC1 captures up to 72.9% of variance. Crucially, principal component analysis (PCA) directions learned on one dataset transfer to others, demonstrating shared text-processing pathways. Surprisingly, in models with modular OCR circuits (notably Qwen3-VL-4B), OCR removal can improve counting performance (up to +6.9 percentage points), suggesting OCR interferes with other visual processing in sufficiently modular architectures.
arXiv:2602.03922v3 Announce Type: replace Abstract: Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context tasks but has expensive quadratic compute and linear memory costs, while linear attention and SSMs use only linear compute and constant memory but struggle with long context processing. In this paper, we develop a sequence mixing layer that aims to find a better compromise between memory-compute costs and long-context processing, which we call online vector-quantized (OVQ) attention. OVQ-attention requires linear compute costs and constant memory, but, unlike linear attention and SSMs, it uses a sparse memory update that allows it to greatly increase the size of its memory state and, consequently, memory capacity. We develop a theoretical basis for OVQ-attention based on Gaussian mixture regression, and we test it on a variety of synthetic long context tasks and on long context language modeling. OVQ-attention shows significant improvements over linear attention baselines and the original VQ-attention, on which OVQ-attention was inspired. It demonstrates competitive, and sometimes identical, performance to strong self-attention baselines up 64k sequence length, despite using a small fraction of the memory of full self-attention.
arXiv:2605.15715v1 Announce Type: new Abstract: Blockchain systems such as Solana or Monad employ tree- or star-shaped broadcast topologies in which a single source node disseminates message shards to a set of target peers within a strictly bounded time window. In these architectures, shard propagation must complete before the next consensus step, making timely delivery to a large fraction of the validator set essential. A fundamental limitation of such designs is that the outbound bandwidth of the source node constitutes the primary system bottleneck. In this paper, we introduce peer Turbo, a technique that allows target nodes to exchange shards using Random Linear Network Coding (RLNC), thereby assisting each other in completing decoding without requiring explicit shard state coordination. We use a tractable fluid approximation of the degree of freedom distribution of peer-Turbo-enabled systems show that this approach reduces source bandwidth required for a set service quality by up to one order of magnitude, or equivalently reduces propagation latency by one order of magnitude under fixed bandwidth constraints.
arXiv:2601.07820v2 Announce Type: replace Abstract: In human conversation, both interlocutors play an active role in maintaining mutual understanding. When listeners are uncertain about what speakers mean, for example, they can request clarification. It is an open question for language models whether they can assume a similar listener role, recognizing and expressing their own uncertainty through clarification. We argue that reference games are a suitable testbed to approach this question as they are controlled, self-contained, and make clarification needs explicit and measurable. To test this, we evaluate three vision-language models comparing a baseline reference resolution task to an experiment where the models are instructed to request clarification when uncertain. The results suggest that even in such simple tasks, models often struggle to recognize internal uncertainty and translate it into adequate clarification behavior. This demonstrates the value of reference games as testbeds for interaction qualities of (vision and) language models.
arXiv:2605.15710v1 Announce Type: new Abstract: Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use evidence distributed across independently originated sources. We argue that source-distributed memory composition is an important and under-examined bottleneck in multimodal agent memory, especially when relevant evidence is fragmented across heterogeneous artifacts such as conversations, profiles, screenshots, tables, images, and documents. To address this gap, we introduce Source-distributed Multimodal Memory Benchmark(SMMBench), which measures whether agents can retrieve, align, and compose multimodal evidence scattered across multiple sources rather than reason within a single curated context. SMMBench evaluates four core capabilities: (1) cross-source multimodal reasoning; (2) conflict resolution; (3) preference reasoning; (4) memory-grounded action prediction. The benchmark contains 1877 samples grounded in 264 sources. Experiments on representative memory-style and retrieval-based baselines show that current systems still struggle on these capabilities, positioning source-distributed multimodal memory as an important and still under-evaluated challenge for multimodal agents. Our data are available at https://huggingface.co/datasets/HuacanChai/SMMBench.
arXiv:2605.15393v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed to perform tasks with minimal human oversight, it is crucial that these models operate robustly. In particular, a model that can solve a given problem should not fail simply because certain entities$\unicode{x2013}$such as names, numbers, or other contextual details$\unicode{x2013}$have changed while the underlying problem logic remains the same. Prior work suggests that current LLMs still struggle with this form of robustness: they often succeed on some variations of a problem but fail on others. However, existing evaluations often lack a systematic way to identify which logic-preserving variations are most likely to induce failure. Instead, they typically test a random subset of allowable variations, which can overstate robustness. To address this gap, we introduce logic-preserving difficulty scaling (LPDS), a framework that (i) quantifies the difficulty of a problem variation and (ii) systematically searches the space of allowable variations to find those that maximize difficulty and expose failures. We show that as difficulty increases, performance declines and errors in the models' reasoning chains become more pronounced. We further demonstrate that LPDS efficiently finds difficult problem variations for a model, resulting in performance drops up to 5 times larger compared to random sampling. Finally, we show that fine-tuning on more difficult variations leads to more consistent robustness gains than training on easier ones.
arXiv:2605.15731v1 Announce Type: new Abstract: This paper presents the real-world implementation and field validation of a user-aware bidirectional electric vehicle (EV) charging system developed within the Mobilities for EU and DymoBat projects in Dresden. Building on earlier simulation frameworks, the system enables transition from conceptual models to operational deployment in urban environments. To support grid flexibility and sustainable mobility, the solution combines real-time vehicle and user data with a centralized optimization platform to enable dynamic charging and discharging decisions. The architecture integrates a wireless On-Board Diagnostic II (OBD-II) interface and an open middleware node connected via a 5G campus network, allowing early access to vehicle state-of-charge before plug-in. A tablet-based interface captures user preferences such as departure time and energy demand, which are incorporated into the optimization together with grid conditions. A key contribution is a multi-level communication architecture linking the EV, charging station, user interface, and grid control center using the Open Charge Point Protocol (OCPP). The system integrates software, embedded hardware, and network communication for real-time charging management. Field deployment at Ostra Sport Park in Dresden demonstrates feasibility, improved load balancing, and robust vehicle-to-grid operation. The results show that early data acquisition and predictive control can enhance system efficiency. This work provides a practical benchmark for positive energy districts and future urban e-mobility systems.
arXiv:2605.15384v1 Announce Type: new Abstract: Memory plays a central role in enabling large language models (LLMs) to operate over sequential tasks by accumulating and reusing experience over time. However, existing evaluations of LLM memory mostly rely on aggregate metrics such as final hold-out accuracy or cumulative online performance, which can obscure critical failure modes such as forgetting and negative transfer. In this paper, we introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving LLM memory. Drawing inspiration from continual learning, it targets a test-time setting in which memory is external, prompt-mediated, and updated without modifying model parameters. Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference. Specifically, it measures online utility, hold-out generalization, backward transfer, and forgetting, providing a finer-grained view of memory quality. Through extensive experiments across diverse tasks and memory methods, we show that higher final or cumulative accuracy does not necessarily imply better memory quality: many methods exhibit strong performance gains while suffering from substantial forgetting or negative transfer. Moreover, different memory designs exhibit distinct trade-offs between adaptability and stability that remain invisible under standard evaluation metrics.
arXiv:2605.15380v1 Announce Type: new Abstract: Recent advances in generative AI have shown their potential to be leveraged for legal education. Yet, work on the development and deployment of such systems for legal education in the Global South is limited. In this work, we developed Eskwai for Students, a generative AI assistant to help law students with their legal education. Eskwai for Students is a retrieval augmented generation (RAG) system that provides answers to a wide range of legal questions for law students grounded in a curated database of over 12K case laws and 1.4K legislation in Ghana. We deployed Eskwai for Students in a longitudinal study of 30 months (2.5 years) used by 3.1K law students in Ghana who made 32K queries. We evaluated the helpfulness of our AI, and provided insight into the kinds of queries law students submit to this generative AI tool, which raises some ethical concerns. This work contributes to an understanding of how law students in the Global South are using generative AI for their studies and the ways it could be leveraged responsibly to advance legal education.