Academic Intelligence · Curated Daily

Explore the Frontier of Global Academia

AcademicHub aggregates real-time literature from top journals and preprint platforms. Build your personal research radar and let large language models compile cross-disciplinary analysis briefings automatically.

01.
arXiv (quant-ph) 2026-06-24

Electrical-Circuit Simulation of the Uhlmann Phase

arXiv:2606.24559v1 Announce Type: new Abstract: The Uhlmann phase extends the concept of geometric phases to mixed quantum states through a parallel-transport condition on purification amplitudes, but its experimental realization has so far required sophisticated quantum platforms with carefully engineered auxiliary degrees of freedom. In this work, we reformulate the Uhlmann parallel-transport condition as a linear matrix differential equation and vectorize it to obtain an effective dynamical generator. This generator can be directly mapped onto the admittance matrix of a classical RC circuit, thereby translating the Uhlmann dynamics into the evolution of circuit node voltages. We illustrate the mapping using the equatorial-loop model and, via a rotating-frame transformation followed by a real decomposition, derive a time-independent, real-valued dynamical system suitable for analog implementation. LTspice simulations of the resulting active RC network faithfully reproduce the Uhlmann geometric phase and its topological transition at the critical purity, demonstrating that classical electrical circuits offer a simple and accessible platform for probing mixed-state geometric phases.

02.
arXiv (CS.AI) 2026-06-16

Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call

arXiv:2606.15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are costly to collect and constrained by privacy and learner engagement. Learner simulators play a critical role in simulating scalable learner behavior without the need for continuous involvement of real learners. However, existing methods are predominantly individual-centric, pairing a simulator with each learner to iteratively infer latent knowledge states from dense interaction histories, which is both data- and computation-intensive, and fragile in cold-start scenarios. We propose a cohort-aware roll-call simulation paradigm that first constructs cohort-level proficiency priors and refines individual learner states through a small number of targeted diagnostic queries. Based on this paradigm, we introduce Edu-Theater, an LLM-powered agent system that performs cohort-aware learner simulation via a teacher agent and retrospective roll-call probing over learner logs. Edu-Theater enables scalable future behavior simulation without the need for dense per-learner histories. Experiments on two real-world datasets demonstrate that Edu-Theater achieves higher simulation accuracy with significantly fewer LLM calls, producing synthetic data that enhances downstream applications such as adaptive testing.

03.
arXiv (CS.CV) 2026-06-16

SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation

In this paper, we propose SGFormer++, a novel Semantic Graph Transformer for 3D scene graph generation (SGG), which aims to parse point cloud scenes into semantic structural graphs, where nodes denote detected object instances and edges encode their pairwise relationships, with the core challenge lying in modeling complex global scene structure. While existing graph convolutional network (GCN)-based methods suffer from over-smoothing and limited receptive fields, SGFormer++ leverages Transformer layers as its backbone to enable global message passing. Specifically, we introduce two key components tailored for 3D SGG: (1) a Graph Embedding Layer++ that efficiently integrates edge-aware global context with linear computational complexity, and (2) a Semantic Injection Layer++ that enriches visual features with linguistic priors from large language models (LLMs) and vision-language models (VLMs), boosting semantic representation without introducing extra trainable parameters. To further address the practical challenge of incremental SGG (I-SGG), where new relationship categories arrive sequentially, we equip SGFormer++ with a novel Spatial-guided Feature Adapter, which calibrates predicate features using subject-object spatial geometry to counter scale variation, and a Cascaded Binary Prediction Head that mitigates catastrophic forgetting via task-incremental classifier expansion and logit distillation. Extensive experiments on the 3DSSG benchmark demonstrate that SGFormer++ achieves state-of-the-art performance in both standard and incremental settings: it yields a significant 4.49% absolute improvement in Predicate A@1 under the incremental setting. Code and data are available at: https://github.com/Andy20178/SGFormer.

04.
arXiv (CS.AI) 2026-06-12

GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models

arXiv:2606.12821v1 Announce Type: new Abstract: Environmental scientists spend disproportionate effort on data wrangling rather than analysis, and AI agents that automate geospatial workflows remain unvalidated: no benchmark evaluates agents operating through structured tool calling against real APIs. We introduce the GeoNatureAgent Benchmark, the first benchmark for environmental analysis agents that operate via structured tool calls to a production-style geospatial API. It comprises 93 tasks across 18 categories, covering municipality analysis, multi-turn conversation, spatial reasoning, cross-indicator synthesis, error handling and recovery, ranking, comparison, multilingual understanding, habitat analysis, and task rejection. Tasks are evaluated against an open, self-hostable API serving three environmental indicators across Spain and Portugal via sixteen tools. We evaluate seven LLMs (Claude Sonnet 4, DeepSeek V3.2, GLM-5, Gemini 2.5 Pro, Qwen3-235B, GPT-OSS-120B, Llama 4 Scout) under three temperature-1.0 seeds, reporting capability and per-case cost as orthogonal axes. We find: (1) Claude Sonnet 4 leads at 60.8% +/- 0.8%, followed by DeepSeek V3.2 at 56.3% +/- 3.1%, with no other model above 51%; (2) the cost-accuracy Pareto frontier is occupied mostly by open-weight models, with DeepSeek V3.2 offering 93% of Claude's capability at 11x lower cost ($0.011/case); (3) comparison tasks remain universally unsolved (0% on close-value comparisons), exposing systematic reasoning limits; and (4) structured tool calling against a real API is more discriminative than general-purpose GIS benchmarks, with accuracies 25-35 points lower. We further show extensibility by integrating BigEarthNet V2 land cover for Portugal alongside Spanish CO2 and erosion indicators. The benchmark, harness, and self-hostable API are publicly available.

05.
arXiv (CS.AI) 2026-06-12

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

arXiv:2606.13316v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods often encourage unnecessarily long reasoning rollouts, which can degrade reasoning coherence and exhaust the available context budget. Existing approaches to long-context organization often depend on external mechanisms to organize rollouts, rather than enabling the model to manage its own reasoning trajectory. To address this limitation, we propose ReSum, a novel RLVR framework that enables LLMs to compress and organize their reasoning trajectories through self-summarization. Our pilot studies show that self-summarization stabilizes generation by lowering token-level entropy, and that introducing a ``summarization'' phrase can substantially mitigate errors propagated from an incorrect rollout prefix. Motivated by these findings, ReSum adopts a summarization-aware adaptive rollout mechanism that contrastively evaluates whether self-summarization benefits the ongoing reasoning process. Specifically, when the model spontaneously triggers self-summarization, ReSum masks the summarization phrase to create a contrastive branch; for non-summarization positions, it instead randomly injects the phrase to create a matched branch. We further design a summarization-aware advantage to enable finer-grained comparison between contrastive rollout trajectories. Extensive experiments show that ReSum improves performance at an average of 4\% while reducing rollout length by 18.6\%.

06.
arXiv (CS.LG) 2026-06-24

Extended pseudo-spectral physics-informed neural networks for phase-field models

arXiv:2606.24660v1 Announce Type: cross Abstract: Phase-field models play a central role in the continuum description of phase separation, in which the bulk free-energy density and the interfacial thickness parameter determine pattern formation and microstructural evolution. In practice, these constitutive quantities are rarely known a priori and must be inferred from limited dynamical observations. In this work, an extended pseudo-spectral physics-informed neural network (ESPINN) framework is developed for the inverse identification of phase-field models from transient snapshot data. It enables the simultaneous recovery of both the bulk chemical potential and unknown gradient coefficients. Numerical experiments on the one-dimensional Cahn-Hilliard equation demonstrate accurate and statistically stable reconstruction in the noiseless regime, with substantial constitutive information recoverable from even a single snapshot pair. In the presence of noise, reconstruction accuracy degrades gracefully, and increasing the number of snapshots improves robustness by reducing variance across runs. These results establish ESPINN as a data-efficient and physically consistent approach for learning free-energy structure in continuum models of phase separation.

07.
arXiv (CS.AI) 2026-06-16

Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations

arXiv:2606.14817v1 Announce Type: cross Abstract: This work presents the design, implementation, and evaluation of a system for generating personalized reading content using Large Language Models (LLMs) combined with Retrieval-Augmented Generation (RAG). The proposed architecture consists of four modules: Input, RAG, Generation, and Judging and enables users to specify both a question and a target reading content complexity. RAG is employed to retrieve relevant information from the Internet, enriching and grounding the content produced by three modern LLMs: Meta LLaMA 4 Scout, LLaMA 3.1 8B Instant, and Google Gemma2 9B. Reading materials are generated using three prompting strategies (Chain-of-Thought, zero-shot, and few-shot), and the LLM-as-a-Judge module automatically evaluates answer quality and alignment with the desired readability level. Experimental results show that RAG consistently improves system performance across all models and prompting techniques, increasing relevance and particularly groundedness by up to 26-35 percentage points. Overall, the findings demonstrate that the RAG-augmented architecture effectively produces reading content tailored to user queries and desired textual complexity.

08.
PLOS Computational Biology 2026-06-16

Evolution and the ultimatum game: An agent-based model with interbirth intervals and population structure

by Jeffrey C. Schank, Matt L. Miller The ultimatum game (UG) is widely used to study mutually beneficial exchanges, fairness, and prosocial behavior across different societies. However, human behavior in UG experiments does not align with the game-theoretical prediction that proposers should offer the least positive amount and responders should accept such offers. Instead, proposers make generous offers that are greater than the minimum responders are willing to accept, resulting in generous offers with wide offer-acceptance gaps. Numerous evolutionary models of the UG have been created and studied to explain human behavior, particularly generous offers made in UG experiments. These models have recently faced criticism for lacking biological realism and not adequately explaining the data. Here, we present an agent-based model inspired by our hunter-gatherer ancestors and with a biologically more realistic selection process. We assume that (1) agents exist in group-structured and group-clustered populations, where reproduction (2) depends on resource accumulation, but (3) is limited by interbirth intervals. We ran simulations to assess whether this biologically more realistic model evolves patterns of behavior consistent with patterns in the data from meta-analyses of human behavior in the UG. For the proposed model, we show that generous offers robustly evolve, as well as the difficult-to-explain offer-acceptance gaps, only in group-structured populations with interbirth intervals. We demonstrate that these results are robust and may help explain variation in data across societies. We discuss how interbirth intervals interact with group structure to modulate offer and rejection costs, favoring the evolution of generous offers, offer-acceptance gaps, and other patterns in the data on human behavior in the UG. We also discuss why weak selection and/or high mutation rate models cannot explain all the patterns in UG experimental data. We discuss biological realism and conclude that group structure and interbirth intervals may be essential for explaining prosocial behavior across societies.

09.
arXiv (CS.AI) 2026-06-12

Democracy in the Era of Artificial Intelligence

arXiv:2606.13026v1 Announce Type: cross Abstract: Interfacing Artificial Intelligence (AI) with democracy is one of the most profound challenges of our times. On the one hand, AI comes with opportunities to overcome long-standing challenges in democracy, such as low participation in deliberative and voting processes with poor representation of people. On the other hand, new risks arise from AI algorithms that are privacy-intrusive, biased, manipulative, spread misinformation and influence election results. Moving beyond the over-simplistic question of whether AI is good or bad for democracy, the Handbook on Democracy in the Era of Artificial Intelligence asks instead: how to upgrade democracies and the principles they are built on, using AI? How to engage with AI and on what terms? Which new values and design principles are required to build democratic resilience? In 34 chapters by 59 authors across the world from different disciplines, we explore how AI can empower collective intelligence for democracy (Part 1) and what is the future of deliberative democracy using large language models and social media (Part 2). We also illustrate the role of AI for building resilient self-governance systems (Part 3) and the challenges of transforming democracy in the age of AI (Part 4). We conclude with broader perspectives (Part 5) that re-imagine the interplay of democracy and AI.

10.
medRxiv (Medicine) 2026-06-17

The interaction between chronic hepatitis B (CHB) and Metabolic dysfunction-associated steatotic liver disease (MASLD) in a diverse central London population

Introduction: The overlap between chronic hepatitis B (CHB) and metabolic dysfunction-associated steatotic liver disease (MASLD) is an emerging global health challenge. We investigated the impact of MASLD and metabolic comorbidity in a diverse London viral hepatitis clinic. Methods: This retrospective cross-sectional study (May 2018-Feb 2024) included adults with CHB having controlled attenuation parameter (CAP) measurements. MASLD was defined as CAP >264 dB/m plus [≥]1 cardiometabolic factor (CMF). We used univariable and multivariable models to examine MASLD's relationship with liver stiffness and hepatitis B viral load (HBV VL). Results: Among 323 individuals (67% male, median age 36), most were from Black (35%) or non-white British/Irish (29%) backgrounds. Overall, 64% had [≥]1 CMF, and 20% had MASLD. The CHB/MASLD group was significantly older (median 43 vs 35 years, p

11.
bioRxiv (Bioinfo) 2026-06-23

FateLimit quantifies the prediction horizon of cell fate

Single-cell technologies have enabled increasingly detailed reconstruction of developmental trajectories, yet a fundamental question remains unresolved: when does future cellular identity become predictable from cells current molecular state? Existing approaches infer lineage relationships, transition probabilities or future transcriptional dynamics, but do not directly quantify the emergence of fate predictability during cellular state transitions. Here we present FateLimit, an information-theoretic framework for measuring the temporal dynamics of cell-fate predictability from single-cell omics data. FateLimit combines probabilistic fate assignment, fate entropy and mutual information to quantify how information about future cellular outcomes is encoded in present molecular states. We introduce two quantitative descriptors: the Fate Information Half-Life (FIHL), which measures the characteristic timescale of fate-information dynamics, and the Prediction Horizon (PH), defined as the earliest developmental stage at which observed fate predictability exceeds the 95th percentile of a permutation-derived null distribution. We applied FateLimit across developmental, lineage-tracing and reprogramming systems, including pancreatic endocrinogenesis, CellTag reprogramming, human hematopoiesis and zebrafish embryogenesis. Across all datasets, FateLimit identified significant fate information and reproducible prediction horizons that were robust to cell-state representation, lineage structure and biological context. Comparative analysis revealed that prediction horizons differ substantially among cellular lineages, indicating that distinct developmental programs acquire predictive information at different rates. FateLimit establishes a general framework for quantifying the predictability of future cellular identity from present molecular states. By transforming developmental trajectories into predictability landscapes, FateLimit enables systematic comparison of commitment dynamics across biological systems and establishes prediction horizons as a quantitative measure of cell-fate determination.

12.
arXiv (CS.AI) 2026-06-11

Agentic Software: How AI Agents Are Restructuring the Software Paradigm

Authors:

arXiv:2606.05608v2 Announce Type: replace-cross Abstract: For over half a century, software engineering has operated on a foundational premise: human engineers decompose problems, encode decision logic into static code, and manually adapt that code as requirements evolve. This paper argues that the emergence of AI agents – systems where large language models serve as the primary reasoning engine, dynamically generating and discarding code as an instrumental resource – constitutes a fundamental restructuring of what software is, not an incremental tool improvement. We formalize the distinction between traditional deterministic software and agentic software: in the former, code is the carrier of pre-written decision logic; in the latter, the agent itself is the software, and its decision logic is generated at runtime. We trace the historical arc from licensed software to SaaS to Agent-as-a-Service (AaaS), showing that each shift transferred additional complexity away from end-users – with the agentic shift transferring not just operational complexity but decision-making complexity itself. We introduce Agentic Engineering as an expansion of the software engineering discipline into a new paradigm, distinct in its core object of study (agent systems rather than static source code), its control model (LLM-driven rather than human-predefined), and its human role (intent architect rather than code author). Through analysis of recent benchmark evidence including SWE-bench Verified, EvoClaw, and LangChain's multi-agent coordination studies, we demonstrate both the transformative potential of the agentic paradigm and its current limitations. We conclude with a four-stage roadmap toward self-evolving agent ecosystems and concrete recommendations for practitioners navigating this transition.

13.
arXiv (CS.LG) 2026-06-18

Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment

arXiv:2606.18703v1 Announce Type: new Abstract: Pretrained biological language models expose per-token probability distributions through masked-token prediction, providing the likelihood interface central to sequence design, variant scoring, and mechanistic interpretation. Yet these distributions are learned from broad unlabeled corpora and are not naturally conditioned on task-specific biological contexts such as interaction partners, cellular environments, or therapeutic interventions. Existing contextual matching methods often distort this interface through pooled embeddings, contrastive latent spaces, or task-specific prediction heads. We introduce LOGICA (Logit-space Contrastive Alignment), a framework for context-conditioned prediction that performs contrastive learning directly in output-logit space. Using gated cross-modal adapters compatible with each model's native token head, LOGICA preserves the pretrained likelihood interface and converts contextualized token log-likelihoods into matching scores. Alignment is defined through context-sensitive token probabilities rather than proximity in a shared embedding space, enabling learning from sparse paired data across models with distinct vocabularies, without a shared tokenizer or decoder. LOGICA is particularly effective for mutation-local variant ranking, where comparisons reduce to context-conditioned likelihoods of mutant tokens at perturbed sites. Across protein–ligand binding, TCR–peptide activity, and drug-conditioned resistance prediction, LOGICA improves over prior state-of-the-art methods, including matched latent-contrastive and conditional MLM baselines, while retaining a token-level interface for interpretation and generation. On held-out-gene single-mutation drug-resistance prediction, LOGICA improves AUC from near-random latent-space baselines of $\sim$0.55 to $\sim$0.65.

14.
Nature (Science) 2026-06-10

A first-in-class pulsatile FXR agonist for bile-acid-related liver diseases

Authors:

Nuclear receptors are central regulators of metabolism1, yet therapeutic strategies that enforce continuous receptor activation frequently lead to reduced efficacy and unacceptable toxicity. Here we report a first-principles drug design strategy that aligns pharmacokinetics with physiological signalling cycles. We developed linafexor, a potent non-bile-acid agonist of the farnesoid X receptor (FXR)2; it is engineered for rapid systemic clearance, which enables pulsatile receptor activation that mirrors endogenous bile acid dynamics3–5. Linafexor has robust efficacy across multiple preclinical models of metabolic dysfunction-associated steatohepatitis6, liver fibrosis7, primary biliary cholangitis and primary sclerosing cholangitis8,9. Transcriptomic analyses reveal that, unlike long-acting FXR agonists10,11, linafexor preserves cyclic FXR signalling, avoids receptor downregulation and prevents broad transcriptional dysregulation. Direct manipulation of delivery patterns demonstrates that sustained FXR activation—independent of compound identity—induces severe toxicity, establishing activation duration as a determinant of therapeutic index. In phase 1 clinical studies (ClinicalTrials.gov; NCT05082779), linafexor administered once daily produces transient FXR pathway engagement, marked by (1) induction of FGF1912–14, a key endocrine mediator of bile acid feedback regulation; and (2) suppression of C415, an intermediate reflecting hepatic bile acid synthesis, with no treatment-related adverse events. Together, these findings identify pulsatile FXR activation as a mechanistically grounded and clinically translatable strategy, and establish linafexor as a first-in-class therapeutic for bile acid–related liver diseases. Linafexor is a rapidly cleared FXR agonist designed to mimic natural bile acid signalling, achieving transient receptor activation with strong efficacy and reduced toxicity in preclinical and early clinical studies.

15.
arXiv (CS.CL) 2026-06-15

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capabilities of Speech LLMs to their text-based counterparts. X-OPD enables the Speech LLM to explore its own distribution via on-policy rollouts, where a text-based teacher model evaluates these trajectories and provides token-level feedback, effectively distilling teacher's capabilities into student's multi-modal representations. Extensive experiments across multiple benchmarks demonstrate that X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.

16.
arXiv (CS.LG) 2026-06-18

Fair Online Resource Allocation

arXiv:2606.18679v1 Announce Type: cross Abstract: We study the problem of fair online resource allocation, motivated by applications such as refugee resettlement and airline scheduling, where agents arrive sequentially and must be assigned to facilities with limited capacities. We introduce a model that maximizes the overall welfare subject to resource constraints and a Lipschitz fairness requirement, which ensures that similar agents arriving in the same batch receive similar expected outcomes. We first analyze the offline problem, proving that the value of the optimal fair allocation is at least an $\Omega(1/\gamma)$ fraction of the optimal unfair allocation, where $\gamma$ is the fairness coefficient, thereby bounding the price of fairness. For the online setting, we propose an algorithm based on dual mirror descent that enforces fairness constraints within batches while estimating optimal dual variables. We prove that this algorithm achieves sublinear regret relative to the optimal offline fluid benchmark. Finally, we validate our theoretical results using real-world data from the Refugee Economies Programme, demonstrating the algorithm's performance and examining the trade-offs between welfare maximization and fairness enforcement.

17.
arXiv (math.PR) 2026-06-16

Sharp One-Dimensional Sub-Gaussian Comparison in Convex Order

Authors:

arXiv:2604.26819v2 Announce Type: replace Abstract: We prove that any random variable $X$ whose moment generating function is point-wise upper bounded by that of $ G \sim \mathcal{N}(0,1) $ must be dominated by $ G/\mathbb{E}[|G|] $ in convex order, meaning $ \mathbb{E}[f(X)] \le \mathbb{E}[f(G/\mathbb{E}[|G|])] $ for all convex $f$. This is sharp as witnessed by $ X \sim \mathrm{Unif}(\{-1,1\}) $ and $ f(x) = |x| $.

18.
arXiv (CS.LG) 2026-06-12

Uncertainty Estimation for Molecular Diffusion Models

arXiv:2606.13451v1 Announce Type: new Abstract: Diffusion models have seen wide adoption for 3D molecular generation, yet they offer no principled signal of when a generated molecule is likely to be of low quality. We propose a post-hoc method for estimating per-sample uncertainty in pretrained molecular diffusion models. Building on a Laplace approximation of the denoising network, we measure the variability of the noise prediction across the generation trajectory. Empirically, we show that the resulting uncertainty score is informative of sample quality, exhibiting a negative correlation with established sample-level quality metrics. We further study how the proposed uncertainty score can be used to filter generated samples, improving model performance via test-time scaling.

19.
arXiv (CS.CL) 2026-06-12

Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings

Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich contextualized representations. However, long-document KPE remains challenging because salient keyphrase evidence may be scattered across distant document sections that cannot be jointly captured within the limited context window of most PLMs. Although long-context large language models (LLMs) can process broader textual contexts, their computational cost limits their practicality for efficient and high-throughput KPE. To overcome this limitation, we propose an attention expansion mechanism that augments PLM token representations with information from surrounding out-of-context chunks using pre-trained word embeddings. The proposed mechanism expands the effective contextual scope of PLM-based KPE models without requiring full-document attention or expensive LLM-based inference. We evaluate our approach across five PLM backbones, including general-purpose, scientific, task-specific, and long-context encoders, using two training regimes and five benchmark corpora from scientific and news domains. Experimental results demonstrate that attention expansion consistently enhances KPE performance across all evaluation settings, outperforming state-of-the-art models and yielding notable improvements in F1 score. The improvements extend to domain-specific, task-specialized, and native long-context models, showing that the proposed mechanism provides complementary information rather than merely compensating for limited input length. These results establish attention expansion as an efficient and effective strategy for long-document KPE.

20.
arXiv (CS.CL) 2026-06-24

Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

Voice agents face a fundamental tension: the reasoning, retrieval, and tool use that make foundation models capable are iterative and slow, while conversational interaction demands responses on a millisecond timescale. Smaller, real-time models meet the latency bar but cannot match foundation models on complex tasks, leaving current voice agents to trade away either responsiveness or capability. We introduce conversational infill, where a small talker model both immediately generates contextually grounded responses to hide the latency of an external reasoner model and fluently integrates streamed reasoner knowledge into its responses during inference. We curate a 290,571-example synthetic dataset spanning six domains and demonstrate that this task is learnable across seven widely used small language models ranging from 135M to 1.7B parameters. Our system implementation, ConvFill, sustains millisecond-level time-to-first-response while closing the accuracy gap to within 6.3% of the corresponding frontier reasoner performance. In a live user study (n=18) with talker deployments running on an Apple M2 SoC, participants rank ConvFill on par with frontier models overall, prefer it for retrieval-heavy tasks, and rate it significantly more responsive. These results show that conversational infill unlocks a new point on the latency-capability Pareto frontier, offering a practical path toward voice agents that are both responsive and highly capable. Code, models, and datasets are available at https://github.com/vysri/conversational-infill.

21.
arXiv (CS.LG) 2026-06-15

A Composite Activation Function for Learning Stable Binary Representations

arXiv:2605.11558v2 Announce Type: replace Abstract: Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations has attracted significant attention due to their advantages in computational and memory efficiency, as well as interpretability. However, training neural networks with Heaviside activations remains challenging, as their non-differentiability obstructs standard gradient-based optimization. In this paper, we propose Heavy Tailed Activation Function (HTAF), a smooth approximation to the Heaviside function that enables stable training with gradient-based optimization. We construct HTAF as a sigmoid hyperbolic tangent composite function and theoretically show that it maintains a large gradient mass around zero inputs while exhibiting slower gradient decay in the tail regions. We show that Spiking Neural Networks, Binary Neural Networks and Deep Heaviside neural Networks can be trained stably using HTAF with gradient-based optimization. Finally, we introduce Implicit Concept Bottleneck Models (ICBMs), an interpretable image model that leverages HTAF to induce discrete feature representations. Extensive experiments across various architectures and image datasets demonstrate that ICBM enables stable discretization while achieving prediction performance comparable to or better than standard models.

22.
arXiv (CS.LG) 2026-06-24

Aligning Audio Captions with Human Preferences

arXiv:2509.14659v3 Announce Type: replace-cross Abstract: Current audio captioning relies on supervised learning with paired audio-caption data, which is costly to curate and may not reflect human preferences in real-world scenarios. To address this, we propose a preference-aligned audio captioning framework based on Reinforcement Learning from Human Feedback (RLHF). To capture nuanced preferences, we train a Contrastive Language-Audio Pretraining (CLAP) based reward model using human-labeled pairwise preference data. This reward model is integrated into an RL framework to fine-tune any baseline captioning system without ground-truth annotations. Extensive human evaluations across multiple datasets show that our method produces captions preferred over baseline models, particularly when baselines fail to provide correct and natural captions. Furthermore, our framework achieves performance comparable to supervised approaches with ground-truth data, demonstrating effective alignment with human preferences and scalability in real-world use.

23.
arXiv (CS.LG) 2026-06-19

Utility-Aware DRL-Based TXOP Adaptation for NR-U and Wi-Fi Coexistence Networks

arXiv:2605.00457v4 Announce Type: replace-cross Abstract: The coexistence of NR-U and Wi-Fi in the unlicensed spectrum introduces a challenging resource management problem, where heterogeneous channel access mechanisms can lead to unbalanced spectrum utilization and severe Wi-Fi performance degradation. To address this issue, this paper proposes a utility-aware deep reinforcement learning (DRL) framework for adaptive transmission opportunity (TXOP) control in NR-U/Wi-Fi coexistence networks. The coexistence process is formulated as a Markov decision process (MDP), in which the NR-U TXOP duration is treated as a controllable variable for regulating post-access channel occupancy. A deep Q-network (DQN) is then employed to learn adaptive TXOP control policies through online interaction with the coexistence environment. A key feature of the proposed framework is the integration of a configurable reward and criterion design, which enables explicit control of the fairness-efficiency-utility tradeoff. Three operating policies are developed, namely absolute fairness, moderate fairness, and utility-oriented moderate fairness, to characterize different coexistence operating points. Simulation results show that the proposed framework achieves a Jain fairness index above 0.9 under strict fairness control. Compared with the absolute fairness policy, the moderate fairness policy improves aggregate throughput by 68.22%, while the utility-oriented policy achieves a 177.6% improvement under the adopted utility evaluation metric. These results demonstrate that the proposed utility-aware DRL framework provides an effective and flexible solution for adaptive TXOP control and tradeoff management in heterogeneous unlicensed coexistence networks.

24.
arXiv (CS.AI) 2026-06-17

Optimism Stabilizes Thompson Sampling for Adaptive Inference

arXiv:2602.06014v2 Announce Type: replace-cross Abstract: Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are random and coupled with the rewards through the action-selection rule. We study adaptive inference for Thompson sampling with Gaussian randomized indices in $K$-armed stochastic bandits with independent sub-Gaussian reward noises, and identify optimism as a key mechanism for restoring stability, meaning that each arm's pull count concentrates around a deterministic scale. This stability yields asymptotically valid Wald inference despite adaptive sampling. First, we prove that variance-inflated TS is stable for any $K \ge 2$, including the challenging regime where multiple arms are optimal, with asymptotically uniform allocation over optimal arms and sharp logarithmic pull-count asymptotics for suboptimal arms. This resolves the $K$-armed extension question raised by \citet{halder2025stable}, using new winner-map and Lyapunov-drift techniques to control allocation among multiple optimal arms. Second, we analyze an alternative optimistic modification that keeps the Gaussian index variance unchanged but adds an explicit mean bonus to the index center, and establish a similar stability conclusion. In summary, suitably implemented optimism stabilizes Thompson sampling and enables asymptotically valid Wald inference in multi-armed bandits, while incurring only a mild additional regret cost.

25.
arXiv (CS.AI) 2026-06-11

Mind the Perspective: Let's Reason Recursively for Theory of Mind

arXiv:2606.11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Existing prompting-based approaches improve ToM reasoning through observable-event filtering or temporal belief chains, without explicitly modeling nested beliefs. We introduce RecToM, an inference-time framework for ToM reasoning that models nested beliefs via recursive perspective construction. RecToM constructs each character perspective from the preceding character perspective along the character chain specified by the question, reducing higher-order belief questions to actual-world questions within the final constructed perspective. We further provide a KD45 analysis showing that RecToM's perspective construction induces a well-formed belief modality beyond simple event filtering. Experiments on ToM benchmarks, including Hi-ToM, Big-ToM, and FanToM, across multiple LLM backbones show that RecToM consistently outperforms recent advanced approaches, achieving state-of-the-art performance. Notably, RecToM reaches 100\% accuracy on Hi-ToM with GPT-5.4 and Qwen3.5, a benchmark requiring higher-order ToM reasoning.