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 (CS.AI) 2026-06-11

Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge

作者:

arXiv:2606.11430v1 Announce Type: cross Abstract: Mathematical knowledge is split between bibliographic databases (e.g., MathSciNet, zbMATH Open) and formal proof libraries (e.g., Lean mathlib), preventing unified access between published results and their formalizations. We propose a relational bridge-database that aligns publication metadata with formal artifacts, providing an interoperability layer between mathematical literature and machine-verifiable proofs. We introduce a paper-level formalization score that measures how much of a publication is covered in formal systems. As a feasibility study, we show how such scores can be estimated via cross-document alignment between informal texts and Lean formalizations, enabling large-scale analysis of formalization coverage. This framework is a first step toward integrating bibliographic and formal mathematical ecosystems into scalable, machine-actionable knowledge graphs linking publications to formal proof objects.

02.
arXiv (quant-ph) 2026-06-16

Entanglement as a Witness of Quantum Coherence: A Bipartite Monty-Hall Protocol

arXiv:2604.25953v3 Announce Type: replace Abstract: We present a bipartite protocol inspired by the Monty Hall puzzle that operationally distinguishes quantum coherence from classical ignorance. A principal qutrit is entangled with an ancillary qutrit via a controlled unitary, preparing $|\Psi\rangle = \frac{1}{\sqrt{3}}(|A,0\rangle + |B,1\rangle + |C,2\rangle)$. A rank-1 projective discard then eliminates one basis state, leaving a coherent superposition of the two remaining states. Finally, the ancilla and qutrit are measured, yielding joint probabilities that encode the interplay between superposition and measurement back-action. We show that the conditional probability $P(B|anc=0)$ takes the value $1/4$ in both quantum mechanics and the classical ignorant-host model, making it unsuitable as a witness. The true quantum-classical separation emerges in conditional joint probabilities that correlate ancilla outcomes with specific discard operations. We define witnesses $\mathcal{W}_{i,j} = P(anc=i, qutrit=j \mid discard k)$ where $j$ differs from the ancilla-implied state. Quantum mechanics predicts $\mathcal{W} = 1/4$, while any classical epistemic model with perfect initial correlations yields $\mathcal{W} = 0$. We provide the explicit $9 \times 9$ unitary matrix, a complete analysis of all measurement outcomes, and a detailed proof of the violation. The witness is fully immune to white noise and robust against moderate dephasing. The protocol requires only a single pair of entangled qutrits and sequential measurements – no spatial separation, no multiple copies, and no complex sets of incompatible observables. This makes it suitable for advanced undergraduate laboratories and provides a pedagogically accessible test of the ontic-epistemic distinction in quantum foundations.

03.
arXiv (math.PR) 2026-06-16

Sharp connectivity bounds for the vacant set of random interlacements

arXiv:2504.02777v2 Announce Type: replace Abstract: We consider percolation of the vacant set of random interlacements at intensity $u$ in dimensions three and higher, and derive lower bounds on the truncated two-point function for all values of $u>0$. These bounds are sharp up to principal exponential order for all $u$ in dimension three and all $u \neq u_\ast$ in higher dimensions, where $u_*$ refers to the critical parameter of the model, and they match the upper bounds derived in the article arXiv:2503.14497. In dimension three, our results further imply that the truncated two-point function grows at large distances $x$ at a rate that depends on $x$ only through its Euclidean norm, which offers a glimpse of the expected (Euclidean) invariance of the scaling limit at criticality. The rate function is atypical, it incurs a logarithmic correction and comes with an explicit pre-factor that converges to $0$ as the parameter $u$ approaches the critical point $u_*$ from either side. A particular challenge stems from the combined effects of lack of monotonicity due to the truncation in the super-critical phase, and the precise (rotationally invariant) controls we seek, that measure the effects of a certain "harmonic humpback" function. Among others, their derivation relies on rather fine estimates for hitting probabilities of the random walk in arbitrary direction $e$, which witness this invariance at the discrete level, and preclude straightforward applications of projection arguments.

04.
bioRxiv (Bioinfo) 2026-06-20

Evaluation of Trypanosoma brucei Phosphofructokinase Allosteric Inhibition: An In-Silico Study

Human African trypanosomiasis, caused by a protozoan parasite Trypanosoma brucei, is a neglected tropical disease for which well-tolerated, conveniently administered, and highly efficacious medicines are still missing. Previously, T. brucei Phosphofructokinase was targeted by small-molecule inhibitor development efforts. This approach has shown promise both in vitro and in vivo. In this study, we have used these wet-lab results, evaluated the compounds already characterised by Molecular Dynamics simulations, found relationships between in silico and wet-lab data and used these observations to evaluate compounds that we selected through several different approaches of virtual screens. We observed that inhibitor-ATP interactions are highly predictive of the inhibitory activity. Several compounds selected through virtual screens have outperformed previously characterised compounds.

05.
arXiv (quant-ph) 2026-06-16

Comparative Performance Analysis of NIST PQC Standards: From STM32 Software Limitations to FPGA-SoC Acceleration

arXiv:2606.15744v1 Announce Type: new Abstract: The rapid advancement of quantum computing poses a significant threat to classical public-key cryptographic systems, necessitating the transition to Post-Quantum Cryptography (PQC). This study investigates the implementation challenges of NISTstandardized signature schemes on resource-constrained embedded hardware. We present a comparative analysis of SPHINCS+ and CRYSTALS-Dilithium on an ARM Cortex-M4 (STM32F407G) microcontroller. Our findings reveal that SPHINCS+ is practically unusable in this software-only environment, with impractical execution times. Furthermore, the reference Dilithium implementation failed to execute entirely on the MCU due to severe RAM and timing constraints. To overcome these hardware limitations, we integrated a hardware-accelerated Dilithium core onto a Xilinx Zynq-7000 ZedBoard SoC. By implementing a specialized Number Theoretic Transform (NTT) accelerator in the FPGA fabric, we achieved successful execution with performance rates for key generation and signature generation at millisecond levels. These results demonstrate that while pure software PQC is non-viable for standard microcontrollers, a hardware-software codesign approach provides the necessary efficiency for quantumresistant embedded systems.

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

VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation

Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades in specialized, culturally specific domains such as Vietnamese Traditional Medicine (VTM), primarily due to the scarcity of high-quality, structured benchmarks. In this paper, we introduce VietMed-MCQ, a novel multiple-choice question dataset generated via a Retrieval-Augmented Generation (RAG) pipeline with an automated consistency check mechanism. Unlike previous synthetic datasets, our framework incorporates a dual-model validation approach to ensure reasoning consistency through independent answer verification, though the substring-based evidence checking has known limitations. The complete dataset of 3,190 questions spans three difficulty levels and underwent validation by one medical expert and four students, achieving 94.2 percent approval with substantial inter-rater agreement (Fleiss' kappa = 0.82). We benchmark seven open-source models on VietMed-MCQ. Results reveal that general-purpose models with strong Chinese priors outperform Vietnamese-centric models, highlighting cross-lingual conceptual transfer, while all models still struggle with complex diagnostic reasoning. Our code and dataset are publicly available to foster research in low-resource medical domains.

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

Enabling Real-Time Point-of-Care Ultrasound Segmentation: A GPU-Free Deployment in Resource-Limited Settings

作者:

Ultrasound imaging is the most widely adopted medical modality globally due to its low cost and portability, yet artificial intelligence (AI) deployment remains constrained by reliance on GPU-accelerated models, creating a structural paradox where the cost of "intelligence" exceeds that of the imaging device itself. Here, we present the systematic adaptation and extensive evaluation of UltraSeg, an ultra-lightweight architecture originally developed for colonoscopic polyp segmentation, now engineered for point-of-care ultrasound (POCUS) across ten public datasets spanning six anatomical sites (breast, thyroid, kidney, carotid, fetal, and small-animal tumor). We systematically validate both variants in ultrasound domains: UltraSeg-130K (0.13M parameters) achieves 89.7 FPS on single-core CPUs and 34.8 FPS on a refurbished mobile device, while UltraSeg-500K (0.5M parameters) delivers 44.6 FPS on CPU and 16.1 FPS on mobile device. UltraSeg-500K matches or exceeds the Dice performance of the 31M-parameter UNet and approaches 105M-parameter TransUNet in average performance, with superior zero-shot cross-dataset generalization on external validation sets (UDIAT, DDTI). By enabling clinical-grade segmentation without GPU dependency, this work brings AI costs in line with ultrasound accessibility, making advanced diagnostics available in resource-limited settings.

08.
arXiv (CS.LG) 2026-06-12

LLM-ODDR: A Large Language Model Framework for Joint Order Dispatching and Driver Repositioning

arXiv:2505.22695v2 Announce Type: replace Abstract: Ride-hailing platforms face significant challenges in optimizing order dispatching and driver repositioning operations in dynamic urban environments. Traditional approaches based on combinatorial optimization, rule-based heuristics, and reinforcement learning often overlook driver income fairness, interpretability, and adaptability to real-world dynamics. To address these gaps, we propose LLM-ODDR, a novel framework leveraging Large Language Models (LLMs) for joint Order Dispatching and Driver Repositioning (ODDR) in ride-hailing services. LLM-ODDR framework comprises three key components: (1) Multi-objective-guided Order Value Refinement, which evaluates orders by considering multiple objectives to determine their overall value; (2) Fairness-aware Order Dispatching, which balances platform revenue with driver income fairness; and (3) Spatiotemporal Demand-Aware Driver Repositioning, which optimizes idle vehicle placement based on historical patterns and projected supply. We also develop JointDR-GPT, a fine-tuned model optimized for ODDR tasks with domain knowledge. Extensive experiments on real-world datasets from Manhattan taxi operations demonstrate that our framework significantly outperforms traditional methods in terms of effectiveness, adaptability to anomalous conditions, and decision interpretability. To our knowledge, this is the first exploration of LLMs as decision-making agents in ride-hailing ODDR tasks, establishing foundational insights for integrating advanced language models within intelligent transportation systems. While the current framework incurs higher computational costs than traditional methods, we show that parallel decomposition and model distillation can reduce latency to production-viable levels for deployment.

09.
arXiv (CS.AI) 2026-06-19

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

arXiv:2605.29483v2 Announce Type: replace Abstract: Wearable devices enable continuous monitoring of physiological signals such as ECG and PPG, but existing mHealth systems are largely limited to task-specific prediction pipelines or reactive question answering over static summaries. They lack the ability to support temporal reasoning, persistent physiological context, and proactive monitoring over long-term signal streams. We propose VitalAgent, a tool-augmented agentic framework for ECG/PPG-based mHealth that supports both reactive question answering and proactive monitoring. VitalAgent is built on a longitudinal physiological memory and a tool-augmented reasoning interface that enables dynamic computation over raw signals. We further introduce VitalBench, a longitudinal physiological monitoring benchmark dataset comprising 1,862 QA pairs for reactive question answering and 90.2 hours of continuous ECG/PPG recordings for proactive monitoring, covering cardiac, physical activity, and stress-related tasks. Experiments demonstrate that VitalAgent achieves over 25% improvement over prompt-based and ReAct baselines in reactive evaluation and supports proactive alert monitoring over long-term physiological signals, highlighting the importance of dynamic tool use and long-term physiological monitoring.

10.
arXiv (CS.CV) 2026-06-11

Tac-DINO: Learning Vision-Tactile Features with Patch Alignment

Touch is the primary medium through which humans interact with the environment. Currently, tactile learning mainly focuses on image-level pretraining or alignment. However, tactile signals correspond to local object contact, while research into scale alignment and holographic matching remains limited and proper datasets and benchmarks also lack. To bridge this gap, we first construct a data collection system to acquire a large-scale tactile dataset, with over 20 K tactile contacts from 505 real-world objects. Building on this dataset, we design a Vis-Tac Holographic Matching Benchmark to evaluate vision-tactile local-to-global alignment ability. Then we propose Vision-Tactile Patch Alignment (VTPA) methods for vision-tactile representation learning. Experiments demonstrate that these exceed the performance of methods without alignment and align with whole-object images.

11.
arXiv (CS.LG) 2026-06-18

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

arXiv:2606.18312v1 Announce Type: cross Abstract: Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient inversion attacks show that these updates can reveal enough information to reconstruct client inputs. Existing attacks on transformers either optimize dummy inputs to match the true client updates, which is costly and unstable for modern models, or exploit the low rank of attention gradients to identify a subspace containing the true layer embeddings, followed by a discrete membership test for candidate tokens. However, this token test is brittle under numerical noise, i.e., from quantization or Differential Privacy (DP), and scales poorly for encoder models with non-causal attention. We introduce TIGER, a continuous gradient inversion attack that turns this subspace signal into a differentiable objective. Instead of searching over tokens or matching full gradients, TIGER directly optimizes token embeddings to minimize their distance to the subspace. Our experiments demonstrate that on encoder-only models, TIGER substantially improves both reconstruction quality and runtime over existing attacks, while on decoder models, TIGER is more robust than prior subspace-based attacks, enabling the first successful reconstructions in DP-defended federated learning settings.

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

GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving

End-to-end autonomous driving has made significant progress by unifying perception, prediction, and planning within a single learning framework, achieving strong performance in short-horizon decision making. However, most existing E2E-AD methods remain confined to short-horizon planning and lack the ability to model long-term temporal dependencies, which severely limits their generalization and security in complex and highly interactive driving scenarios. In this work, we propose GraphWorld, an E2E-AD framework that explicitly enhances long-horizon planning through latent world modeling. We introduce an Ego-Centric Interaction Graph, which adaptively models critical neighboring agents based on spatial proximity, and propagates relational context to planning queries via cross-node cross-attention. We present a World-State-Conditioned Planning that learns ego-centric latent world representations by modeling interactions between an ego vehicle and surrounding agents. This latent world state captures key interaction dynamics and safety-relevant semantics, and serves as a conditioning signal to guide long-horizon, safety-aware trajectory planning. Extensive experiments on Bench2Drive, NAVSIMv1/2, and nuScenes demonstrate that GraphWorld significantly reduces collision rates and improves long-horizon planning performance, validating its effectiveness in complex driving environments.

13.
arXiv (CS.LG) 2026-06-16

Generative Modeling on Metric Graphs via Neural Optimal Transport

arXiv:2606.16273v1 Announce Type: cross Abstract: We introduce, to our knowledge, the first deep generative modeling framework for probability distributions continuously supported on compact metric graphs. Given source and target measures on a metric graph, our method embeds the graph into a smooth ambient space, solves an entropic Kantorovich problem via a neural semidual parameterization, and projects generated samples back onto the original graph. We study two embedded geometries: an extrinsic Euclidean realization and the intrinsic tropical Abel–Jacobi embedding into the Jacobian torus. In both cases, the resulting generator is graph-supported by construction. We prove that, in the joint limit of increasing neural expressivity, the learned generator converges weakly to a valid transport coupling between the original graph measures. Empirically, across a range of geometrically distinct graphs, our method matches or improves upon heuristic transport baselines based on discrete graph OT, while scaling more favorably. Finally, we demonstrate scalability on real-world urban mobility data by training our model on one million Uber pickup locations in Manhattan, New York City.

14.
arXiv (quant-ph) 2026-06-15

Sensitivity of polaron-molecule observables to MDR/GUP-like ultraviolet deformations at low energies via quantum computing

arXiv:2606.14479v1 Announce Type: new Abstract: We show that impurity many-body observables can display enhanced sensitivity to ultraviolet deformations of generalized-uncertainty-principle and modified-dispersion-relation type at accessible energy scales. Using a deformed polaron-molecule Hamiltonian constructed to preserve the infrared sector, we quantify the impact of such deformations on spectral and Ramsey observables and implement the corresponding dynamics in a controlled quantum computing setting. We identify regimes near the polaron-molecule crossover where small ultraviolet deformations are strongly amplified, leading to experimentally resolvable changes in quasiparticle properties and spectral response. Our results establish a concrete sensitivity-based route to low-energy quantum-gravity phenomenology in a well-defined many-body platform and delimit the validity of the effective description. Furthermore, we report experimental validation on the QRed superconducting quantum processor (BSC-CNS).

15.
Nature (Science) 2026-06-17

Cucurbituril-based anion-conducting membranes with supramolecular nanopores

作者:

Nanoporous anion-conducting membranes have gained considerable interest for their potential to reduce resistance in electrochemical devices1–4. Current pore-forming methods, such as backbone engineering through polymers of intrinsic microporosity5,6 or covalent organic and metal–organic frameworks7,8, however, suffer from limited structural control, mechanical fragility or demanding synthesis. Here we establish a supramolecular strategy that overcomes these limitations by constructing uniform, dynamic nanopores. Co-assembly of the rigid macrocyclic host cucurbit[7]uril with the cationic polymer guest quaternized poly(piperidinium-terphenyl) yields a robust network of nanometre-scale channels while simultaneously enhancing mechanical and chemical stability. The dynamic host–guest interactions allow the pore structure to fluctuate on picosecond and angstrom scales. This transient environment supports low-friction hydroxide migration through a Grotthuss mechanism, producing a marked enhancement in ionic conductivity. This bottom-up design principle provides a versatile new tool for molecularly engineering transport pathways and promises to advance electrochemical reactors with respect to energy efficiency, operational stability and the production of high-purity products. A supramolecular strategy, in which uniform, dynamic nanopores are constructed, overcomes the limitations of limited structural control, mechanical fragility or demanding synthesis in nanoporous anion-conducting membranes, providing a versatile tool for molecularly engineering transport pathways.

16.
arXiv (math.PR) 2026-06-15

Secondary terms for first moments of Selmer groups of twists of elliptic curves over global function fields

作者:

arXiv:2606.14274v1 Announce Type: cross Abstract: Let $E$ be a non-isotrivial elliptic curve over a global function field $\mathbb{F}_q(t)$ of characteristic coprime to $2$ and $3$. Under some explicit conditions, we determine the secondary terms for the first moments of prime Selmer groups of cyclic prime twist families of $E$ over $\mathbb{F}_q(t)$.

17.
arXiv (CS.LG) 2026-06-12

To GAN or Not To GAN: Segmentation Analysis on Mars DEM

arXiv:2606.13252v1 Announce Type: new Abstract: To better understand Martian Surface, which is needed to enable Rovers navigate Mars with ease, it is necessary to be able to determine the location of mounds. Detecting and studying these morphologies can also help us find evidence of extraterrestrial life, in this case, more specifically, water or signs of life conducive environments. Detection of mounds was done by manually mapping morphological parameters onto Digital Elevation Models. This paper solves the problem by automatically detecting and or predicting mounds on Mars using Neural Network based Semantic Segmentation methodologies. This is done by using supervised semantic segmentation model and generative adversarial approach. A comparison of the approaches shows that adding extra artificially generated data did not improve the result.

18.
arXiv (CS.CL) 2026-06-11

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with the distribution it produces under privileged context, typically a verified solution. However, we show that the learning signal drawn from this distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce more direct, shorter outputs. We term this pathology privilege-induced style drift, which destabilizes training or causes response length to shrink. To address this, we propose RLCSD (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing the style shift that conditioning on a hint tends to induce regardless of correctness, and yielding a signal that is more concentrated on task-bearing tokens. Experiments on Qwen3 (1.7B/4B/8B) and Olmo-3-7B-Think across mathematical and logical reasoning show that RLCSD consistently outperforms GRPO and prior OPSD methods. We further show that the contrastive principle is general: it plugs into existing OPSD methods to improve them, and its underlying insight extends to the broader cross-model on-policy distillation setting.

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

The Complexity of Min-Max Optimization for Quadratic Polynomials

arXiv:2606.17000v1 Announce Type: cross Abstract: We prove that computing approximate stationary points of min-max optimization over the hypercube is PPAD-hard for quadratic polynomials. This holds even when the polynomials are multilinear, each variable appears in at most three monomials, and the approximation factor is inverse polynomial. As a direct consequence, we obtain the first PPAD-hardness results for two-team zero-sum polymatrix games.

20.
arXiv (CS.CL) 2026-06-17

ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions

Large language models perform increasingly well on standardized logical reasoning benchmarks, but whether this ability remains robust beyond English is unclear. We introduce ChLogic, an English–Chinese aligned benchmark that tests whether models preserve logical reasoning performance when the same latent logical structure is expressed in English and diverse Chinese surface realizations. Built from formal logical templates, the benchmark contains three data sets: (i) the General aligned set, derived from 60 General Propositions across nine template families; (ii) the Difficult aligned set, derived from 40 Difficult Problems; and (iii) the Chinese-only set, covering 15 language-specific phenomenon types. Each aligned item pairs one English reference expression with five Chinese realizations. Experiments on Qwen3, Ministral, and GLM models reveal a persistent English–Chinese performance gap. Back-translation from standard Chinese into English often improves performance on the General aligned set, but produces mixed effects on the Difficult aligned set, where Qwen3-32B and GLM-5.1 perform worse after translation. These results indicate that Chinese surface realization, translation artifacts, and model-specific behavior jointly affect multilingual logical reasoning. Overall, ChLogic provides a useful stress test for the robustness of multilingual reasoning.

21.
arXiv (CS.CV) 2026-06-16

RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos

Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale. Editable 3D Gaussian Splatting (3DGS) simulation offers a promising alternative by reconstructing real driving scenes and supporting controllable scene editing. However, edited 3DGS-rendered videos still suffer from a significant Sim-to-Real gap, including rendering artifacts, degraded foreground assets, inconsistent illumination, and temporal flickering. Existing restoration and video generation methods are insufficient for this task, as they often fail to jointly repair 3DGS-specific artifacts, improve visual realism, and ensure temporal consistency. To fill this gap, we propose RealityBridge, a structure-preserving and asset-aware Sim-to-Real framework for edited 3DGS driving videos. RealityBridge uses multimodal controls, including rendered videos, foreground masks, edge maps, and semantic masks, together with a lightweight GateNet for adaptive condition allocation across backbone layers. We further construct targeted training data and introduce autoregressive long-video training with reward-guided post-training to improve restoration quality, temporal stability, and hallucination suppression. Extensive experiments on internal and public driving datasets show that RealityBridge outperforms existing methods in artifact removal, illumination harmonization, and long-sequence temporal consistency.

23.
arXiv (CS.AI) 2026-06-16

Honeypot Protocol

作者:

arXiv:2604.13301v1 Announce Type: cross Abstract: Trusted monitoring, the standard defense in AI control, is vulnerable to adaptive attacks, collusion, and strategic attack selection. All of these exploit the fact that monitoring is passive: it observes model behavior but never probes whether the model would behave differently under different perceived conditions. We introduce the honeypot protocol, which tests for context-dependent behavior by varying only the system prompt across three conditions (evaluation, synthetic deployment, explicit no-monitoring) while holding the task, environment, and scoring identical. We evaluate Claude Opus 4.6 in BashArena across all three conditions in both honest and attack modes. The model achieved 100% main task success and triggered zero side tasks uniformly across conditions, providing a baseline for future comparisons with stronger attack policies and additional models.

24.
arXiv (CS.CL) 2026-06-12

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with standard on-policy reinforcement learning (RL) and hard to interpret causally. Our key insight is that a single pair of explicit boundary tokens can address both issues at once: discrete entry and exit anchors make the latent block compatible with standard on-policy RL, and the same anchors offer a natural foothold for mechanistic analysis. Motivated by this, we propose SWITCH, a switchable latent reasoning framework. The model emits to enter latent mode and to exit. Because the boundaries are ordinary discrete tokens, the GRPO policy ratio is well-defined at every decision point. The same anchors also expose the latent steps to direct probing and causal intervention. We train the model with a visible-to-latent curriculum and a Switch-GRPO objective that propagates gradients through recurrent latent computation. SWITCH consistently outperforms prior hidden-state-recurrence latent reasoning approaches at similar scale. Mechanistic analysis through the boundary tokens further reveals three findings: (i) is a sharply localised, learned switching policy rather than a stylistic artefact; (ii) the latent step it opens performs problem-specific, causally important computation rather than acting as an inert placeholder; and (iii) that computation is concentrated at a single hidden-state transition on entry. Together, these results show that hidden-state-recurrence latent reasoning is both RL-trainable and open to direct mechanistic analysis, including of how on-policy RL itself improves the model from the inside.

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

Planning under Distribution Shifts with Causal POMDPs

arXiv:2602.23545v2 Announce Type: replace Abstract: In the real world, planning is often challenged by distribution shifts. As such, a model of the environment obtained under one set of conditions may no longer remain valid as the distribution of states or the environment dynamics change, which in turn causes previously learned strategies to fail. In this work, we propose a theoretical framework for planning under partial observability using Partially Observable Markov Decision Processes (POMDPs) formulated using causal knowledge. By representing shifts in the environment as interventions on this causal POMDP, the framework enables evaluating plans under hypothesized changes and actively identifying which components of the environment have been altered. We show how to maintain and update a belief over both the latent state and the underlying domain, and we prove that the value function remains piecewise linear and convex (PWLC) in this augmented belief space. Preservation of PWLC under distribution shifts has the advantage of maintaining the tractability of planning via $\alpha$-vector-based POMDP methods.