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) 2026-06-12

Diffusive Dynamics of Nonstabilizerness

arXiv:2606.13606v1 Announce Type: new Abstract: Symmetries shape the quantum-information dynamics of many-body systems, but their effect on nonstabilizerness, the resource complementary to entanglement, is less understood. We compute the stabilizer Rényi entropy, a measure of nonstabilizerness, in $\mathrm{U}(1)$-symmetric one-dimensional random circuits. The disorder-averaged dynamics is captured by a four-replica tensor network, which we evaluate by $S_4$-adapted infinite time-evolving block decimation (iTEBD) directly in the thermodynamic limit. Together with a hydrodynamic argument, our results identify a diffusive universality class for the late-time approach of nonstabilizerness to its random-state value, with the stabilizer Rényi entropy gap closing as $1/t$. The same scaling is verified in an energy-conserving nonintegrable Ising chain. More broadly, our framework provides a hydrodynamic perspective on nonstabilizerness generation and offers insight into the design of approximate Haar-random states in Hamiltonian dynamics.

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

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

arXiv:2602.05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts. Adapting automated jailbreak optimizers does not close this gap: jailbreaks shape models toward generic compliance, while prompt injection requires emitting specific tool calls with correct parameters. The success signal is binary, and randomly sampled suffixes almost never trigger it, so standard optimizers have no gradient to follow. We present AutoInject, a black-box reinforcement learning (RL) framework that learns adversarial suffixes for prompt injection. A learned comparison-based reward scores each candidate against the best suffix seen so far, turning the binary signal into a dense reward suitable for RL optimization. The framework supports both online query-based attacks and offline-trained transferable suffixes that need no utility access at deployment, and incorporates a utility objective when task-completion feedback is available. On AgentDojo, AutoInject outperforms template attacks, GCG, TAP, and adaptive attack across production models, with statistically significant improvements under McNemar's test with p

03.
arXiv (CS.LG) 2026-06-11

TacCoRL: Integrating Tactile Feedback into VLA via Simulation

arXiv:2606.11743v1 Announce Type: cross Abstract: Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, but visual observations alone often miss the local contact state required for contact-rich tasks. We present TacCoRL, a scalable framework that injects Tactile feedback into VLA policies and improves them through sim-real Co-training and simulation-based reinforcement learning (RL), without requiring large-scale tactile pretraining or extensive real-world contact exploration. The key idea is not only adding touch as an input, but learning how contact readings should modulate action responses in near-failure states that are rare in demonstrations and risky to collect on hardware. We use a real-aligned simulator as a closed-loop training environment for contact interaction. Mixed simulated and real trajectories first warm-start tactile-conditioned actions in the pretrained policy. Reinforcement learning with verifiable task rewards then optimizes the policy using simulated contact rollouts. It reinforces tactile-conditioned actions that lead to task completion, while a supervised objective on real trajectories keeps the refined policy anchored to deployment visual, tactile, and action distributions. The resulting policy transfers directly to the real robot without privileged simulation state or online real-world RL. Across four bimanual contact-rich tasks, the final visuo-tactile policy achieves an average success rate of 72.5%, compared to baseline of 50.0%. Result videos and more details are available at https://tac-corl.github.io/

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

A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

arXiv:2606.13565v1 Announce Type: new Abstract: Discrete diffusion models offer a simple and stable likelihood-based framework for sequence generation, recently extended to any-length settings via token insertion. Principled reward-guided fine-tuning for any-length discrete diffusion, however, remains largely unexplored. We introduce Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding (A2D2), a unified framework for reward-guided fine-tuning of any-length discrete diffusion models via joint optimization of the insertion and unmasking policies together with a quality-based inference schedule. We derive the Radon-Nikodym derivative for the joint insertion-unmasking path measures, enabling theoretically guaranteed convergence to the intractable reward-tilted sequence distribution without requiring target samples. Building on this, we establish unmasking and insertion quality as tractable approaches for minimizing decoding error and introduce the Adaptive Joint Decoding (AJD) loss, which provably yields the optimal path measure that generates the reward-tilted distribution. Empirically, A2D2 improves reward optimization while enhancing generation flexibility and accuracy over prior fixed-length fine-tuning and inference-time guidance methods.

05.
arXiv (CS.AI) 2026-06-17

Belief-Space Control for Personalized Cancer Treatment via Active Inference

arXiv:2606.10376v2 Announce Type: replace Abstract: Cancer treatment is at the core a sequential decision-making problem with partial observability, latent patient heterogeneity, and explicit constraints on the budget for medical measurements. Unlike standard Reinforcement Learning (RL) approaches that control state trajectories, cancer treatments permanently modify patients' transition dynamics, changing how states evolve over time. We model cancer treatment as a belief-space planning problem using active inference, deriving an expected free-energy objective that unifies goal-directed control and information acquisition under measurement budgets without. We implement this framework using real clinical cancer data from the AACR Project GENIE Biopharma Collaborative dataset. Results on clinical data demonstrate a simultaneous patient categorization and high treatment efficacy, under real measurement and treatment constraints.

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

MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics

arXiv:2606.11249v1 Announce Type: cross Abstract: Realizing the vision of 6G connected robotics requires reconciling high-performance collaborative control with the rigid spectral limitations of physical wireless channels. In realistic collaborative sensing scenarios, spectral resources are quantized into finite physical resource blocks or orthogonal subcarriers, rendering simultaneous transmission by all agents infeasible. To address this, we propose Multi-Agent Semantic K-Scheduling (MASK), a control architecture designed to sustain robust, risk-aware coordination under strict instantaneous bandwidth caps. We introduce Arbiter-Assisted Semantic Information Gating (A-SIG), a lightweight coordination mechanism that enforces hard access constraints by scheduling only the top-K agents based on locally computed semantic importance scores. By aggregating these prioritized observations into a compact latent state, a self-supervised global encoder enables a distributional policy to mitigate tail risks despite data sparsity. We evaluate MASK across diverse benchmarks, demonstrating that it matches the performance of communication-unconstrained baselines even when channel access is restricted to a small fraction of the swarm size. Furthermore, the framework exhibits inherent resilience to packet erasures, validating semantic scheduling as a critical enabler for resource-constrained 6G systems.

07.
arXiv (CS.LG) 2026-06-17

A Bayesian Boolean Matrix Factorization with Application to Copy Number Analysis in Cancer

arXiv:2606.17491v1 Announce Type: cross Abstract: Binary data factorization is common, but real-valued methods ignore discreteness and yield hard-to-interpret factors. Boolean Matrix Factorization (BooMF) instead decomposes a binary matrix into two lower-rank binary matrices via logical AND and OR, expressing the data as a Boolean disjunction of interpretable patterns. In cancer genomics, BooMF can reveal coordinated feature changes that may drive tumor evolution, unlike rotational or additive decompositions. Most existing BooMF methods are heuristic, greedy, sensitive to initialization, prone to local optima, and do not support principled model selection or uncertainty quantification. We introduce Bayesian Boolean Matrix Factorization (BBMF), a fully conjugate generative model with sparsity-inducing priors. It enforces Boolean constraints, yields interpretable latent factors with coherent uncertainty quantification, and admits Gibbs sampling with closed-form full conditionals. Because cancer evolution often involves widespread, near-simultaneous chromosome-number changes (e.g., whole-genome duplication followed by instability and selection), Boolean factorizations capture these patterns more naturally than additive models. Applied to arm-level copy-number alteration data in multiple myeloma, where entries indicate presence/absence of chromosomal-arm amplifications, BBMF finds a small set of interpretable bicliques linking patient subsets to recurrently co-altered chromosomal arms, providing a compact, biologically meaningful summary of tumor heterogeneity and demonstrating BBMF's utility for uncovering discrete latent structure in complex binary data.

08.
arXiv (CS.LG) 2026-06-19

Towards Graph-Based Deep Learning for Map Generalization: Insights from Building Footprints Simplification and Aggregation

arXiv:2606.19956v1 Announce Type: new Abstract: Map generalization remains one of the fundamental tasks in cartography, especially for the simplification and aggregation of complex building footprints. This study presents the first exploratory application of graph-based deep learning to both tasks, reformulating simplification as node movement prediction and aggregation as link prediction within a unified graph learning framework. We evaluate representative graph neural network architectures (GCN, GAT, and GraphSAGE) on multi-scale building datasets, showing that GraphSAGE demonstrates relative strengths in link prediction accuracy, while also revealing persistent challenges in precise node movement prediction. Beyond quantitative performance, the results highlight that aggregation poses greater complexity and challenges than simplification, underscoring the difficulty of capturing higher-level spatial relationships in map generalization with current deep learning approaches. Although limitations such as data imbalance and the need for post-processing remain, the study provides valuable insights and methodological directions for advancing automated map generalization with deep learning approaches.

10.
arXiv (CS.CV) 2026-06-24

Quantifying mandibular positioning error and simulated temporomandibular joint-space changes in patient-specific occlusal splints

Patient-specific occlusal positioning splints can be regarded as physical realisations of planned mandibular transformations. However, the achieved mandibular pose may differ from the planned one because of acquisition, registration, fabrication, and positioning errors. This study presents a transformation-based biomedical engineering framework for quantifying mandibular positioning accuracy and propagating the resulting error to a simulated temporomandibular joint configuration. Multimodal 3D data, including CBCT, facial motion acquisition, and dental scans, were integrated in a common coordinate system. Positioning splints corresponding to selected mandibular poses were designed and fabricated, and their realised positions were evaluated using repeated scans of plaster models. Discrepancies between planned and achieved positions were represented as rigid-body error transformations and analysed in SE(3), together with surface-distance metrics. The estimated transformations were propagated to CBCT-derived TMJ structures to quantify changes in condyle-fossa distance maps. The results demonstrate a systematic translational component and anisotropic variability of mandibular positioning error, with measurable propagation to simulated TMJ-space changes. The proposed framework provides an objective method for documenting planned and achieved mandibular configurations and for analysing positioning uncertainty in patient-specific splint workflows.

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

NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems

Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is widely adopted to improve grounding, confidence calibration in RAG settings remains poorly understood. We conduct a systematic study across four benchmarks, revealing that LLMs exhibit poor calibration performance especially when noisy contexts are retrieved. Specifically, contradictory or irrelevant evidence tends to exacerbate the model's overconfidence issue. To address this, we propose NOVA Rules (NOise-Aware Verbal Confidence CAlibration Rules) to provide a principled foundation for resolving overconfidence under noise. We further design NOVA, a noise-aware calibration framework that synthesizes supervision from ~2K HotpotQA examples guided by these rules. By performing supervised fine-tuning (SFT) with this data, NOVA equips models with intrinsic noise awareness without relying on stronger teacher models. Empirical results show that NOVA yields substantial gains, improving ECE scores by 10.9% in-domain and 8.0% out-of-domain. By bridging the gap between retrieval noise and verbal calibration, NOVA paves the way for both accurate and epistemically reliable LLMs.

12.
arXiv (CS.AI) 2026-06-15

Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry

arXiv:2606.13934v1 Announce Type: new Abstract: Humans cannot always intuit what scenarios are most challenging to LLMs. Hoping to capture challenging edge cases, developers either design problems to be difficult for humans or curate extensive benchmarks. What if we could instead anticipate which scenarios a model will fail on? In this paper, we use an LLM's representational geometry to predict which concept combinations it will fail on. We attribute this compositional failure to interference between salient features. In tasks that require systematic composition - toy programmatic settings, multihop reasoning, multilingual factual recall - we find that when a pair of concepts is encoded near-orthogonally, the model reliably composes them. When their linear encodings are close, producing interference, the model fails to compose them. Our method reliably anticipates failure modes across different compositional tasks, without evaluating specific inputs. These results lay the groundwork to use representational geometry to identify high-risk examples, construct targeted stress tests, and provide a scalable foundation for active learning in real-world deployment.

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

Pepti-Agent: An AI Agent for Peptide Design and Optimization

Therapeutic peptides occupy a valuable design space between small molecules and biologics, but their development requires satisfying several competing constraints at once: solubility, hemolytic activity, and nonspecific surface fouling are governed by overlapping sequence features, so improving one property often degrades another. Computational design addresses this by pairing generative models with sequence-based property predictors, iteratively proposing and refining candidates. However, these components are typically wired together as monolithic scripts that are difficult to inspect, extend, or reuse, and they often refine sequences by natural-language reasoning rather than by tracking the evolving multi-property state of each candidate. We present Pepti-Agent, a closed-loop, peptide-specific framework that exposes generation, property prediction, and single-residue mutation as independently inspectable Model Context Protocol (MCP) tools. A large language model controller invokes these tools and consults live predictor output between calls, so refinement is guided by each sequence's current property profile rather than by language reasoning alone. Task-specific PeptideGPT models generate candidates, ProtBERT-based classifiers score solubility, hemolysis, and non-fouling, and two interchangeable mutation operators propose sequence edits. By recording a per-step trace of controller decisions, predictor outputs, and accepted mutations, Pepti-Agent offers a reproducible substrate for benchmarking multi-objective design strategies and for prioritizing candidates for experimental validation.

14.
arXiv (CS.LG) 2026-06-19

Tracking Representation Dynamics in Large Language Models with Persistent Homology

arXiv:2606.19542v1 Announce Type: new Abstract: Large language models are commonly aligned through supervised fine-tuning, yet little is known about how their internal representations evolve during this process. We study alignment dynamics using persistent homology by tracking the topology of activation spaces throughout fine-tuning. Across four transformer language models ranging from 1B to 7B parameters and three alignment objectives corresponding to helpful, harmless, and mixed training data, we find that the majority of topological reorganization occurs during the earliest stages of training. A dense checkpoint analysis reveals a transient peak in topological activity followed by rapid stabilization. We further show that different alignment objectives induce distinguishable topological trajectories, while instruction-tuned and pretrained models exhibit qualitatively different patterns of evolution. Our results suggest that persistent homology provides a complementary perspective on alignment, revealing representation-level changes that are not apparent from behavioral metrics alone.

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

Scaling limits of multitype Bienaymé trees

arXiv:2507.23241v2 Announce Type: replace Abstract: We consider critical multitype Bienaymé trees that are either irreducible or possess a critical irreducible component with attached subcritical components. These trees are studied under two distinct conditioning frameworks: first, conditioning on the value of a linear combination of the numbers of vertices of given types; and second, conditioning on the precise number of vertices belonging to a selected subset of types. We prove that, under a finite exponential moment condition, the scaling limit as the tree size tends to infinity is given by the Brownian Continuum Random Tree. Additionally, we establish strong nonasymptotic tail bounds for the height of such trees. Our main tools include a flattening operation applied to multitype trees and sharp estimates regarding the structure of monotype trees with a given sequence of degrees.

16.
arXiv (math.PR) 2026-06-18

A scaling limit theorem for controlled branching processes with a size-divisible term

arXiv:2508.17116v2 Announce Type: replace Abstract: This paper establishes general sufficient conditions for a sequence of controlled branching processes to converge weakly on the Skorokhod space. We focus on a class of control mechanisms that extend previous results by decomposing those random variables into the sum of two independent components: an immigration term, which depends on the current population size, and a size-divisible term, which can be expressed as the sum of random contributions from each individual. This extension allows us to capture a broad range of control functions including Poisson, binomial, and negative binomial distributions, commonly used in the literature. The assumptions are formulated in terms of probability generating functions of the offspring and control laws, distinguishing in this latter between the immigration and the size-divisible parts. The limit process is shown to be a continuous-state branching process with dependent immigration. The proof essentially relies on tightness arguments and the identification of a martingale problem. We also identify the special case in which the limit reduces to a classical Feller branching diffusion with immigration.

17.
arXiv (CS.LG) 2026-06-19

FloatDoor: Platform-Triggered Backdoors in LLMs

arXiv:2606.19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has shown that an identical model can produce measurably different outputs depending on the deployment platform, a consequence of non-associative floating-point arithmetic and divergent kernel implementations. We study the security implications of this platform-dependent variability and uncover a novel attack surface on LLM deployments. We introduce FloatDoor, the first input-independent, platform-triggered backdoor attack against generative LLMs. The compromised model exhibits adversary-chosen behavior when served on a target platform and is otherwise benign. FloatDoor is realized through two lightweight LoRA adapters, one that amplifies inter-platform numerical divergence and one that binds the resulting platform signature to a malicious downstream task, while leaving aggregate model utility largely intact. FloatDoor exploits a pronounced time-of-check, time-of-use gap between model auditing and serving. We demonstrate FloatDoor on Qwen3-4B across a broad range of deployment targets, including NVIDIA GPUs, Google TPUs, AWS Graviton, and Alibaba Yitian-710. As a final case study, we show that FloatDoor reliably induces exploitable code vulnerabilities on a chosen target platform. Our results establish a new class of attacks on LLM deployments and underscore the pressing need for trusted model supply chains in sensitive, LLM-powered applications.

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

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these systems often suffer from a critical limitation in practice: agents fail to recognize their own knowledge boundaries, blindly triggering searches when internal knowledge suffices and failing to terminate search even when adequate evidence has been collected. The lack of self-awareness leads to severe over-search, incurring substantial inference latency and prohibitive computational cost. To this end, we propose SAAS, a novel RL framework designed to cultivate dynamic self-awareness that precisely regulates search behavior without compromising accuracy. SAAS introduces three key components: (i) a search boundary modeling mechanism, which identifies the search boundary under the evolving policy by contrasting search-disabled and search-enabled rollouts; (ii) a boundary-aware reward module, which translates this boundary awareness into trajectory-level penalties, suppressing unnecessary and redundant searches; and (iii) a stage-wise optimization strategy, which leverages a sequential curriculum to prioritize reasoning over search regularization, thereby avoiding reward hacking. Extensive experiments demonstrate that SAAS substantially reduces over-search, while maintaining accuracy. Our code and implementation details are released at https://github.com/XMUDeepLIT/SAAS.

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

Tensor-Network-Based Distributed Quantum Dynamics on Independent Quantum Computers

arXiv:2606.11579v1 Announce Type: new Abstract: We present an approach based on tensor networks for distributed quantum computing simulation of chemical wavepacket dynamics in a continuous variable representation. The central idea is that the tensor-network representation of the multidimensional time-evolution operator naturally induces an elevated Hilbert space where the dynamics decomposes into a set of independent lower-dimensional propagations. This transformation converts an entangled quantum evolution into a set of parallel computational tasks that can be executed asynchronously across heterogeneous quantum and classical computing architectures. The resulting formalism establishes a direct connection between tensor-network decompositions, uniformly controlled quantum circuits, and asynchronous distributed quantum computing. The approach is developed with a goal towards hybrid quantum/classical implementation, and is appropriate for a general heterogeneous mixture of quantum hardware systems. The experimental realization of the asynchronously distributed quantum processes that arise from the tensor-network decomposition are carried out on the Sandia National Laboratories' trapped-ion quantum computer, where the circuits are compiled using native partial-entangling $XX(\theta)$ gates, reducing the expected two-qubit gate infidelity by more than 30\% relative to conventional fully entangling decompositions. We demonstrate the methodology by quantum computing the vibrational spectra of a small protonated water cluster that shows critical quantum nuclear behavior. Such water cluster systems have been found to be challenging for experimental action spectroscopy and for theory, and here, for the first time, we provide results for vibrational spectroscopy that are in agreement with the respective classical results to within 4cm$^{-1}$, thus allowing for the potential for spectroscopic accuracy from quantum computations.

20.
arXiv (quant-ph) 2026-06-17

Unclonable Encryption in the Haar Random Oracle Model

arXiv:2603.11437v2 Announce Type: replace-cross Abstract: We construct unclonable encryption (UE) in the Haar random oracle model, where all parties have query access to $U,U^\dagger,U^*,U^T$ for a Haar random unitary $U$. Our scheme satisfies the standard notion of unclonable indistinguishability security, supports reuse of the secret key, and can encrypt arbitrary-length messages. That is, we give the first evidence that (reusable) UE, which requires computational assumptions, exists in "microcrypt", a world where one-way functions may not exist. As one of our central technical contributions, we build on the recently introduced path recording framework to prove a natural ``unitary reprogramming lemma'', which may be of independent interest.

21.
arXiv (CS.CL) 2026-06-24

Harmonic: Hierarchical State Space Models for Efficient Long-Context Language Modeling

Authors:

We present Harmonic, a hierarchical state space model (SSM) for language modeling. The architecture stacks three recurrent levels at progressively slower timescales; each level receives the prediction error of the level below as input, rather than its raw hidden state. On enwiki8 with equal token budgets, Harmonic outperforms a comparable Transformer (28M params) by +1.4% at 1K tokens, +6.7% at 8K tokens, and +11.4% at 32K tokens (bpt, lower is better). It also outperforms Mamba at every tested length by 0.7–1.8%. At 64K tokens, both Mamba and Transformer run out of memory on an 80GB H100; Harmonic trains successfully, reaching 6.169 bpt. Results replicate on WikiText-103 (H-TF gap +1.7% to +7.2% across 1K–32K). At 1B parameter scale, replacing all attention layers in TinyLlama 1.1B with HarmonicBlock eliminates the RoPE positional encoding limit: the resulting Hallamonic model maintains stable loss across sequence lengths 1K–8K on two independent clean benchmarks (Lambada and fineweb-edu held-out), while TinyLlama degrades catastrophically past its 2K-token RoPE limit (gap: +9.4 bpt at seq=8K on Lambada). Compute is O(L) per forward pass vs. O(L^2) for attention. Logs: https://github.com/Omibranch/harmonic-logs.

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

AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages

Despite their linguistic diversity and global significance, African languages remain underrepresented in research and resources to support NLP. We aim to bridge this gap by introducing AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine diverse African languages spanning major language families and regions across Sub-Saharan Africa. Using the Surface-Syntactic Universal Dependencies (SUD) framework, our community-led effort provides high-quality, native-speaker verified data that capture typological key features such as agglutination and tone. We evaluate a range of models on AfriSUD for part-of-speech tagging and dependency parsing including non-transformer baselines, multilingual pretrained encoders, and LLMs. Our results reveal a significant syntax gap, where models still show clear limitations across the nine languages, suggesting that existing architectures may not fully capture the structural diversity of African-language syntax.

23.
arXiv (CS.AI) 2026-06-11

On the Geometry of On-Policy Distillation

arXiv:2606.07082v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is increasingly used to improve large language model reasoning, but its training dynamics remain poorly understood. We characterize the trajectory of OPD updates in parameter space and compare it with supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). A suite of parameter-space diagnostics consistently places OPD in a relaxed off-principal regime: compared with SFT, its updates affect fewer weights and avoid principal directions more strongly, while compared with RLVR, they remain less tightly constrained. Beyond this static localization, OPD exhibits subspace locking: its cumulative updates rapidly enter a narrow low-dimensional channel. Constraining training to the update subspace formed early in training preserves OPD performance but substantially degrades SFT, indicating that the locked subspace is functionally sufficient for OPD. Control experiments further show that sparsifying the update tokens and shifting rollout generation off-policy preserve the rank dynamics, whereas mixing the OPD objective with RLVR changes them. Overall, these results suggest that OPD is not merely an intermediate point between SFT and RLVR, but induces its own update geometry in parameter space.

24.
arXiv (CS.AI) 2026-06-16

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling

arXiv:2605.02427v3 Announce Type: replace Abstract: A recurring pattern in "reasoning without training" is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the bottleneck is locating these modes efficiently at inference time. Power sampling provides a principled way to bias decoding toward such modes by targeting p_theta(x)^alpha with alpha > 1, but practical approximations must account for future-dependent correction factors that determine which prefixes remain promising. We introduce Auxiliary Particle Power Sampling (APPS), a blockwise particle algorithm for approximating the sequence-level power target with a bounded population of partial solutions. APPS propagates hypotheses in parallel using proposal-corrected power reweighting and refines their survival through future-value-guided selection at resampling boundaries. This redistributes finite compute across competing prefixes rather than committing to a single unfolding path, while providing a direct scaling knob in the particle count and predictable peak memory. We instantiate the future-value signal with short-horizon rollouts and also study an amortized variant that replaces rollouts with a lightweight learned selection head. AMore broadly, APPS improves the accuracy–runtime trade-off of training-free decoding, further supporting the view that inference-time power approximation can recover gains often attributed to post-training.

25.
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.