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 (quant-ph) 2026-06-16

Hyperinvariant Spin Network States – An AdS/CFT Model from First Principles

arXiv:2510.06602v2 Announce Type: replace Abstract: We study the existence and limitations of hyperinvariant tensor networks incorporating a local SU(2) symmetry. As discrete implementations of the anti de-Sitter/conformal field theory (AdS/CFT) correspondence, such networks have created bridges between the fields of quantum information theory and quantum gravity. Adding SU(2) symmetry to the tensor network allows a direct connection to spin network states, a basis of the kinematic Hilbert space of loop quantum gravity (LQG). We consider a particular situation where the states can be interpreted as kinematic quantum states for three-dimensional quantum gravity. We show that important aspects of the AdS/CFT correspondence are realized in certain quantum states of the gravitational field in LQG, thus justifying, from first principles, a class of models introduced by [F. Pastawski et al., JHEP 06, 149 (2015)]. We provide examples of hyperinvariant tensor networks, but also prove constraints on their existence in the form of no-go theorems that exclude absolutely maximally entangled states as well as general holographic codes from local SU(2)-invariance. We calculate surface areas as expectation values of the LQG area operator and discuss further possible constraints as a consequence of a decay of correlations on the boundary.

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

Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization

arXiv:2606.16899v1 Announce Type: new Abstract: Matrix based optimizers such as Muon can substantially speed up language model pretraining, but their gains over AdamW are observed to shrink as model size and data scale grow when using standard constant decoupled weight decay. We propose Hyperball, a simple optimizer wrapper that addresses this issue. Given a base optimizer such as Adam or Muon, Hyperball sets the Frobenius norms of weight matrices and their corresponding optimizer updates to fixed constants. On Qwen3 style models up to 1.2B parameters, Muon Hyperball achieves 20–30% token equivalent speedup over weight decay baselines. Hyperball also improves learning rate transfer across widths and depths compared to decoupled weight decay. This method is motivated by prior theory showing that training with weight decay leads to an equilibrium weight norm that only depends on the training hyperparameters. Through this mechanism, the weight decay then decides the angular learning rate, i.e. how fast the direction of the weight matrix changes.

03.
arXiv (math.PR) 2026-06-18

On a class of reflected McKean-Vlasov Stochastic Differential Equations with jumps

arXiv:2606.18433v1 Announce Type: new Abstract: This paper investigates a class of reflected McKean-Vlasov Stochastic Differential Equations driven by both Brownian motion and a compensated Poisson random measure. We establish the existence and uniqueness of solutions and provide moments estimates for the state processes.

04.
arXiv (quant-ph) 2026-06-12

Representation-Induced Symmetry Trapping in Adaptive Variational Quantum Simulations of Multi-Reference Topologies

arXiv:2606.13387v1 Announce Type: new Abstract: Evaluating the trainability of adaptive quantum chemistry algorithms under multi-reference static correlation requires understanding how representation topologies intertwine with molecular geometry. We systematically expose a deep physical dependence on point-group symmetry by evaluating a spin-conserved SUSD operator pool across highly stretched configurations (2 x Re) of asymmetric LiH, symmetric BeH2, and asymmetric H2O. Under asymmetric distortions, the non-local mapping constraints of the Bravyi-Kitaev transformation create an optimization trapping effect–an encodement-locked manifestation of the broader barren plateau crisis. Crucially, by comparing these to the symmetrical stretching baseline of BeH2, we demonstrate that the preservation of point-group symmetry structurally protects the optimization landscape, proving that ansatz symmetry restrictions are necessary but insufficient without accounting for the underlying fermion-to-qubit representation. While current methods rely on numerical pruning to throttle pool sizes, our structural approach establishes that the mapping representation remains a critical factor in maintaining landscape trainability. Furthermore, exploiting structural overlap within our pool, we introduce a covariance-driven, adaptive shot-allocation filter. Diverging from static energy-variance minimization frameworks, our allocation engine operates as a dynamic runtime diagnostic tool. By continuously monitoring the gradient precision threshold epsilon, it aggressively prunes dead symmetry channels and triggers an automated circuit-termination sequence upon detecting representation-induced flat-lined states (dE/dtheta approx 0). This integration of algebraic measurement reuse with topology-aware statistical filtering provides a promising, resource-efficient strategy for executing deep variational algorithms on early fault-tolerant architectures.

05.
arXiv (CS.AI) 2026-06-16

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

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

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

SAM-Deep-EIoU: Selective Mask Propagation for Multi-Object Tracking

Multi-object tracking has a heavy-tailed difficulty distribution: most frames are easy for a lightweight base tracker, while a small fraction are intrinsically hard. Video object segmentation (VOS) models can often preserve identity through the hard frames where the base tracker fails, but they are much more expensive in compute and memory. We propose selective mask propagation, a tracking algorithm that dispatches from a base tracker to a VOS model only on windows where an assignment-uncertainty signal fires. The base tracker's output is modified only when the VOS model makes a confident prediction that contradicts the base tracker's identity assignment; weak or inconclusive predictions preserve the base output. The method is training-free, treats both the base tracker and the VOS model as black boxes, and can benefit from replacing the VOS component with a more capable model. On DanceTrack, selective mask propagation improves three different base trackers. On SportsMOT, where identity preservation is central to sports analytics, SAM3-Deep-EIoU with global track association achieves state-of-the-art performance on the benchmark with 86.8 HOTA.

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

ToolMenuBench: Benchmarking Tool-Menu Filtering Strategies for Reliable and Efficient LLM Agents

arXiv:2606.15508v1 Announce Type: new Abstract: Tool-augmented large language model agents increasingly operate over large tool libraries, but existing evaluations often focus on whether a model can call a tool correctly rather than how the visible tool menu shapes reliability, efficiency, and safety-relevant risk exposure. We introduce ToolMenuBench, a benchmark for evaluating tool-menu construction in multi-step LLM agents. ToolMenuBench varies tool-menu size, distractor type, state-dependent task structure, and risk exposure, and reports both filter-level and downstream agent metrics, including visible-tool count, risky-tool exposure, task success, wrong-tool calls, premature actions, and token usage. In a controlled evaluation across seven model backends, three tool-menu sizes, six filtering methods, and seven evaluation settings, CMTF improves task success from 32.1% under all-tools exposure to 85.7%, while reducing average token usage by roughly 98%. Causal minimal tool filtering achieves the strongest overall tradeoff, reducing visible tools, wrong-tool calls, premature actions, and risky-tool exposure relative to unfiltered exposure, lexical filtering, state-aware filtering, and broader causal-path baselines. ToolMenuBench provides a reusable evaluation framework for studying the agent-interface problem: which tools should be visible, when they should be visible, and under what cost or risk constraints.

08.
arXiv (CS.CV) 2026-06-17

Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations

Multi-task table recognition jointly addresses table structure prediction, cell localization, and cell content recognition within a unified framework. Existing approaches often rely on autoregressive decoders to generate table structures and reuse their hidden states for cell localization and content recognition. This autoregressive generation process can make cell representations order-dependent, degrading global consistency across cells. This paper proposes a structural refinement module that produces order-independent cell features through non-causal attention. This design enables parallel inference of cell contents while conditioning each cell on global context encoded in the refined features. Experiments on two large datasets demonstrate consistent gains in cell localization and end-to-end recognition, while reducing overall inference time by around threefold.

09.
arXiv (CS.LG) 2026-06-16

When to use what Schatten-$p$ norm in deep learning?

arXiv:2606.15268v1 Announce Type: new Abstract: Schatten-$\infty$ based optimizers such as Muon have shown promising empirical performance, but there remains seemingly conflicting observations regarding whether they are beneficial. We resolve this conflict by showing that the conclusion is regime dependent. Even when the objective is smooth in the Schatten-$\infty$ geometry, smaller Schatten-$p$ geometries can be optimal, specifically in the low-dimensional regime, which we show includes Chinchilla scaling. This conclusion follows from a new noise-robust acceleration result for the SODA framework for $p>2$. The same analysis explains why Muon-like methods do not require warmup, why they naturally favor large batches, and yields a batch size scaling rule for arbitrary $p$.

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

Semantic search for 100M+ galaxy images using AI-generated captions

Finding scientifically interesting phenomena through slow manual labeling campaigns severely limits our ability to explore the billions of galaxy images produced by telescopes. In this work, we develop a pipeline to create a semantic search engine from completely unlabeled image data. Our method leverages Vision-Language Models (VLMs) to generate descriptions for galaxy images, then contrastively aligns a pre-trained astronomy foundation model with these embedded descriptions to produce searchable embeddings at scale. We find that current VLMs provide descriptions that are sufficiently informative to train a semantic search model that outperforms direct image similarity search. Our model, AION-Search, achieves state-of-the-art zero-shot performance on finding rare phenomena despite training on randomly selected images with no deliberate curation for rare cases. Furthermore, we introduce a VLM-based re-ranking method that nearly doubles the recall for our most challenging targets in the top-100 results. For the first time, AION-Search enables flexible semantic search for over 100 million galaxy images, enabling discovery from previously infeasible searches, including the identification of 36 new extragalactic stellar stream candidates. More broadly, our work provides an approach for making large, unlabeled scientific image archives semantically searchable, expanding data exploration capabilities in fields from Earth observation to microscopy. The code, data, and app are publicly available at https://github.com/NolanKoblischke/AION-Search

11.
Nature (Science) 2026-06-17

Visualizing the impact of quenched disorder on 2D electron Wigner solids

作者:

Electron Wigner solids (WSs)1–12 provide an ideal system for understanding the competing effects of electron–electron and electron–disorder interactions, a central unsolved problem in condensed matter physics. Progress in this topic has been limited by a lack of single-defect-resolved experimental measurements as well as accurate theoretical tools to enable realistic experiment/theory comparison. Here we overcome these limitations by combining atomically resolved scanning tunnelling microscopy (STM) with neural-quantum-state quantum Monte Carlo (NQS-QMC) simulation of disordered 2D electron WSs to discover new disorder-induced physical regimes of correlated electron behaviour. STM was used to image the electron density (ne)-dependent evolution of electron WSs in gate-tunable bilayer MoSe2 (BL-MoSe2) devices with varying long-range (nLR) and short-range (nSR) disorder densities. These images were compared with NQS-QMC simulations using realistic disorder maps extracted from experiment, thus allowing the roles of different disorder types to be disentangled. We identify two distinct physical regimes for disordered electron WSs that depend on nSR. For nSR ≲ ne, the WS behaviour is dominated by long-range disorder and features extensive mixed solid–liquid phases, a new type of local re-entrant melting/crystallization and prominent Friedel oscillations. By contrast, when nSR ≫ ne, these features are suppressed and a more robust amorphous WS phase emerges that persists to higher ne, highlighting the importance of short-range disorder in this regime. Our work establishes a powerful framework for studying disordered quantum solids through a combined experimental–theoretical approach. A technique combining atomically resolved scanning tunnelling microscopy with neural-quantum-state quantum Monte Carlo simulation of disordered 2D electron Wigner solids establishes a powerful framework to enable the clear identification of two distinct defect-induced disorder regimes.

12.
bioRxiv (Bioinfo) 2026-06-18

novelBGC: An interactive dual-score framework for biosynthetic gene cluster novelty assessment and candidate prioritisation

Genome mining now yields tens of thousands of putative biosynthetic gene clusters (BGCs) per project, yet, separating genuinely novel candidates from rediscoveries of known compounds remains the rate-limiting step before experimental validation. Single-axis prioritisation tools, antiSMASH similarity, BiG-FAM GCF distance, and self-resistance-enzyme (SRE) filters such as ARTS, each surface a different facet of evidence, yet their isolated use systematically over-ranks rediscovery-prone BGCs and overlooks genuinely orphan clusters. We present novelBGC, a web-hosted framework that converts these disparate outputs into two deliberately non-inverse continuous metrics per BGC, a Novelty (N) and a Reference Similarity (RS) score which together define a 2D decision plane that resolves rediscoveries, divergent family members, contig-edge artefacts, and uncharted chemistry with interactive visualisations, with all component weights user-tuneable at submission. Retrospective validation across three independent experimental datasets demonstrates the utility of the framework for candidate prioritization. Within the first 186-BGC SRE-guided cloning study, every confirmed bioactive product fell within the low-to-mid N band whereas 55 high-N (N [≥] 0.50) BGCs were never selected. Moreover, in the other two studies, it correctly prioritised the fully orphan lariocidin BGC of Paenibacillus sp. M2 and the divergent within-family indanopyrrole-A idp BGC of Streptomyces sp. CNX-425. Together, these case studies demonstrate that the joint (N, RS) space facilitates prioritization decisions that are difficult to achieve using any single criterion alone. from identical input data. novelBGC requires no command-line expertise, no local tool installation, and no manual integration of intermediate output formats, addressing a well-documented accessibility barrier for wet-laboratory researchers engaging with genome-mining workflows. novelBGC is freely available at https://project.iith.ac.in/sharmaglab/novelbgc/.

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

Hierarchical Probabilistic Conformal Prediction for Distributed Energy Resources Adoption

arXiv:2411.12193v4 Announce Type: replace-cross Abstract: The rapid growth of distributed energy resources (DERs) presents both opportunities and operational challenges for electric grid management. Accurately predicting DER adoption is critical for proactive infrastructure planning, but the inherent uncertainty and spatial disparity of DER growth complicate traditional forecasting approaches. Moreover, the hierarchical structure of distribution grids demands that predictions satisfy statistical guarantees at both the circuit and substation levels, a non-trivial requirement for reliable decision-making. In this paper, we propose a novel uncertainty quantification framework for DER adoption predictions that ensures validity across hierarchical grid structures. Leveraging a multivariate Hawkes process to model DER adoption dynamics and a tailored split conformal prediction algorithm, we introduce a new nonconformity score that preserves statistical guarantees under aggregation while maintaining prediction efficiency. We establish theoretical validity under mild conditions and demonstrate through empirical evaluation on customer-level solar panel installation data from Indianapolis, Indiana that our method consistently outperforms existing baselines in both predictive accuracy and uncertainty calibration.

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

VOiLA: Vectorized Online Planning with Learned Diffusion Model for POMDP Agents

arXiv:2606.19729v1 Announce Type: cross Abstract: Planning under uncertainty is an essential capability for autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for such a capability. Although POMDP-based planning has advanced significantly, its application to real-world problems is often limited by the difficulty of obtaining faithful POMDP models. We present Vectorized Online planning wIth Learned diffusion model for POMDP Agents (VOiLA), a framework that learns task-agnostic POMDP models for online planning under uncertainty. VOiLA learns transition and observation samplers using conditional diffusion models and learns observation-likelihood models for particle-based belief updates. To enable efficient online planning, the diffusion samplers are distilled into compact feedforward generators and integrated with Vectorized Online POMDP Planner (VOPP), an online POMDP planner designed to leverage GPU parallelization. Experimental results indicate the distillation strategy reduces sampling cost by up to nearly three orders of magnitude, making learned generative POMDP models practical for online planning. Evaluation of VOiLA on three benchmark problems indicate that VOiLA achieves equal or better performance than Recurrent Soft Actor Critic while using less than 10% training data, and generalizes much better to unseen environment configurations. Physical robot evaluation indicates VOiLA uses the models learned using only simulated data and generates a policy that successfully accomplish the task in 10 of 10 runs.

15.
arXiv (CS.CL) 2026-06-16

Learn-to-learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM

Conventional LLMs may suffer from corpus heterogeneity and subtle condition changes. While finetuning can create the catastrophe forgetting issue, application of meta-learning on LLMs is also limited due to its complexity and scalability. In this paper, we activate the meta-signal of $\beta$ within the SwiGLU blocks, resulting in a meta-gating mechanism that adaptively adjusts the nonlinearity of FFN. A hypernetwork is employed which dynamically produces $\beta$ on textual conditions, providing meta-controllability on LLMs. By testing on different condition types such as task, domain, persona, and style, our method outperforms finetuning and meta-learning baselines, and can generalize reasonably on unseen tasks, condition types, or instructions. Our code can be found in https://github.com/AaronJi/MeGan.

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

Sumi: Open Uniform Diffusion Language Model from Scratch

Diffusion models have become a promising alternative to autoregressive models. Among these, uniform diffusion language models (UDLMs) permit any token to be updated at any step, in principle enabling more flexible generation. However, no UDLM has yet been pretrained from scratch at both large parameter scale and large token budget. Both autoregressive modeling and masked diffusion modeling already have capable models at scale that the community can study and build on; uniform diffusion has none. A scratch-pretrained UDLM at scale would provide a clean reference point for studying scaling behavior, generation dynamics, controllability, and trade-offs against established autoregressive and masked diffusion models. To this end, we introduce Sumi ("ink" in Japanese), a fully open 7B uniform diffusion language model pretrained from scratch on 1.5T tokens. Sumi performs competitively with autoregressive models trained at comparable token budgets on knowledge, reasoning, and coding benchmarks, while under-performing on commonsense benchmarks, where our education-heavy data mixture is a likely contributor. We release our model weights, checkpoints, and full training recipe, including a complete specification of the data mixture over publicly available corpora. We hope this release enables the community to study native uniform diffusion at scale and catalyzes work on its as-yet poorly understood aspects.

17.
Nature (Science) 2026-06-10

Daily briefing: Ancient ground squirrels ate like ‘zombies of the Pleistocene’

作者:

Evidence from fossilized poo reveals the diverse diet of ancient ground squirrels. Plus, the science behind the peptide craze and our innate tendency to wander anticlockwise. Evidence from fossilized poo reveals the diverse diet of ancient ground squirrels. Plus, the science behind the peptide craze and our innate tendency to wander anticlockwise.

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

Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language Models

With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under complex personality conditions is essential. This paper introduces explicit personality conditioning and establishes a systematic evaluation framework encompassing single-personality induction, multi-personality induction, and personality switching. Experiments show that personality induction improves image captioning performance but can impair performance on tasks requiring precise reasoning, such as visual question answering (VQA). Balancing and residual effects are observed during multi-trait composition and dynamic switching, indicating that model behavior is co-modulated by both previous and current personality constraints. Existing prompt-based personality induction methods show limited transferability to multimodal settings. Our work reveals the dynamic and complex nature of personality modeling in MLLMs and underscores the need for robust, tailored methods for personality induction and evaluation. The code will be released when the paper is accepted.

19.
bioRxiv (Bioinfo) 2026-06-11

inquiSTR: a toolkit for accurate and efficient population-scale tandem repeat genotyping and analysis

Tandem repeats are highly mutable genomic elements linked to human traits and diseases. Profiling large catalogs of tandem repeats from population-scale long-read sequencing data requires accurate and efficient tools. We introduce inquiSTR, a command-line toolkit for fast genome-wide tandem repeat length genotyping. inquiSTR, with efficient parallel processing and low-memory streaming algorithms, genotypes a genome-wide repeat catalog of 1.78 million loci in less than two minutes. Benchmarking shows high accuracy and significantly faster performance compared to existing tools and truth sets. inquiSTR also provides methods for downstream analyses such as population structure inference, association testing, and outlier detection.

20.
arXiv (CS.LG) 2026-06-11

Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach

arXiv:2606.11738v1 Announce Type: cross Abstract: We study online estimation for high-dimensional generalized linear models with streaming data. First, for the non-distributed setting, we propose a gradient-enhanced surrogate loss that approximates the cumulative loss using only historical summaries, which modifies and improves upon the existing renewable estimation approach for the same model in the high-dimensional setting, and removes the batch-number constraint in previous studies. We then extend the method to distributed streaming data under the master-client architecture, where batches are partitioned across sites and only summaries (gradient vectors) are exchanged. Instead of directing applying the popular method of Jordan et al. (2019) to the surrogate quadratic loss, our adjusted approach does not require the clients to compute the full surrogate loss. We derive non-asymptotic error bounds under the high-dimensional scaling, without the stringent constraint on the number of batches in the previous studies. Simulation results under linear and logistic models, together with a real-data application, show improved accuracy over existing renewable estimators.

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

When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting

A model can learn that the piano piece Für Elise is calm and reflective by listening to the audio or by reading a text description, but does it matter which route that knowledge took when it is later at risk of being forgotten? Forgetting research in multimodal models measures what knowledge is lost under adaptation, yet has not asked whether acquisition route affects how easily that knowledge is forgotten. We call this untested premise the Pathway-Invariant Assumption. Music understanding enables a clean test because a music clip and a canonical text description can be aligned to the same perceptual content, allowing the same knowledge unit to enter a model through listening or reading while the target remains fixed. Across multiple architecturally distinct audio-language models, we observe a consistent asymmetry: text-pathway knowledge is forgotten more than matched audio-pathway knowledge under identical adaptation pressure. To attribute this effect to route rather than confounds, we introduce the Paired Pathway Controlled Protocol (PPCP), a three-phase design that establishes matched pathway baselines, activates both pathways under symmetric supervision on the same knowledge pool, and applies identical forgetting pressure to both pathways. The gap is stable across models and gain-controlled analyses, persists when contradictory overwrite is replaced by correct-label cross-domain learning, remains under single-modality pressure, and is not removed by lightweight replay. Two independent routing-depth controls confirm that the effect is not explained by architectural depth, pointing to input representation as the dominant factor. Under PPCP, our results demonstrate that forgetting is highly route-dependent, establishing acquisition route as a new analytical dimension for forgetting research and multimodal system design.

22.
arXiv (CS.CL) 2026-06-16

Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations

In-context learning (ICL) is the standard method for low-resource classification, yet its efficacy in specialized domains remains largely unexplored. We address the challenge of classifying semantically complex, multi-party B2B conversations, where traditional ICL encounters significant limitations, especially as context length increases due to the concatenation of multiple few-shot examples. We introduce the \texttt{Call Playbook} dataset, featuring five classification tasks derived from real-world B2B conversations targeting core sales concepts. To bridge the gap between performance and practical utility, we propose novel knowledge extraction methods that distill verbose examples into compact, interpretable representations of structured classification criteria and precise task descriptions. Our approach achieves a 99\% reduction in token usage and improves macro-averaged AUC by up to 7\% over traditional ICL. Notably, it remains robust as context grows, unlike advanced token compression baselines which degrade by over 9 F1 points. Importantly, our framework enables direct refinement of classification logic, addressing critical needs for transparency, efficiency, and user interaction in real-world NLP applications.

23.
arXiv (CS.LG) 2026-06-17

Performance-Driven Environment Abstraction with Multi-Timescale Learning

arXiv:2606.17377v1 Announce Type: new Abstract: We study performance-driven environment abstraction for decision-making in large Markov decision processes. Rather than preserving geometric or topological structure, we seek abstractions that directly optimize decision quality. We model abstraction as a controlled approximation obtained by aggregating the state space and enforcing a shared action distribution within each aggregated state. For a fixed partition, we establish a performance guarantee that separates value-function approximation error from the loss introduced by action sharing. Guided by this analysis, we develop a multi-timescale reinforcement learning framework that jointly adapts the policy and a tree-structured environment abstraction. The resulting algorithm refines and coarsens regions of the state space based on Q-value discrepancies, balancing performance against abstraction size and complexity. Empirical results demonstrate substantial state compression, improved sample efficiency, and faster replanning compared to actor-critic baselines.

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

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents

Long-horizon tool-use reinforcement learning can learn from outcome verification, but its trajectory-level advantage is broadcast across many reasoning, API, and answer tokens. Self-distillation promises a denser signal by reusing a policy's own rollouts or a privileged teacher. We show, however, that direct token-level self-distillation can silently destroy tool use: it rehearses teacher behavior without knowing which actions the verifier rewards, so useful skills and harmful shortcuts are amplified together. We introduce Sibling-Guided Credit Distillation (SGCD), which uses distillation for credit assignment rather than as a competing actor loss. Dynamic sampling produces mixed successful and failed sibling rollouts; an external LLM summarizes their contrast into a training-only stepwise credit reference; dense teacher/student divergence drives credit reassignment; and bounded detached credit weights reshape GRPO token advantages. The deployed student sees no external LLM, sibling evidence, or oracle. Across AppWorld and $\tau^3$-airline, SGCD improves over matched GRPO comparators: AppWorld TGC $42.9 \to 45.6$ on test_normal and $24.7 \to 27.0$ on test_challenge, and $\tau^3$-airline pass@1 $0.583 \to 0.602$.

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

Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies

arXiv:2602.18291v2 Announce Type: replace Abstract: Online Multi-Agent Reinforcement Learning (MARL) is a prominent framework for efficient agent coordination. Crucially, enhancing policy expressiveness is pivotal for achieving superior performance. Diffusion-based generative models are well-positioned to meet this demand, having demonstrated remarkable expressiveness and multimodal representation in image generation and offline settings. Yet, their potential in online MARL remains largely under-explored. A major obstacle is that the intractable likelihoods of diffusion models impede entropy-based exploration and coordination. To tackle this challenge, we propose among the first \underline{O}nline off-policy \underline{MA}RL framework using \underline{D}iffusion policies (OMAD) to orchestrate coordination. Our key innovation is a relaxed policy objective that maximizes scaled joint entropy, facilitating effective exploration without relying on tractable likelihood. Complementing this, within the centralized training with decentralized execution (CTDE) paradigm, we employ a joint distributional value function to optimize decentralized diffusion policies. It leverages tractable entropy-augmented targets to guide the simultaneous updates of diffusion policies, thereby ensuring stable coordination. Extensive evaluations on MPE and MAMuJoCo establish our method as the new state-of-the-art across $10$ diverse tasks, demonstrating a remarkable $2.5\times$ to $5\times$ improvement in sample efficiency.