Explore the Frontier of Global Academia

01.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14249

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Authors:

Tingyang Chen↗Shuo Lu↗Kang Zhao↗Weicheng Meng↗Hanlin Teng↗Tianhao Li↗Chao Li↗Xule Liu↗Jian Liang↗Zhizhong Zhang↗Yuan Xie↗Heng Qu↗…

arXiv:2606.14249v1 Announce Type: new Abstract: AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

Read & Discuss → View Source →

02.

arXiv (CS.CL) 2026-06-24 DOI: arXiv:2606.24841

Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models

Authors:

Ahmad Pouramini↗Hesham Faili↗

Prompt-based learning has emerged as a dominant paradigm in natural language processing. This study explores the impact of diverse pre-training objectives on the performance of encoder-decoder pre-trained language models across generation and question answering tasks, with a focus on commonsense knowledge retrieval and completion. We highlight the benefits of incorporating multiple objectives during both pre-training and fine-tuning stages. We introduce the Match Task to Objective (MTO) framework and methods for determining the appropriate objective for a given task. This framework offers automated methods to prepare task-related data for adaptation through unsupervised training, based on the identified objective. In the fine-tuning stage, we design novel templates that align with the objectives of the pre-training and adaptation stages. When aligned with task requirements, these strategies can achieve a performance gain of over 120\% compared to conventional methods in few-shot settings. They significantly outperform related works in few-shot settings and exceed the baseline even in full-dataset scenarios. Furthermore, we extend this approach to include prompt-tuning methodologies, providing guidance for more effective soft prompt engineering and optimization. Our strategies significantly enhance prompt-tuning performance as well. These insights hold substantial value, precisely guiding the selection and optimization of models customized for specific tasks. Code is available at https://github.com/puraminy/MTO/

Read & Discuss → View Source →

03.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.20113

When Does Streaming Tool Use Help? Characterizing Tool-Intent Stabilization in Streaming Retrieval-Augmented Generation

Authors:

Elroy Galbraith↗

Streaming Retrieval-Augmented Generation (Streaming RAG) reduces user-perceived latency by issuing tool queries in parallel with ongoing user input, before the utterance is complete. Reported gains are aggregate, yet the mechanism's benefit is fundamentally query-intrinsic: speculation can only help when the correct tool query becomes determinable before the user stops speaking or typing. We isolate and measure this property – tool-intent stabilization, the point in the input stream at which a speculative query's retrieval converges to the answer-bearing result. On the CRAG benchmark (1371 validation questions) we (i) measure the distribution of stabilization, (ii) derive a model-agnostic bound H on the portion of tool latency that can be hidden behind the user's remaining input, as a function of tool latency L and input cadence {\delta}, (iii) validate against a working streaming pipeline that realized savings meet or exceed this bound, and (iv) identify which query properties predict early versus late stabilization. The study requires no model training and runs on commodity CPU hardware. We find that at a realistic operating point (L=600ms, {\delta}=3w/s, {\theta}=0.8), 73.9% of queries across the full benchmark admit substantial latency hiding – a blended figure that mixes sufficiency stabilization on the 21.3% of questions where gold evidence is verbatim-present and BM25-retrievable (95.2% streamable on this favorable slice) with a grounding-free top-1-settling fallback on the remainder. On the favorable slice, {\phi}_suf is bracketed to [0.26, 0.281] by exact and relaxed grounding – both early. Question type produces a significant but coarse early/late split (Kruskal-Wallis p=0.017, epsilon^2=0.04), directly informing when a learned speculative trigger is worth its cost.

Read & Discuss → View Source →

04.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2310.09149

Structured Approximations of Measures

Authors:

Keaton Hamm↗Varun Khurana↗

arXiv:2310.09149v3 Announce Type: replace-cross Abstract: We study the approximation of probability measures in the Wasserstein-$p$ distance by structured classes of approximators, motivated by applications in imaging, machine learning, and physical measurement under sensor constraints. We obtain three sets of results. First, for measures with densities bounded away from zero on a bounded Lipschitz domain $\Omega$, we prove that any approximation scheme for functions in $\mathrm{L}_p(\Omega)$ transfers, with linear rate, to a corresponding approximation scheme for measures in $\mathrm{W}_p(\Omega)$. The argument applies a theorem of Bogovskii on regularity of solutions to the continuity equation in the Benamou-Brenier formulation of optimal transport. We exhibit concrete approximation schemes (polynomials, shift-invariant spaces, cardinal interpolation with radial basis functions, kernel density estimators, and piecewise approximations on nonuniform Voronoi partitions) that fit the framework. As a matter of independent interest, we prove a negative Sobolev lower bound that generalizes existing bounds from $p=2$ to all $p\in(1,\infty)$. We also consider deterministic bounds for discrete approximations to arbitrary measures in terms of the mesh norm of a quasi-uniform set of points. We specialize these bounds to show that compactly supported measures admit a deterministic $N$-term approximation $\mu_N$ such that $\mathrm{W}_p(\mu,\mu_N) = O(N^{-\frac{1}{d}})$ for all $d\geq 1$, which matches the asymptotic optimal quantizer rate. We also extend these results to non-compactly supported measures with appropriate tail decay.

Read & Discuss → View Source →

05.

medRxiv (Medicine) 2026-06-11 DOI: HASH:8e5207761f742b313a5b124308162cf5

PCRAgent: A Multi-Agent Framework for Transforming Noisy clinical conversations into Structured Pre-Consultation Medical Records and Reusable Clinical Data Resources

Authors:

Zhang↗Zhao↗Tang↗Xing↗Li↗Qiu↗

In primary care and outpatient settings, clinically important patient information is often embedded in fragmented, ambiguous, repetitive, and noisy communication between physicians and patients. This limits physicians ability to obtain a clear preconsultation overview of symptoms, history of present illness, and visit intent, while also preventing real world clinical dialogues from being reused in hospital information systems and medical artificial intelligence applications. To address this challenge, we developed PCRAgent, a centrally coordinated multi agent framework for preconsultation clinical information organization. Guided by physician inquiry logic, PCRAgent identifies, extracts, corrects, and standardizes patient-reported information from noisy consultations. Its coordinated modules including error detection, semantic editing, output control, contextual memory, and intent recognition enable robust parallel handling of spelling errors, repetitions, grammatical inconsistencies, medical ambiguities, and non-medical interference. A traceable edit list records intermediate corrections and context, allowing iterative refinement without redundant modifications. PCRAgent generates two complementary outputs. One is a PreConsultation Clinical Report for rapid physician review. The other is a Structured Clinical Conversation Dataset for hospital data construction and downstream AI applications. In evaluations using 220000 strongly perturbed consultations, PCRAgent maintained high robustness, achieving a clinical information accuracy of 4.99 out of 5 and key element completeness of 5 out of 5, outperforming GPT4o. Expert review of Chinese and English dialogues confirmed high clinical accuracy of 4.85 out of 5 and high safety of 4.79 out of 5. Multicenter validation in real-world outpatient workflows further demonstrated practical utility. These findings indicate that PCRAgent can efficiently transform noisy and unstructured consultations into physician ready reports and AI ready structured data, improving outpatient efficiency, reducing cognitive burden, ensuring information completeness, supporting precise decision-making, and enabling high-quality reuse of clinical data.

Read & Discuss → View Source →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.13602

EpiBench: Verifiable Evaluation of AI Agents on Epigenomics Analysis

Authors:

Harihara Muralidharan↗Reema Baskar↗Soo Hee Lee↗Tim Proctor↗Kenny Workman↗

arXiv:2606.13602v1 Announce Type: new Abstract: We introduce EpiBench, a verifiable benchmark for short-horizon epigenomics analysis. EpiBench evaluates whether agents can make well-defined analysis decisions from realistic workflow states and return deterministically gradable answers. The benchmark includes 106 evaluations across CUT\&Tag/CUT\&RUN, ATAC-seq, ChIP-seq, and DNA methylation workflows. Across 5,088 valid trajectories from 16 model-harness pairs, no system passed a majority of attempts: GPT-5.5 / Pi led at 45.0\% (143/318 attempts; 95\% confidence interval (CI), 36.3–53.7), followed by GPT-5.5 / OpenAI Codex at 39.9\% (127/318 attempts; 95\% CI, 31.6–48.3). Claude Opus 4.8 Max / Pi and GPT-5.4 / Pi each passed 39.0\% (124/318 attempts; 95\% CI, 30.2–47.8 and 31.0–47.0, respectively). Performance varies across assay types, and many failed runs still contain parts of the correct answer. Agents often found the right files and computed useful intermediate results, but failed when the task required deeper, assay-specific scientific judgment.

Read & Discuss → View Source →

07.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2602.05413

SciDef: Datasets and Tools for Automated Definition Extraction from Scientific Literature with LLMs

Authors:

Filip Ku\v{c}era↗Christoph Mandl↗Isao Echizen↗Radu Timofte↗Timo Spinde↗

Scientific concepts are often defined inconsistently across papers, making it difficult to compare findings, reuse terminology, and build reliable downstream resources. We present SciDef, a resource suite for scientific definition extraction. The suite contains DefExtra, a benchmark of 268 human-validated author-stated definitions from 75 academic papers; DefSim, 60 human-labeled definition-pair similarity judgments; and an open LLM-based pipeline for PDF preprocessing, chunking, definition extraction, prompt optimization, and evaluation. We validate the resources by benchmarking 16 language models across prompting strategies and chunking schemes. The strongest set-level configuration achieves a score of 0.397, while the highest-coverage configuration matches at least one prediction to 86.4% of gold definitions but over-generates candidate definitions. We further show that an NLI-based matching metric agrees strongly with human DefSim judgments. These results position SciDef as a reusable benchmark and tooling layer for definition-centric literature analysis, while highlighting relevance-aware filtering as the key bottleneck for fully automatic definition extraction. Code & datasets are available at https://github.com/Media-Bias-Group/SciDef.

Read & Discuss → View Source →

08.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.20212

CzechDocs: A Multiway Parallel Dataset of Formatted Documents for Minority Languages in Czechia

Authors:

Josef Jon↗Ond\v{r}ej Bojar↗

We present CzechDocs, a multiway parallel dataset of formatted documents (HTML, DOCX, and PDF) covering Czech and minority languages used in Czechia-primarily Ukrainian and English, with smaller portions of Vietnamese, Russian and other languages. The dataset is designed to support the evaluation of machine translation systems that aim to preserve document formatting during translation. We provide a comparison of the most common approaches to format-preserving machine translation on a validation subset of the dataset. This validation split, together with the evaluation toolkit, is publicly released for further research. A held-out test split will be reserved for a future shared task focused on document-level translation with formatting preservation.

Read & Discuss → View Source →

09.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2606.17175

Self-Generated Error Training for Token Editing in Diffusion Language Models

Authors:

Lin Yao↗

Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains this editor on random vocabulary corruptions, but at inference the editor sees the model's own fluent, high-confidence draft errors instead. We study this training-inference mismatch and propose self-generated T2T, which performs a no-gradient draft pass, fills masked positions with predicted tokens, and supervises recovery in a second pass under these self-generated corruptions. We implement the update as a short LoRA continued-pretraining pass on LLaDA2.1-mini and evaluate on several benchmarks under the official Q-Mode T2T procedure with unchanged inference parameters. The method generally improves accuracy while reducing T2T edit intensity, mitigating failure modes such as final-digit transcription errors after otherwise correct reasoning and excessive self-correction before short factual answers.

Read & Discuss → View Source →

10.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2604.16592

Human Cognition in Machines: A Unified Perspective of World Models

Authors:

Timothy Rupprecht↗Pu Zhao↗Amir Taherin↗Arash Akbari↗Arman Akbari↗Yumei He↗Tooba Imtiaz↗Sean Duffy↗Juyi Lin↗Yixiao Chen↗Rahul Chowdhury↗Enfu Nan↗…

This report of world models distinguishes prior works by the cognitive functions they innovate. Many works claim an almost human-like cognitive capability in their world models. To evaluate these claims requires a proper grounding in first principles from human and machine cognition theory. In moving towards human-like world models we present a conceptual unified framework for world models that fully incorporates all the cognitive functions (i.e., memory, perception, language, reasoning, imagining, motivation, and metacognition) and identify gaps in existing research as a guide for future states of the art. In particular, we find that motivation (especially intrinsic motivation) and metacognition remain drastically under-researched, and we propose concrete directions to address these gaps informed by active inference and global workspace theory. We also introduce epistemic world models, a new category encompassing agent frameworks for scientific discovery that operate over structured knowledge. Our taxonomy, applied to video, embodied, and epistemic world models, suggests research directions where prior taxonomies have not.

Read & Discuss → View Source →

11.

arXiv (CS.CV) 2026-06-18 DOI: arXiv:2606.18610

SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation

Authors:

Wei-Cheng Tseng↗Gashon Hussein↗Yuzhu Dong↗Allen Z. Ren↗Lucy X. Shi↗XuDong Wang↗Sergey Levine↗Zhaoshuo Li↗Jinwei Gu↗Florian Shkurti↗Ming-Yu Liu↗Quan Vuong↗…

Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer a scalable alternative by simulating policy rollouts. Autoregressive rollouts accumulate compounding errors, observations across multiple camera views must remain mutually consistent, and the evaluator must generalize to policies whose behaviors lie outside the training distribution. We address these challenges with SC3-Eval, a self-consistent video generation recipe that adapts a pre-trained video foundation model into an accurate policy evaluator by enforcing three complementary forms of consistency. First, forward-inverse dynamics consistency jointly trains the model to predict frames from actions and to recover actions from frames, anchoring generated rollouts to a physically plausible action manifold and counteracting the drift a forward-only model cannot penalize. Second, cross-view consistency trains the model to inpaint each camera view from the other, keeping the multi-camera observation coherent over long rollouts without any explicit memory mechanism. Third, test-time consistency reuses the inverse dynamics mode at inference as a per-action-chunk uncertainty signal that terminates rollouts whose generated frames drift away from the requested actions. We also demonstrate SC3-Eval rollouts reproduce the failure modes that policies exhibit in real-world rollouts, supporting fine-grained diagnostic comparison rather than aggregate ranking alone. Across seven real-world vision-language-action policies, SC3-Eval attains a closed-loop Pearson correlation of $0.929$ and MMRV of $0.119$, outperforming three strong prior video-model-based baselines, and generalizes to new tasks.

Read & Discuss → View Source →

12.

arXiv (CS.LG) 2026-06-25 DOI: arXiv:2408.01273

Certified Robust Invariant Polytope Training in Neural Controlled ODEs

Authors:

Akash Harapanahalli↗Samuel Coogan↗

arXiv:2408.01273v3 Announce Type: replace Abstract: We propose a framework for training neural network controllers with certified robust forward invariant polytopes. First, we parameterize a family of lifted control systems in a higher dimensional space, where the original neural controlled system evolves on an invariant subspace of each lifted system. We use interval analysis and neural network verifiers to further construct a family of lifted embedding systems, carefully capturing the knowledge of this invariant subspace. If the vector field of any lifted embedding system satisfies a sign constraint at a single point, then a certain convex polytope of the original system is robustly forward invariant. Treating the neural network controller and the lifted system parameters as variables, we propose an algorithm to train controllers with certified forward invariant polytopes in the closed-loop control system. Through two examples, we demonstrate how the simplicity of the sign constraint allows our approach to scale with system dimension to over $50$ states, and outperform state-of-the-art Lyapunov-based sampling approaches in runtime.

Read & Discuss → View Source →

13.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13735

VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation

Authors:

Yijun Shen↗Minghao Shao↗Yichen Zhao↗Zhuoyan Yu↗Boyuan Chen↗Yik-Cheung Tam↗Muhammad Shafique↗

arXiv:2606.13735v1 Announce Type: cross Abstract: Large Language Models (LLM) have shown impressive capabilities in Register Transfer Level (RTL) code generation, particularly for Verilog. However, evaluating their performance with other Hardware Description Languages (HDL), especially VHDL, remains limited although its distinct language characteristics, such as stricter semantic rules, introduce evaluation considerations that differ from Verilog. This lack of coverage restricts fully understanding of how well current models generalize across hardware design languages with differing structures and semantics. To address this gap, we introduce VHDLSuite, a benchmark-centered infrastructure for scalable VHDL generation evaluation, integrating automated benchmark synthesis, executable validation, and multi-model diagnostic analysis. First, we propose a data pipeline that automatically converts Verilog designs and their accompanying testbenches into executable VHDL benchmark instances, followed by VUnit/GHDL-based validation to ensure each released task is compilable, runnable, and consistently checkable in the VHDL environment. Second, we introduce VHDLBench, a benchmark with over 200 VHDL problems with complete and validated testbenches across a wide range of complexity levels. Third, we extensively evaluate cutting-edge LLMs and uncover key challenges specific on LLM-aided VHDL generation. Our findings provide important insights and support future work in multi-language hardware design automation.Our data pipeline, benchmark, and evaluation framework will be open-sourced.

Read & Discuss → View Source →

14.

arXiv (CS.CV) 2026-06-15 DOI: arXiv:2606.14383

IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products

Authors:

Haonan Qi↗Jin Cao↗Yongqi Zhang↗Xintong Wang↗Weidong Tang↗Bin Chen↗Chengfu Huo↗Haojun Pan↗Hengyu You↗Jing Li↗Yingde Wang↗Liang Ding↗…

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction – recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86–94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15–34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

Read & Discuss → View Source →

15.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2603.02668

SorryDB: Can AI Provers Complete Real-World Lean Theorems?

Authors:

Austin Letson↗Leopoldo Sarra↗Auguste Poiroux↗Oliver Dressler↗Paul Lezeau↗Dhyan Aranha↗Frederick Pu↗Aaron Hill↗Miguel Corredera Hidalgo↗Julian Berman↗George Tsoukalas↗Lenny Taelman↗…

arXiv:2603.02668v2 Announce Type: replace Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world formalization projects on GitHub. Unlike existing static benchmarks, often composed of competition problems, hillclimbing the SorryDB benchmark will yield tools that are aligned to the community needs, more usable by mathematicians, and more capable of understanding complex dependencies. Moreover, by providing a continuously updated stream of tasks, SorryDB mitigates test-set contamination and offers a robust metric for an agent's ability to contribute to novel formal mathematics projects. We evaluate a collection of approaches, including generalist large language models, agentic approaches, and specialized symbolic provers, over a selected snapshot of 1000 tasks from SorryDB. We show that current approaches are complementary: even though an agentic approach based on Gemini Flash is the most performant, it is not strictly better than other off-the-shelf large-language models, specialized provers, or even a curated list of Lean tactics.

Read & Discuss → View Source →

16.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12896

PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent

Authors:

Junfeng Guo Heng Huang↗

arXiv:2606.12896v1 Announce Type: cross Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration. In particular, recent work has revealed that RL agents are vulnerable to backdoor attacks, where a victim agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing backdoor defenses for RL either require access to the agent's internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL agents, we propose \texttt{PolicyGuard}, a test-time step-level backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.

Read & Discuss → View Source →

17.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15033

Cloze: An Open Research Platform for Studying Human-AI Conversations in Mental Health Contexts

Authors:

Matthew Flathers↗Francesco Cipriani↗John Torous↗

Cloze is an open-source web platform for conducting controlled, monitored studies of human-AI conversation in mental health research contexts. Consumer large language model (LLM) products such as ChatGPT, Claude, and Gemini are built for individual productivity, and offer researchers little experimental control, inconsistent data export, and no shared safety scaffolding that holds across providers. Cloze gives research teams a single environment in which they configure which models participants converse with, how the AI is instructed, how conversations are scheduled over time, and which safety constraints apply unconditionally, while every message is captured with full provenance (model version, prompt configuration, timing). The platform currently supports OpenAI, Anthropic, Google, and locally hosted open-weight models served through Ollama behind a unified interface, and runs in the cloud or fully on premises so that participant data need never leave an institution. Cloze is research infrastructure for building an evidence base on human-AI interaction in mental health contexts. It is not a therapeutic product.

Read & Discuss → View Source →

18.

arXiv (CS.CV) 2026-06-24 DOI: arXiv:2606.24068

ObsGraph: Hierarchical Observation Representation for Embodied Reasoning and Exploration

Authors:

Taekbeom Lee↗Youngseok Jang↗Jeonghwa Heo↗Jeongjun Choi↗H. Jin Kim↗

Embodied reasoning and exploration are increasingly considered crucial abilities for robots operating in complex and unfamiliar environments. To accomplish tasks in such settings, an agent must identify and acquire the information necessary for the task through exploration. We propose ObsGraph, an observation-centric hierarchical scene graph that unifies scene representation, retrieval, and exploration. It retains visual evidence and organizes it into room-view-object layers: rooms provide coarse semantic anchors, views preserve contextual object covisibility, and objects store fine-grained details. On top of this representation, we perform coarse-to-fine hierarchical retrieval under a bounded budget, and crucially use retrieval outcomes to structure the exploration candidate space–activating room-level exploration, view refinement, or frontier exploration–thereby tightly coupling representation, retrieval, and adaptive multi-scale exploration. Experiments across embodied reasoning and exploration benchmarks demonstrate improved success and efficiency, highlighting the benefits of structured scene representation and more targeted information gathering driven by identified evidence gaps.

Read & Discuss → View Source →

19.

PLOS Medicine 2026-05-21 DOI: HASH:cc1df30b9c3ada10bb266853412aeaae

Novel symptoms associated with eclampsia could improve detection and save lives

Authors:

Alice Beardmore-Gray↗

by Alice Beardmore-Gray, Andrew Shennan Eclampsia is a life-threatening complication of pre-eclampsia, yet remains difficult to predict. In this Perspective, Alice Beardmore-Gray and Andrew Shennan highlight a recent study that identifies 10 novel prodromal symptoms of eclampsia, with potential to better predict which women are at risk and therefore reduce delays in intervention.

Read & Discuss → View Source →

20.

arXiv (CS.CL) 2026-06-16 DOI: arXiv:2606.15412

Few-Shot Biomedical Relation Extraction with Large Language Models: A Viable Alternative to Supervised Learning?

Authors:

Jakob Mraz↗Toma\v{z} Curk↗Bla\v{z} Zupan↗

Biomedical relation extraction (BioRE) is a key step in transforming biomedical literature into structured knowledge. However, most existing approaches rely on supervised models trained on costly annotated datasets, limiting their scalability and adaptability across relation types and domains. We investigate few-shot BioRE using prompt-based learning with large language models (LLMs) and compare two task formulations: pairwise classification, which predicts relations for individual entity pairs, and joint generation, which extracts multiple relations in a single model call. Experiments on the BioREDirect dataset reveal a clear precision-recall trade-off. Pairwise classification achieves higher recall, whereas joint generation is more precise and computationally efficient. The best-performing model achieves a micro-F1 score of 0.44, substantially outperforming previous few-shot results (0.34) while remaining below the supervised baseline (0.56). Much of this gap is attributable to a single ambiguously defined relation type. When evaluated using macro-F1, which better captures performance across relation types in an imbalanced setting, prompt-based approaches outperform the supervised baseline (0.45 vs. 0.38), particularly on rare relation types. These findings highlight the potential of LLMs for BioRE in low-resource settings and underscore the importance of well-defined relation schemas.

Read & Discuss → View Source →

21.

arXiv (CS.AI) 2026-06-19 DOI: arXiv:2602.04396

LoRDO: Distributed Low-Rank Optimization with Infrequent Communication

Authors:

Andrej Jovanovi\'c↗Alex Iacob↗Mher Safaryan↗Ionut-Vlad Modoranu↗Lorenzo Sani↗William F. Shen↗Xinchi Qiu↗Dan Alistarh↗Nicholas D. Lane↗

arXiv:2602.04396v2 Announce Type: replace-cross Abstract: Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication requirements of optimizer states. Low-rank optimizers can alleviate these constraints; however, in the local-update regime, workers lack access to the full-batch gradients required to compute low-rank projections, which degrades performance. We propose $\texttt{LoRDO}$, a principled framework unifying low-rank optimization with infrequent synchronization. We first demonstrate that, while global projections based on pseudo-gradients are theoretically superior, they permanently restrict the optimization trajectory to a low-rank subspace. To restore subspace exploration, we introduce a full-rank quasi-hyperbolic update. $\texttt{LoRDO}$ achieves near-parity with low-rank $\texttt{DDP}$ in language modeling and downstream tasks at model scales of $125$M–$720$M, while reducing communication by $\approx 10 \times$. Finally, we show that $\texttt{LoRDO}$ improves performance even more in very low-memory settings with small rank/batch size.

Read & Discuss → View Source →

22.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2606.11326

DarkVGGT: Seeing Through Darkness Using Thermal Geometry without Daylight Tax

Authors:

Minseong Kweon↗Wenyuan Zhao↗Nuo Chen↗Lulin Liu↗Huiwen Han↗Zihao Zhu↗Srinivas Shakkottai↗Chao Tian↗Zhiwen Fan↗

Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation from image streams. However, their reliance on visible-light appearance makes them vulnerable in dark and low-visibility environments, where RGB cues are severely degraded and geometric evidence becomes ambiguous. To address this challenge, we propose DarkVGGT, an RGB-T feed-forward geometry framework that uses physics-aware thermal modeling for robust 3D estimation in low-light scenes. DarkVGGT introduces two complementary modules. First, physics-inspired thermal factorization extracts emissive-dominant, geometry-consistent thermal cues while isolating sparse reflective residuals that may introduce geometric ambiguity. Second, geometry-shared thermal routing isolates modality-invariant geometric structures from thermal-specific patterns, selectively injecting reliability-aware structural guidance into the RGB stream. Together, these components enable accurate thermal-informed geometry estimation under degraded RGB conditions while largely preserving performance in well-lit environments. Experiments on low-visibility RGB-T benchmarks demonstrate consistent improvements in both depth and camera pose estimation over existing feed-forward geometry baselines.

Read & Discuss → View Source →

23.

arXiv (CS.CV) 2026-06-25 DOI: arXiv:2604.07904

Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency

Authors:

Mingqing Xiao↗Yansen Wang↗Dongqi Han↗Caihua Shan↗Dongsheng Li↗

Spatiotemporal neural dynamics and oscillatory synchronization are widely implicated in biological information processing and have been hypothesized to support flexible coordination such as feature binding. By contrast, most deep learning architectures represent and propagate information through activation values, neglecting the joint dynamics of rate and phase. In this work, we introduce Kuramoto oscillatory Phase Encoding (KoPE) as an additional, evolving phase state to Vision Transformers, incorporating a neuro-inspired synchronization mechanism to advance learning efficiency. We show that KoPE can improve training, parameter, and data efficiency of vision models through synchronization-enhanced structure learning. Moreover, KoPE benefits tasks requiring structured understanding, including semantic and panoptic segmentation, representation alignment with language, and few-shot abstract visual reasoning (ARC-AGI). Theoretical analysis and empirical verification further suggest that KoPE can accelerate attention concentration for learning efficiency. These results indicate that synchronization can serve as a scalable, neuro-inspired mechanism for advancing state-of-the-art neural network models. Code is avaliable at https://github.com/microsoft/Neuro-inspired_Phase_Encoding.

Read & Discuss → View Source →

24.

arXiv (math.PR) 2026-06-16 DOI: arXiv:2606.16487

Logarithmic Large Deviations for Heavy-Tailed Sums

Authors:

Jos\'e M. Zapata↗

arXiv:2606.16487v1 Announce Type: new Abstract: We establish logarithmic large-deviation bounds for sums of independent nonnegative random variables with regularly varying tails. The normalization is chosen at the extreme-value scale and the speed is $\log n$. In contrast with Cramér's theorem, the resulting rate function is determined only by the tail index. The proof transfers a maximum large-deviation principle to sums in the one-big-jump region.

Read & Discuss → View Source →

25.

arXiv (CS.AI) 2026-06-24 DOI: arXiv:2606.23740

Weight-Space Geometry of Offline Reasoning Training

Authors:

Aleksandr Nikolich↗Igor Kiselev↗Vladimir Platonov↗Karina Romanova↗

arXiv:2606.23740v1 Announce Type: cross Abstract: Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill reasoning from large teachers into smaller students, and are typically compared on downstream accuracy alone. We ask whether they are mechanistically distinct or converge to a similar weight update. Training six methods (SFT, RFT, DFT, RIFT, Offline GRPO, DPO) on identical math rollouts from a single base model (Qwen3-4B) with attention-only LoRA, we analyze the resulting deltas via cosine similarity, principal-angle subspace analysis, linear mode connectivity, and CKA. We observe: (i) SFT, RFT, and RIFT have nearly colinear weight deltas (cosine >= 0.97, top-1 principal angle ~7 deg median over 144 modules) and comparable GSM8K accuracy (87-88%, n=1319; pairwise McNemar p >= 0.15); (ii) DFT diverges further in direction than any reward-weighted method despite using the same data; (iii) Offline GRPO adds a substantial component orthogonal to the SFT direction (~67% globally, up to ~86% in late layers) while staying in the SFT loss basin; (iv) DPO sits in a near-orthogonal subspace, shows a mode-connectivity barrier, and collapses late-layer CKA to ~0.46. DPO also reaches the highest accuracy in our protocol on both GSM8K (93.5%, McNemar p < 10^-9 vs. each other method) and AIME26 (30.0% vs. 3.3-10.0%); its training uses a 10x smaller learning rate than the others (the standard convention), so the update-norm and accuracy gaps reflect loss-function and optimizer choices jointly, and a learning-rate-matched DPO comparison is left for future work.

Read & Discuss → View Source →