×

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.

Authors: Ryan ×
Shuffle
01.
arXiv (quant-ph) 2026-06-16

Chiral Lattice Gauge Theories from Symmetry Disentanglers

arXiv:2601.04304v2 Announce Type: replace-cross Abstract: We propose a Hamiltonian framework for constructing chiral gauge theories on the lattice based on symmetry disentanglers: constant-depth circuits of local unitaries that transform not-on-site symmetries into on-site ones. When chiral symmetry can be realized not-on-site and such a disentangler exists, the symmetry can be implemented in a strictly local Hamiltonian and gauged by standard lattice methods. Using lattice rotor models, we realize this idea in 1+1 and 3+1 spacetime dimensions for $U(1)$ symmetries with mixed 't Hooft anomalies, and show that symmetry disentanglers can be constructed when anomalies cancel. As an example, we present an exactly solvable Hamiltonian lattice model of the (1+1)-dimensional "3450" chiral gauge theory, and we argue that a related construction applies to the $U(1)$ hypercharge symmetry of the Standard Model fermions in 3+1 dimensions. Our results open a new route toward fully local, nonperturbative formulations of chiral gauge theories.

02.
arXiv (CS.CL) 2026-06-12

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an execution-granularity mismatch: locally deterministic tool workflows are unfolded into repeated model-visible decisions, consuming context and forcing the model to manage low-level dataflow in the trace. We introduce HyperTool, a unified executable MCP-style tool interface that changes the model-visible unit of tool execution. A model invokes HyperTool with a code block that can call existing tools through their original schemas, manipulate returned values, and pass intermediate results locally, folding deterministic tool subroutines into a single outer call. To train models to use this interface, we synthesize HyperTool-format trajectories from cross-tool compositional tasks and verify them in real MCP environments. On MCP-Universe, HyperTool improves average accuracy from 15.69\% to 35.29\% on Qwen3-32B and from 9.93\% to 33.33\% on Qwen3-8B, and surpass GPT-OSS and Kimi-k2.5 on average accuracy, showing that our HyperTool can substantially improve multi-step tool use.

03.
arXiv (CS.LG) 2026-06-19

Efficient Neural Network Model Selection for Few-Class Application Datasets

arXiv:2606.19712v1 Announce Type: new Abstract: While much effort has focused on developing and benchmarking high-performance neural networks, less attention has been given to how dataset properties, known to practitioners, can guide efficient model selection. Neural models are typically evaluated on datasets with thousands of classes, yet many real-world applications involve fewer than ten. To address this understudied but common setting, we develop a measure of classification difficulty based on data-side properties and show how it enables more efficient model selection for few-class datasets, where traditional approaches are less effective. We term this phenomenon "few-class distinctiveness". Our metric allows comparison of models and datasets 6 to 29$\times$ faster than repeated training and testing. Leveraging this insight, we extend scaled model families below the smallest published models, achieving greater efficiency at similar accuracy, for example models up to 42% smaller than YOLOv5-nano for a mobile robot task. Targeting resource-constrained applications, we demonstrate few-class model selection across mobile robot, drone, and IoT scenarios, highlighting practical gains in efficiency without sacrificing performance.

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

EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments

Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.

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

AIPatient Arena: EHR-grounded evaluation of large language models in end-to-end clinical consultation workflows

Large language models (LLMs) are increasingly considered for use in clinical consultation tasks, yet most medical evaluations remain static, single-turn, or narrowly outcome-based, limiting their ability to reflect the sequential, uncertain, and interactive nature of real-world care. Here, we propose AIPatient Arena, an EHRs-grounded evaluation framework for assessing the clinical utility of LLMs across eight dimensions of clinical competence. The framework integrates EHR data into patient-specific knowledge graphs, enabling multi-turn physician-patient interactions. We applied AIPatient Arena on a primary cohort of 437 patients and two out-of-distribution validation cohorts of 119 and 67 patients. We observe that LLMs performed well in medical interview questioning skills (QS; mean scores, 4.43-4.99/5), ethical and professional conduct (ET; 4.38-4.93/5), and clarity and transparency of clinical explanations (EX; 3.80-4.72/5). Performance was moderate in information integration (II; 3.19-4.21/5) and medication safety and justification (MS; 3.13-3.78/5), but persistent weaknesses were observed in handling of ambiguous patient responses (HR; 2.57-3.32/5), information coverage (IC; 2.08-3.02/5), and diagnostic accuracy and reasoning (Dx; 2.63-3.55/5). Process-based evaluation revealed recurrent interaction failures, including repetitive questioning, omission of past medical history, and inadequate handling of uncertainty. Richer conversational context improved diagnostic reasoning but yielded limited gains in treatment planning. These findings indicate that final-answer accuracy alone is insufficient for evaluating clinical readiness and highlight the importance of assessing how models gather, interpret, and communicate information throughout a consultation. AIPatient Arena provides an EHR-grounded framework for workflow-oriented pre-deployment evaluation of medical LLMs.

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

Regression Language Models for Code

We study code-to-metric regression: predicting numeric outcomes of code executions, a challenging task due to the open-ended nature of programming languages. While prior methods have resorted to heavy and domain-specific feature engineering, we show that a single unified Regression Language Model (RLM) using a frozen LLM encoder can simultaneously predict directly from text, (i) the memory footprint of code across multiple high-level languages such as Python and C++, (ii) the latency of Triton GPU kernels, and (iii) the accuracy and speed of trained neural networks represented in ONNX. In particular, a relatively small 300M parameter RLM based on T5Gemma, obtains >0.9 Spearman-rank on competitive programming submissions from APPS, and a single unified model achieves >0.5 average Spearman-rank across 24 different programming languages from CodeNet. Furthermore, the RLM can obtain the highest average Kendall-Tau of 0.46 on five classic NAS design spaces previously dominated by graph neural networks, and simultaneously predict architecture latencies on numerous hardware platforms.

07.
arXiv (CS.CL) 2026-06-24

CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression

"Talk short. Drop grammar. Save token." This caveman style is widely promoted as a way to cut inference cost, but whether it actually saves anything depends on which channel (the user's prompt or the model's response) is being compressed. We present Cavewoman, a two-channel evaluation protocol that scores every generation on task accuracy, realized per-item cost, and reference-text agreement against the model's unconstrained reference. We evaluate eight models on five datasets at five reduction levels, with both channels measured on the same items. Output compression cuts realized cost on most API models (1.4-2.4x per model, up to 3x in the best case) and on all four open-weight models under public-tier pricing. Input compression has the opposite effect, a strict lose-lose: it raises net cost rather than lowering it (~1.15x on the five-benchmark mean, up to 1.8x on the worst dataset and 2.7x under stronger compression), because models compensate with longer responses even as accuracy collapses. Under the same setting, surface text diverges from the unconstrained reference: on the non-reasoning models, roughly half of all generations are correct yet their surface text no longer entails the model's own unconstrained baseline generation. The divergence survives length-controlled re-scoring, multiple-comparisons correction, and replication under complementary semantic measures. Code and data are available at https://github.com/danielle34/cavewoman.

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

Occupational Prompting Reveals Cultural Bias in Large Language Models

Social roles shape expectations, priorities, and judgments, yet it remains unclear how large language models (LLMs) associate occupational identities with broader cultural value patterns. Prior work used nationality-based cultural prompting to study how LLM responses to value-survey questions align with human cultural benchmarks. In this paper, we extend that framework by replacing cultural prompting with occupational prompting to examine how professional-role cues influence value-survey responses in open-weight LLMs. Using a survey-grounded evaluation pipeline based on questions from the Integrated Values Surveys, we project model responses into the two-dimensional Inglehart–Welzel cultural space. We prompt open-weight LLMs to answer questions under occupational identities such as accountant, teacher, engineer, and nurse, and then analyze how these occupation-conditioned responses are positioned on the cultural map. Our results show that when open-weight LLMs are prompted with occupations rather than national identities, their responses remain within a broadly Western-leaning region of the cultural map. However, different occupations introduce shifts within this region, producing distinct occupational skews. This indicates that occupational prompts are not treated as neutral role labels, but instead elicit structured value patterns. These findings extend survey-based evaluation of cultural bias beyond nationality-based prompting and provide a framework for studying how occupational personas shape value expression in LLMs.

09.
arXiv (quant-ph) 2026-06-17

Coupled-Mode Equations with Arbitrary Mode Combinations for Kinetic-Inductance Superconducting Traveling-Wave Parametric Devices: Theory and Experimental Validation

arXiv:2606.17264v1 Announce Type: cross Abstract: The coupled-mode equations (CMEs) have proven very successful in describing parametric processes in nonlinear optics. More recently, the same formulation has been used to model microwave superconducting parametric amplifiers and frequency multipliers. However, when applied to the microwave regime, not all assumptions remain valid and losses play a more dramatic role. Here, we revisit the CMEs applied to traveling-wave superconducting amplifiers to include losses and provide a formulation that enables their systematic derivation for any combination of traveling waves. As examples, we discuss the impact of unwanted harmonics and intermodulation products on parametric amplification, as well as harmonic generation. We verify that, if not properly accounted for, device performance can deviate considerably from the ideal case. Furthermore, using a superconducting CPW-based artificial transmission line and combining an independent experimental determination of its nonlinear parameter $I'_*$ with simulations of its linear properties, we obtain a parameter-free validation of this formulation. The nonlinear parameter was determined to be $I'_* \approx 27$ mA which, surprisingly, scales with the theoretical depairing current and not with the much smaller critical current of the device. For the validation, we measured multiple-harmonic generation and found excellent agreement between theory and experiment. The fact that $I'_* \gg I_C$ has direct implications for device design.

10.
arXiv (CS.LG) 2026-06-19

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training

arXiv:2510.18784v3 Announce Type: replace Abstract: Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training. To address this, we introduce CAGE (Curvature-Aware Gradient Estimation), a new QAT method that augments the straight-through estimator (STE) gradient with a curvature-aware correction designed to counteract the loss increase induced by quantization. CAGE is derived from a multi-objective view of QAT that balances loss minimization with the quantization constraints, yielding a principled correction term that depends on local curvature information. On the theoretical side, we introduce the notion of Pareto-optimal solutions for quantized optimization, and establish that CAGE yields strong convergence guarantees in the smooth non-convex setting. In terms of implementation, our approach is optimizer-agnostic, but we provide a highly-efficient implementation that leverages Adam statistics. CAGE significantly improves upon the prior state-of-the-art methods in terms of accuracy, for similar computational cost: for QAT fine-tuning, it halves the compression accuracy loss relative to the prior best method, while for QAT pre-training of Llama models, its accuracy for 3-bit weights-and-activations (W3A3) matches the accuracy achieved at 4-bits (W4A4) with the prior best method. The official implementation can be found over https://github.com/IST-DASLab/CAGE .

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

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery

Frontier models are transitioning from multimodal large language models (MLLMs) that merely ingest visual information to unified multimodal models (UMMs) capable of native interleaved generation. This shift has sparked interest in using intermediate visualizations as a reasoning aid, akin to human mental imagery. Central to this idea is the ability to form, maintain, and manipulate visual representations in a goal-oriented manner. To evaluate and probe this capability, we develop MentisOculi, a procedural, stratified suite of multi-step reasoning problems amenable to visual solution, tuned to challenge frontier models. Evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance. Analysis of UMMs specifically exposes a critical limitation: While they possess the textual reasoning capacity to solve a task and can sometimes generate correct visuals, they suffer from compounding generation errors and fail to leverage even ground-truth visualizations. Our findings suggest that despite their inherent appeal, visual thoughts do not yet benefit model reasoning. MentisOculi establishes the necessary foundation to analyze and close this gap across diverse model families.

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

Cost-Optimal LLM Routing with Limited User Feedback under User Satisfaction Guarantees

arXiv:2606.19376v1 Announce Type: cross Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expect high-quality responses, and in commercial settings this is formally codified in Service Level Agreements (SLAs), creating a fundamental tension between cost and quality. Recent progress on cost-aware LLM request routing has shown potential to resolve this tension, but existing approaches rely on complete feedback signals, offline training, extensive per-workload tuning, and most lack SLA guarantees or inference-time adaptivity. We introduce SLARouter, an online routing algorithm that learns a cost-optimal policy from the sparse, one-sided user feedback available in production systems. SLARouter provides theoretical guarantees for both cost optimality and strict SLA compliance. Experiments across a wide range of LLM benchmarks show that SLARouter satisfies SLA constraints without the need for per-benchmark tuning, reducing operating cost by up to 2.2x over existing baselines.

13.
arXiv (CS.LG) 2026-06-17

Statistical Learning from Attribution Sets

arXiv:2602.06276v2 Announce Type: replace Abstract: We address the problem of training conversion prediction models in advertising domains under privacy constraints, where direct links between ad clicks and conversions are unavailable. Motivated by privacy-preserving browser APIs and the deprecation of third-party cookies, we study a setting where the learner observes a sequence of clicks and a sequence of conversions, but can only link a conversion to a set of candidate clicks (an attribution set) rather than a unique source. We formalize this as learning from attribution sets generated by an oblivious adversary equipped with a prior distribution over the candidates. Despite the lack of explicit labels, we construct an unbiased estimator of the population loss from these coarse signals via a novel approach. Leveraging this estimator, we show that Empirical Risk Minimization achieves generalization guarantees that scale with the informativeness of the prior and is also robust against estimation errors in the prior, despite complex dependencies among attribution sets. Simple empirical evaluations on standard datasets suggest our unbiased approach significantly outperforms common industry heuristics, particularly in regimes where attribution sets are large or overlapping.

14.
arXiv (CS.CL) 2026-06-17

Dissociating Decodability and Causal Use in Bracket-Sequence Transformers

When trained on tasks requiring an understanding of hierarchical structure, transformers have been found to represent this hierarchy in distinct ways: in the geometry of the residual stream, and in stack-like attention patterns maintaining a last-in, first-out ordering. However, it remains unclear whether these representations are causally used or merely decodable. We examine this gap in transformers trained on the Dyck language (a formal language of balanced bracket sequences), where the hierarchical ground truth is explicit. By probing and intervening on the residual stream and attention patterns, we find that depth, distance, and top-of-stack signals are all decodable, yet their causal roles diverge. Specifically, masking attention to the true top-of-stack position causes a sharp drop in long-distance accuracy, while ablating low-dimensional residual stream subspaces has comparatively little effect. These results, which extend to a templated natural language setting, suggest that even in a controlled setting where the relevant hierarchical variables are known, decodability alone does not imply causal use.

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

Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection

Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical. While supervised models can be integrated pre-flight, adding new semantic capabilities in orbit requires retraining and re-uploading parameters. We investigate whether prompt-driven vision–language models can enable post-launch semantic expansion, allowing new spacecraft components to be specified via natural-language prompts without modifying onboard weights. We evaluate zero-shot instance segmentation of spacecraft components under a strictly frozen, single-pass inference protocol on a test set of $129$ images of previously unseen satellites. Under fixed global thresholds and no post-processing, SAM3 achieves $0.385$ mAP@$0.5$ and $0.267$ mAP@$0.5{:}0.95$. Performance is strongly scale-dependent: large structural elements like spacecraft bodies ($0.639$ AP@$0.50$) and solar arrays ($0.598$ AP@$0.5$) localize reliably, while relatively small appendages like antennas ($0.221$ AP@$0.5$) and thrusters ($0.081$ AP@$0.5$) remain difficult. Prompt formulation influences performance, with structured prompts incorporating spatial and geometric descriptors yielding up to $82%$ improvement over short category-name prompts. The model operates within the memory and compute envelope of contemporary embedded GPUs, suggesting prompt-driven grounding can provide a practical mechanism for post-launch semantic extension of dominant spacecraft structures while highlighting limitations of zero-shot localization for fine-scale components under orbital domain shift.

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

Exploring Feature Extraction Technique Parameters for Acoustic Gunshot Classification

arXiv:2606.19568v1 Announce Type: cross Abstract: Acoustic gunshot detection is a problem with applications across civilian public safety, military operations, and wildlife conservation, yet the field lacks a rigorous exploration of feature extraction techniques with a focus on generalization to realistic data. The mixed effectiveness of commercial gunshot detection and classification systems indicates an open problem that is not adequately addressed by the current literature. In this paper, we present a systematic investigation of common feature extraction techniques using a dataset of 23,000 gunshot recordings across 85 firearms and 21 calibers. We benchmark three feature extraction techniques with 12 total unique parameter sets using ResNet-18. Our results demonstrate that using the correct feature extraction technique can improve top-1 accuracy by up to 20%, and utilizing the correct parameters for a given feature extraction technique can improve that value by up to 4.7%.

17.
arXiv (math.PR) 2026-06-15

Stability of the $k$-Plane Transform on Measures and Hölder-Type Comparisons of Wasserstein Metrics

arXiv:2605.00375v2 Announce Type: replace-cross Abstract: We establish stability estimates for the $k$-plane transform on finite positive Radon measures, with emphasis on Fourier and Wasserstein metrics. We first introduce a metric on $k$-plane transform data and prove a bi-Lipschitz stability estimate showing that this metric is equivalent to a generalized Fourier metric obtained by augmenting the Fourier distance between centered normalized measures with separate barycenter and total mass difference terms. Building on a Hölder-type comparison between Fourier and Wasserstein metrics due to Carrillo and Toscani, we extend this comparison to positive Radon measures under uniform bounds on centered moments of order slightly larger than $2$. This yields Hölder-type stability for the $k$-plane transform in a generalized $2$-Wasserstein metric and, in particular, a $W_2$-stability estimate for centered probability measures. We also compare the $2$-Wasserstein distance with its max-sliced analogue. For centered probability measures with uniformly bounded moments of order slightly larger than $2$, we prove a two-sided Hölder-type comparison between these distances. We then extend the result to positive Radon measures by applying it to centered normalized measures and adding separate barycenter and mass terms. Finally, for absolutely continuous compactly supported probability measures with bounded densities, we prove a strong equivalence between the $2$-Wasserstein distance of the measures and the $(k/2-1)$-order Sobolev norm of the $k$-plane transform data of the difference of their densities.

18.
arXiv (math.PR) 2026-06-12

Mixing times of one-sided $k$-transposition shuffles

arXiv:2112.05085v2 Announce Type: replace Abstract: We study mixing times of the one-sided $k$-transposition shuffle. We prove that this shuffle mixes relatively slowly, even for $k$ big. Using the recent ``lifting eigenvectors'' technique of Dieker and Saliola and applying the $\ell^2$ bound, we prove different mixing behaviors and explore the occurrence of cutoff depending on $k$.

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

VISTA: Video Interaction Spatio-Temporal Analysis Benchmark

Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity types, failing to capture the freeform, multi-action interactions between diverse entities which characterize real-world video understanding. Furthermore, the lack of a systematic framework for analyzing model failures across complementary spatio-temporal axes hinders comprehensive evaluation. To address these gaps, we introduce VISTA, a Video Interaction Spatio-Temporal Analysis benchmark designed for open-set, multi-entity and multi-action spatio-temporal understanding in VLMs. VISTA decomposes videos into interpretable entities, their associated actions, and relational dynamics, enabling multi-axis diagnostics and unified assessment of relational, spatial, and temporal understanding. Our benchmark integrates multiple datasets into a single interaction-aware taxonomy and comprises ~12K curated video-query pairs spanning diverse scenes and complexities. We systematically evaluate 11 state-of-the-art VLMs on VISTA, and break down aggregate performance across our taxonomy to reveal shortcomings and pronounced spatio-temporal biases obscured by traditional metrics. By providing detailed, taxonomy-driven diagnostics on a challenging dataset, VISTA offers a nuanced framework to guide advances in model design, pretraining strategies, and evaluation protocols. Overall, VISTA is the first, large-scale, interaction-aware diagnostic benchmark for spatio-temporal understanding in VLMs.

20.
arXiv (CS.AI) 2026-06-18

MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data

arXiv:2606.18485v1 Announce Type: cross Abstract: Neural Text-to-Speech (TTS) systems achieve remarkable quality on short utterances but long-form speech generation shows prosodic drift, speaker inconsistencies and sentence boundary artifacts. Existing approaches either compress sequences, increase context length or naively concatenate independently synthesized chunks. We present an inference-time approach called MagpieTTS-LF that enables MagpieTTS to produce coherent long-form speech without model retraining. Our method introduces three key innovations: (1) soft attention priors to guide monotonic alignment while preserving past and future context; (2) a stateful inference algorithm that maintains context across sentence chunks, ensuring prosodic continuity; (3) history-aware text encoding that uses past text for discourse-level prosodic planning. Experiments on long texts show significant improvements in long-range intelligibility, prosodic coherence, speaker consistency, and boundary naturalness compared to other baselines.

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

How Post-Training Shapes Biological Reasoning Models

arXiv:2606.16517v1 Announce Type: new Abstract: Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood. We study when post-training improves performance and when it induces over-specialization. Across genomics, transcriptomics, and proteins, we train and evaluate more than 100 biological reasoning models under controlled variation in backbone, continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL), measuring both in-domain (ID) and out-of-domain (OOD) performance. We find that each post-training stage reshapes generalization in a distinct way rather than contributing uniform gains. CPT improves downstream performance by aligning models with biological language. SFT consistently increases ID performance but causes OOD performance to peak early and decline as models fit the training distribution. RL, when applied to strong SFT checkpoints with aligned rewards, improves OOD performance and partially recovers generalization. These results show that biological reasoning does not improve monotonically with additional supervision or compute. Instead, performance depends on how training stages are composed. Under fixed post-training budgets, the strongest ID-OOD trade-off comes from brief SFT, larger RL allocations, and asymmetric adaptation capacity across stages.

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

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

23.
arXiv (CS.AI) 2026-06-18

What Must Generalist Agents Remember?

arXiv:2606.18746v1 Announce Type: new Abstract: This paper develops a formal account of what generalist agents must store in memory in order to act near-optimally across multiple environments and goals. It shows that when two domains share an observational bottleneck but require incompatible optimal actions, any uniformly near-optimal policy must induce distinct memory distributions at that bottleneck. The result yields a separation theorem: sufficiently successful agents cannot rely only on current state observations, but must preserve domain-relevant information in memory. The paper further shows that if an agent's memory contains enough information to estimate values for related goals, then that memory can be used to approximately reconstruct the agent's local transition dynamics. Together, these results characterize memory as the substrate that supports domain disambiguation, transition-model reconstruction, and planning for generalist agents.

24.
arXiv (CS.CL) 2026-06-11

FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase apparent difficulty by enriching graph structures, but structural complexity alone does not guarantee realized search difficulty: the intended search process can collapse through a cheaper identifying route. We formalize this gap with a shortcut-aware difficulty framework and identify four actionable shortcut risks: evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided by this framework, we introduce FORT, a Framework of Shortcut-Resistant Training-Data Synthesis. FORT constructs shortcut-resistant training data by controlling shortcut risks across entity selection, evidence graph construction, question formulation, and adversarial refinement. Experiments show that FORT induces longer pre-answer search and fewer shortcut patterns than existing open-source deep search datasets. Using the resulting trajectories, we train FORT-Searcher with supervised fine-tuning (SFT) only, and it achieves the best overall performance among comparable-size open-source search agents on challenging deep search benchmarks. Relevant resources will be made available at https://github.com/RUCAIBox/FORT-Searcher.

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

UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA

We study whether grounded reasoning supervision from abundant 2D medical images can improve 3D medical VQA when both input types are aligned through a common reasoning interface. We introduce UniReason-Med, a single-checkpoint framework that processes either a 2D image or a slice-serialized 3D volume at inference time, generating interleaved textual reasoning and localized visual evidence through shared box syntax, region-token injection, and a common grounded reasoning policy. To train this interface, we construct UniMed-CoT, a 220K instruction-tuning dataset with interleaved textual reasoning and grounded visual evidence, including 170K 2D and 50K 3D samples. Through supervised fine-tuning followed by outcome-level reinforcement learning, UniReason-Med learns to generate grounded reasoning traces without IoU/Dice-based localization rewards during RL. Data-mixture and component ablations show that joint 2D+3D grounded supervision substantially improves 3D reasoning over 3D-only training, while grounding and region-token injection consistently benefit both 2D and 3D tasks. These results suggest that a shared grounded reasoning interface can transfer reasoning structure from 2D images to slice-serialized volumetric medical understanding. The code and data are publicly available at https://github.com/IQuestLab/unireason-med.