New Tasks

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 46

Sep 30, 2026cs.RO

PhasePlan: Ordered Future-Phase Planning for Robot Brain Models

Robot brain models integrate vision, language, and robot state to generate actions for complex manipulation tasks. Most predict fixed-length action chunks that may span multiple task phases. This can obscure phase transitions and favor frequent action patterns, compromising action timing in dynamic environments. We propose \method, an ordered future-phase planning method for robot brain models. From current multimodal observations, it predicts the task phase at each future action position. The resulting planning representations condition the corresponding actions, preserving temporal alignment between task progress and action generation. Training first learns the planner, then freezes it during action-model adaptation to maintain stable phase representations. We instantiate \method on pretrained

π_{0.5}

and AcrossWAM1.0 robot brain models. Detailed quantitative evaluation uses the

π_{0.5}

implementation. On conveyor-belt manipulation, \method reduces offline joint-action error by approximately 22.5% relative to the original

π_{0.5}

model. It also improves phase-transition modeling and cross-phase action prediction. These results demonstrate the value of ordered future-phase planning for continuous action generation.

Xiaoyu Yang, Yafei Zhang, Wensheng Li +2

Action Prediction Planning Robot Systems New Tasks

Sep 30, 2026cs.AI

Do Self-Evolving Skills Generalize to Held-Out Tasks?

AI agents can externalize what they learn from past tasks into reusable \emph{skills}, such as procedures, checklists, code, or other executable artifacts, that can be retrieved and reused when solving new tasks. Self-evolving skill methods keep rewriting these skills after each round of practice on training tasks, and the skill is then used on new tasks of the same kind. We ask a question: does the improvement a skill shows on its training tasks carry over to new test tasks? We test five self-evolving methods and a one-shot skill on six benchmarks, with the same model, the same agent, and the same train/test split for every method. Of the 21 skills that improve on their training tasks, 5 keep all of that improvement on the test tasks, 13 keep part of it, and 3 keep none of it. No existing method is best everywhere. When we read the skills, the ones that carry over badly often fix details that should depend on the task, such as column names and output files, or turn a fix for one failure into a rule for every task. An LLM judge that reads the skill content can often see this: it ranks finished skills the same way the test results do in 86% of pairs. But it predicts the effect of a single edit poorly, so edits still have to be tested by running them. Based on these findings, we describe Generalizable Skill Optimization (GSO), which keeps only a guide for writing skills and writes a new skill for each task; it scores highest on all six benchmarks.

Xihao Piao, Zifeng Wang, Zhen Chen

SANKEN, Osaka University

Skill Evolution Skills Self-Evolution New Tasks

Sep 30, 2026cs.CR

Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners

Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments. However, this requires their safety alignment to also hold in unseen environments. Existing red-teaming assumes an adversary who optimizes the prompt, the pixels, or text in the environment, and existing benchmarks ask whether a planner recognizes or mitigates a hazard in a fixed scene. Neither asks whether a refusal the planner has already given survives an ordinary change to the environment. We ask that question by placing a single everyday object into the environment, with no pixel, gradient, or prompt under adversarial control. On

846

tasks that a constitution-guarded planner initially refuses, we find

20.2\%

of tasks can be flipped to compliance by one or more objects, and the number of objects differs from one task to another. In addition, the object need not be chosen for the task, i.e., items drawn from a fixed list, with no knowledge of the environment or the instruction, bypass safety about as often as items proposed for the specific task. We qualitatively contrast the tasks bypassed most and least often and find that the distinction lies in how conspicuous the hazard is in the instruction and environment. Susceptibility to safety bypass is therefore a property of the task, which we call its \emph{malleability}, and we show that it can be predicted before the target is ever queried. A composite of signals read from a small open-source VLM identifies malleable tasks

2.4\times

as often as picking at random. Everyday objects, whether placed by an adversary or introduced by ordinary rearrangement of the environment, are thus sufficient to overturn a refusal. Because susceptibility is determined by how a task is specified, we recommend assessing malleability per task prior to deployment.

Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen +1

Purdue University · Amazon · Arizona State University

Safety Alignment Refusals Adversarial Evaluation Recent Vision-Language Models Dynamic Environments New Tasks

Sep 29, 2026cs.AI

Self-Evolving Harness on Multiple Tasks with the Agent as Its Own Optimizer

A harness is the code around a language-model agent that organizes prompts, calls tools, manages context, and controls execution. As models grow stronger, recent work has begun to let agents improve their own harnesses, a line of work known as self-evolving harnesses. In most existing methods, a separate proposer running on a human-designed harness modifies the solver's harness, and a separate harness is evolved for each benchmark. Real-world tasks come from many domains, so both the evolution and the evaluation of a harness should cover a diverse range of tasks. We propose a framework close to recursive self-improvement: the same frozen model, on the same version of the harness, first solves tasks as the solver and then, as the proposer, reads the complete run records and directly edits the harness that runs it. Each evolution batch draws tasks from five benchmarks in different domains. To measure generalization, training and held-out tasks are strictly separated, and we additionally evaluate on five out-of-distribution benchmarks never used during evolution. We frame the evolution process as deep-learning training with two stages, multi-task pretraining and continual training. Starting from a 49-line seed harness, the harness obtained at the end of the first stage improves the average score by 4.48 points on the in-distribution benchmarks and by 12.64 points on the out-of-distribution benchmarks, surpassing Codex on the former and matching it on the latter. In the second stage, continued evolution on Claw-Eval, one of the out-of-distribution benchmarks, further raises the score on that benchmark from 66.17 to 68.06, exceeding Codex. We also provide an in-depth analysis of the mechanisms that emerged during evolution, including output truncation, history compaction, and independent review.

Qiankai Xu

Nanjing University

Evolving Harness Language-Model Agents New Tasks

Sep 27, 2026cs.LG

Compressing Value Predictions for Learning-Augmented Metrical Task Systems

Learning-augmented algorithms for metrical task systems (MTS) can exploit predictions of canonical dual values, but existing formulations typically require a prediction for every state. We study whether these predictions can be compressed to a small set of representative states while retaining their algorithmic value. We introduce landmark-compressed value predictions, in which the predictor reports predicted dual values only at

m

landmarks and the remaining values are reconstructed by a Lipschitz extension. Our algorithm achieves additive excess cost

O(T\,r(L) + \sum_t δ_t)

, where

r(L)

is the covering radius of the landmarks and

δ_t

measures prediction error up to additive shifts; local and value-dependent bounds refine this guarantee. For sparse landmark sets on unit-spaced finite lines, we prove a matching

Ω(T r_m)

lower bound for every randomized algorithm using fixed landmarks, even with advance access to their entire exact absolute-value table. The prediction interface also matters: on two states with one landmark, exact absolute values permit horizon-independent excess, whereas exact relative values force worst-case expected excess linear in

T

. We give PAC guarantees for learning compressed prediction tables, with efficient empirical-risk minimization for fixed landmarks. Our results connect metric coverage, prediction interfaces, and learning guarantees for compressed predictions in online MTS.

Sizhe Li, Yecheng Li, Kun He

School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan, Hubei 430074, China · School of Computer Science and Technology Huazhong University of Science and Technology Wuhan, Hubei 430074, China

Learning-Augmented Algorithms Value New Tasks Duality

Sep 23, 2026cs.RO

Turning Safety into Competence: Minimally Exploitable Robot Policies via Safety-Filtered Reinforcement Learning

Robots deployed for competitive tasks must outmaneuver their opponents without sacrificing safety. Existing approaches, including safe reinforcement learning (RL), train a single policy to achieve task success and avoid failures simultaneously. This coupling can complicate training and leave the learned policy exploitable by deliberate attacks. We propose Safety to Competence (S2C), a two-stage RL framework that separates safety synthesis from competitive task learning. We formulate competitive interactions as safety-critical Markov games and prove that perfect filtering preserves policy non-exploitability when all players commit to safe maneuvers. S2C learns a robust safety filter via adversarial RL, embeds it in the environment during task policy training, and retains the same filter at deployment. In simulated touchdown games, S2C outperforms eight safe RL baselines, achieving the highest win rate and Elo rating, and the lowest exploitability. Hardware stress tests against a human opponent confirm S2C's competence.

Ruihan Wu, Rui Yang, Donggeon David Oh +2

Department of Computer Science, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA

Safety Filters Robot Policies Offline Reinforcement Learning Competence New Tasks

Sep 16, 2026econ.GN

Multitask Reinforcement Learning for Assisting Choice Model Specification

Discrete choice model specification is a time-consuming task in which modellers often specify and estimate multiple models while balancing goodness-of-fit, parsimony, and behavioural plausibility. We present Delphos, a multitask reinforcement learning framework that learns transferable specification strategies across transport choice datasets. Delphos frames model specification as a sequential decision-making problem in which it applies a sequence of modelling actions and receives feedback from an estimation environment based on model performance and convergence. To transfer modelling decisions across datasets with different sets of variables, Delphos represents utility specifications as sets of modelling terms using a DeepSet-Q architecture, allowing a shared specification policy to learn across multiple datasets. Trained on nine transport choice datasets, Delphos consistently outperforms independently trained single-task agents, indicating that sharing modelling experience improves learning efficiency and helps identify promising sequences of modelling decisions with fewer unsuccessful estimation attempts. When applied without further training to the unseen Swissmetro and Decisions datasets, the same agent identifies competitive specifications in less than 20 minutes on a standard CPU. It achieves a higher log-likelihood per observation than the VNS metaheuristic on Swissmetro and performance comparable to a published MNL specification developed by expert modellers on Decisions. These findings show that accumulating and reusing modelling experience enables Delphos to function as an intelligent assistant for discrete choice model specification. It reduces manual trial-and-error while allowing modellers to retain control over model diagnosis, refinement, and final selection.

Gabriel Nova, Stephane Hess, Sander Van Cranenburgh

CityAI Lab, Transport and Logistics Group, Delft University of Technology, The Netherlands · Institute for Transport Studies and Choice Modelling Centre, University of Leeds, UK

Multi-Turn Reinforcement Learning New Tasks Choice Transport

Sep 14, 2026cs.AI

When Does AI Augment Work? A Workflow-Level Framework for Human-Agent Collaboration

We aim to characterise the value of artificial intelligence in the workplace. Current studies largely measure this value in terms of the current automation capabilities and public adoption of AI. However, such metrics ignore the greater impacts of human--agent collaboration in transforming the nature of work. To account for this, we must expand the scope of our analysis beyond atomised tasks of today, and instead focus on how AI can augment entire workflows of the future. To ground this analysis, we establish a precise definition of AI augmentation comprising six conditions, spanning durable net value, meaningful human control, accountability and recovery, and long-term human development through learning, career pathways, and job purpose. We elaborate on these conditions and apply the framework in a case study of AI-mediated social surveys. We conclude by outlining how organisations, researchers, and government leaders can use this framework to make sense of the future of work.

AI Collaboration, Jiaying Wu, Caleb Ziems +19

National University of Singapore · Stanford University · Genue +10

Human-Ai Collaboration Agentic Workflows Organizational Research Agentic Workflow Design Human Agency Collaboration+2

Sep 8, 2026cs.RO

Actuator Dynamics Curricula for Narrow-Viability Tasks in Legged Robot Learning

Reinforcement learning has produced capable controllers across a broad range of legged-robot tasks, but a subset of these tasks fail to converge under standard training: those for which most exploration trajectories terminate before producing useful gradient signal. To address such tasks we introduce the \emph{Actuator Dynamics Curriculum}, a procedure that initializes joint stiffness at a high value and anneals it toward the system-identified value as completed episode lengths grow. Using a cart-pole system as a representative example, we show that higher closed-loop joint natural frequency under critical damping enlarges the viability kernel of the underlying Markov Decision Process, increasing the fraction of initial states from which the task is feasible. We validate the kernel monotonicity on the cart-pole and apply the curriculum to a quadrupedal-to-handstand transition on the Boston Dynamics Spot, a narrow-viability task where training under fixed identified stiffness plateaus at a policy that never completes the transition. The trained policy executes the transition in simulation across 10 seeds and transfers to hardware. More broadly, our results suggest that simulated actuator dynamics is a useful axis along which to design curricula for tasks in which exploration is bottlenecked by termination conditions rather than by reward signal.

Kousheek Chakraborty, Chandan K. Rajendra, Ayham Alharbat +1

Saxion University of Applied Sciences · University of Groningen · University of Twente

Actuator Agile Locomotion Closed-Loop Feedback Legged Robots Curriculum Robot Systems+1

Sep 8, 2026cs.LG

Let It Go or Learn to Self-Correct: Continuous Diffusion for Constrained Discrete Tasks

Denoising Diffusion Probabilistic Models (DDPMs) generate samples by starting from noise and repeatedly denoising while keeping each update close to the current noisy state. This behavior is effective in many continuous domains, but its role is less clear for globally constrained discrete tasks, such as Sudoku, graph connectivity, Latin squares, and N-queens. In such settings, early discrete errors can be difficult to undo. As a result, standard diffusion sampling may preserve early mistakes, even when the model's clean predictions are informative. We compare standard samplers to sampling directly from the model's clean prediction. Without retraining, this single change improves Sudoku validity from 31% to 95%, with consistent gains across the other discrete tasks. We hypothesize that staying close to the current noisy state is harmful because the reverse trajectory can drift off the forward noising distribution the model was trained on. To reduce this train-test mismatch, we further introduce self-correction training, which exposes the model to its own predictions, improving robustness to errors that arise during inference. This substantially improves the performance of standard samplers. Our results suggest that continuous diffusion models can learn nontrivial global constraints, but discrete reasoning tasks require better alignment between training and inference: either through samplers that reduce commitment to early decisions, or through training that teaches the model to correct its own inference-time errors.

Mariia Drozdova, Stéphane Liem Nguyen, François Fleuret

University of Geneva

Denoising Diffusion Probabilistic Model Diffusion Models Iterative Self-Correction Learn New Tasks

Sep 8, 2026cs.SE

The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?

Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a model can reliably report its task progress at every stage of a task, and where and how its reports fail, has not been studied systematically. We evaluate this ability on the public benchmark

τ^2

-bench and on StageIF, a controlled testbed in which reporting checkpoints are placed across the task's lifecycle. Both settings require reports at multiple task stages. We find that reporting reliability depends on the stage a task has reached, and that almost every deployed model we test is reliable at some stages and unreliable at others. Where reporting breaks down is not the same everywhere. Most deployed models lose accuracy once work is under way and recover once the task is done. The newest generation closes that mid-task drop and instead grows conservative at the finish line. Our study exposes a capability gap in task-progress reporting and provides an evaluation protocol that spans the whole course of task execution for this ability on which agent operation depends. The findings indicate that agent frameworks should not control task flow on the strength of the model's state reports alone.

Boyang Wang, Yunhan Wang, Yalun Wu

Independent Researcher · Beihang University · NExT++ Lab, School of Computing, National University of Singapore

Large Language Model Agents New Tasks Evaluation Protocols

Aug 31, 2026cs.CV

One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning

Class-incremental learning (CIL) requires a model to incrementally learn tasks that contain new classes without accessing earlier training data while preserving the ability to recognize all seen classes. Recently, pretrained-model-based approaches have become prevalent by adapting a frozen backbone with additional lightweight trainable modules. Existing methods, however, exhibit limitations: task-specific adapters learn explicit per-task representations but are parameter- and computation-inefficient, while LoRA-based merging methods combine per-task LoRA parameters into a single model whose static aggregated weights cause representation interference during inference. To address these problems, we present \textbf{FACET}: task-conditioned \textbf{F}e\textbf{A}ture transformation with \textbf{C}ondition\textbf{E}d feature consis\textbf{T}ency, achieving excellent parameter efficiency while producing highly discriminative features during inference. When continually trained on a task sequence, FACET learns a single shared adapter that employs a dynamic task-conditioned feature transformation, shaping the overall feature distribution of the adapter into a mixture of overlap-reduced task-specific components. On the other hand, we propose an efficient replay-free task-conditioned feature consistency loss, aiming to mitigate catastrophic forgetting of the learned mixture distribution in the adapter's feature space. Even when maintaining only a single adapter, FACET demonstrates robust scalability. On both very long task sequences (e.g., 200 tasks) and standard short task sequences (e.g., 20 tasks), our method achieves superior performance while using significantly fewer trainable parameters and GFLOPs. The code will be made open source upon acceptance.

Yunxiang Fu, Meng Lou, Yizhou Yu

School of Computing and Data Science The University of Hong Kong

Class-Incremental Learning Continual Learning Prioritized Experience Replay New Tasks

Aug 27, 2026cs.LG

Decentralized Multitask Learning over Learned Task Graphs

This paper investigates decentralized multitask learning over networks when the underlying task relationships are unknown. While existing graph-regularized multitask frameworks typically assume a known structure, practical settings often require learning inter-task dependencies directly from distributed data. We propose a decentralized two-phase strategy that first estimates a generalized graph Laplacian from noisy non-cooperative stochastic gradient iterates, and subsequently exploits the learned graph to enable cooperative multitask diffusion learning. This framework is motivated by a Gaussian Markov random field prior, which gives rise to a decentralized maximum likelihood estimator for the graph Laplacian. The analysis quantifies the Laplacian estimation error and its propagation to the steady-state performance of the multitask diffusion recursion, and introduces a topology sensitivity index to capture the effect of network heterogeneity. Simulation results corroborate the theoretical findings and demonstrate that cooperation enabled by the learned task graph significantly improves performance over non-cooperative learning, while approaching the true-graph baseline when the estimation stepsize is sufficiently small.

Zirui Wan, Stefan Vlaski

Department of Electrical and Electronic Engineering, Imperial College London, UK

Graph Representation Learning Decentralized Learning New Tasks Maximum Likelihood

Aug 26, 2026cs.RO

A Taxonomy of Construction Task Activities for Robot Workers

Recent vision-language-action models offer a path toward robots with broader repertoires than conventional task-specific systems. Construction deployment, however, requires a precise inventory of worker activities and the capabilities needed to execute them. We present TARCAT, an occupation-grounded taxonomy derived from 91 O*NET tasks across seven high-employment construction occupations and 30 instructional videos of physical work. TARCAT defines 41 action primitives in 12 groups and three classes and provides a mechanism for composing parameterized primitive sequences into reusable skills. This human-interpretable structure can organize demonstrations, specify robot requirements, and support coding agents that retrieve and extend skill libraries. We also demonstrate selected primitives on a DOBOT CR3 arm with a CRAFT hand. TARCAT thereby provides a common vocabulary for analyzing human work and developing general-purpose construction robots. Annotations are available at https://github.com/AICPS/TARCAT-Taxonomy.

Sadman Sakib, Zhangyi None Peng, Yujie Pang +2

The authors are with the Nhu Department of Electrical Engineering and Computer Science, University of California-Irvine, Irvine, CA, USA · The authors contributed during the UCInspire program · The author is with the Department of Civil and Environmental Engineering, University of California-Irvine, Irvine, CA, USA

Construction New Tasks Taxonomy

Aug 10, 2026cond-mat.mtrl-sci

Multitask Scanning Probe Microscopy

Scanning probe microscopy provides nanoscale access to structural, electrical, electromechanical, magnetic, and mechanical properties of materials. Its increasing use for wafer-scale characterization and combinatorial materials exploration creates a need to distribute measurements efficiently across large spatial domains. This is particularly important when available modalities differ in acquisition time and potential for tip and sample damage, making exhaustive multimodal mapping over spatial grids impractical. Here, we demonstrate multitask scanning probe microscopy, a live, closed-loop workflow in which a multitask Gaussian process learns spatial and cross-modal relationships and autonomously selects both the next measurement location and the next experimental protocol. The approach is implemented on an automated large-sample atomic force microscope and demonstrated on a composition-spread AlScN wafer using tapping-mode and Dual AC Resonance Tracking (DART) measurements. Paired initial measurements establish the relation between the tasks, after which noncoincident measurements are used to update both response landscapes. The resulting workflow extends active learning in scanning probe microscopy from spatial sampling to autonomous allocation of measurement modalities and provides a basis for combining rapid, weakly perturbative imaging with slower contact, electrical, electromechanical, magnetic, or spectroscopic measurements.

Aditya Raghavan, Yu Liu, Ian Mercer +2

University of Tennessee, Knoxville, TN, USA · 2Pennsylvania State University, University Park, PA, USA

Electron Microscopy Microscopy Data-Driven Materials Discovery New Tasks

Aug 6, 2026cs.RO

Coordinated Multi-Robot Disassembly for Makespan Optimization of Large-Scale Assemblies

Multi-robot task and motion planning for disassembly tasks requires robots to operate in confined workspaces while coordinating their motions with other robots. To tackle this problem, we propose a planning method called coordinated multi-robot disassembly (CoMuDi). CoMuDi coordinates a team of robots for disassembly tasks. The input is a team of robots, an assembly of objects, and a dependency graph. Based on this information, we create compound tasks for pick, place, and exit motions. By propagating temporal constraints, we ensure that each robot can start and end their tasks as early as possible while avoiding collisions with nearby robots. By integrating the space-time RRT* planner (ST-RRT*) into CoMuDi, we ensure that individual tasks minimize arrival time and thereby help us minimize overall makespan. We compare the performance of CoMuDi using both ST-RRT* and RRT* planners with varying time bounds, demonstrating that the combination of CoMuDi and ST-RRT* leads to a higher success rate while minimizing makespan. Finally, we evaluate CoMuDi on six assemblies with up to 49 pieces and up to 9 robots. In those scenarios, we show that CoMuDi returns robot paths that exhibit low idle times, thereby demonstrating that CoMuDi can reliably solve large-scale assemblies.

Niklas Hargus, Andreas Orthey, Marc Toussaint

Technical University of Berlin, Germany · Robotics Institute Germany (RIG)

Multi-Robot Motion Planning Multi-Robot Systems Motion Planning Assembly Robot Systems New Tasks

Aug 5, 2026cs.LG

Optimal Training-Time Scaling in Gradual Adaptation

In gradual adaptation, how should the training time on each task change as the number of intermediate tasks increases? We study this question for overparameterized linear regression tasks that change smoothly and share a zero-loss solution. With

N

tasks and training time

s_N

on each, the final learning progress converges to a continuum curve when

Ns_N\toτ

. The limiting progress is

Θ(τ)

for small

τ

and

Θ(τ^{-1})

for large

τ

, so both very short and very long training produce little progress. It follows that optimal per-task training times scale as

s_N^\star=Θ(N^{-1})

, equivalently

Ns_N^\star=Θ(1)

. Experiments on gradually rotated MNIST and a natural Yearbook time shift are consistent with less per-task training as the path is divided more finely.

Zonghuan Xu, Krishna Harish

Fudan University Shanghai, China · Lawrence E. Elkins High School Missouri City, Texas, USA

Batch Training Time Overparameterization Rapid Adaptation New Tasks Curves

Aug 4, 2026cs.DB

Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks

Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current evaluation benchmarks remain disproportionately fixated on Text-to-SQL tasks, neglecting the holistic Database Lifecycle-from initial schema design to post-deployment maintenance. This narrow focus fails to capture the diverse capabilities required for real-world database management. To bridge this gap, we introduce DBLifeBench, the first benchmark to evaluate LLMs across five critical lifecycle phases: Design, Implementation, Operation, Debugging, and Maintenance. Furthermore, addressing the cognitive mismatch between ambiguous natural language and complex SQL logic, we propose Progressive-Text2SQL, a novel task utilizing structured reasoning graphs to mimic human iterative problem-solving. Our extensive evaluation reveals a critical insight: while general-purpose models demonstrate balanced performance, specialized Text-to-SQL models suffer from ``catastrophic forgetting'' in non-coding phases like design and maintenance. DBLifeBench serves as a foundational step toward evaluating and building true full-stack database intelligence.

Shunfan Zheng, Dongsheng Shi, Yue Li +3

1East China Normal University · 2Hasso Plattner Institute/University of Potsdam

Text-To-Sql Large Language Model Benchmarks Large Language Model Evaluation Reasoning Graphs New Tasks

Jul 31, 2026cs.SE

Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures

Large Language Model (LLM) agents rely on external tools to perform multistage tasks. Existing agent frameworks typically assume that tool calls are atomic and return binary success or failure signals. However, real-world systems exhibit non-atomic behaviors such as timeouts after dispatch, delayed visibility, and partial state updates. These mismatches lead to reliability issues including duplicate actions, task success, and unnecessary tool executions. A lightweight, verification-aware tool wrapper is introduced that augments tool calls with postcondition verification, verify-before-retry logic, and idempotency keys. The approach is evaluated in a controlled simulated environment with injected non-atomic failures across multiple task templates. The results demonstrate that the proposed method significantly reduces duplicate actions, while maintaining comparable task success rates. Overall, the findings suggest that strengthening tool interaction semantics is a promising direction for improving LLM agent reliability without requiring modifications to the underlying language model.

Isham Kalappurackal Mansoor, Abhishek Phadke, Pratip Rana

Department of Computer Science Old Dominion University Norfolk, VA 23529 · School of Engineering and Computing Christopher Newport University Newport News, VA 23606

Large Language Model Agents Call Verification Framework Latent Failure Patterns New Tasks

Jul 30, 2026cs.AI

Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding

Recent advances in sign language (SL) understanding (SLU) have led to remarkable progress in tasks such as continuous SL recognition and SL translation. However, these tasks are designed with predefined objectives, requiring models to learn a fixed mapping from sign videos to glosses or spoken-language sentences. As a result, they provide only a limited assessment of whether a model truly understands the semantic content of SL videos. To address this limitation, \textbf{we first propose a new task, Sign Language Question Answering (SLQA)}, which evaluates SL understanding by requiring models to answer arbitrary natural language questions about SL videos. Unlike previous SLU tasks, SLQA provides a more flexible and comprehensive evaluation framework that assesses multiple reasoning capabilities beyond recognition and translation. To facilitate this task, \textbf{we further construct two SignQA benchmarks} based on PHOENIX14T and CSL-Daily by automatically generating question-answer pairs from existing gloss and sentence annotations using carefully designed templates. The resulting datasets cover five complementary question categories, including position reasoning, structural reasoning, visual search, gloss recognition, and translation understanding. \textbf{Finally, we propose a simple yet effective baseline model} equipped with a Question-Conditioned Modulated Temporal Downsampling module and an in-domain knowledge transfer strategy, enabling effective knowledge transfer from existing SLU tasks while enhancing question-aware temporal feature modeling. Extensive experiments demonstrate that our baseline consistently outperforms representative vision-language models across all question categories, establishing a strong benchmark for future research on SLQA. Datasets are available at:{https://huggingface.co/datasets/hulala/SignQA-2026}.

Shiwei Gan, Lichen Wang, Xiao Liu +4

State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing 210023, China

Sign Language Translation New Tasks

Jul 24, 2026cs.CL

From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models

Large language model (LLM) evaluation spans diverse tasks and benchmarks, yet evidence remains organized around tasks rather than the capabilities they probe. This fragmentation limits cross-study comparison, obscures capabilities tasks recruit, and makes coverage gaps difficult to identify. We introduce a multi-layer taxonomy of 14 capability domains and 91 subskills across Primitive, Constructed, and Integrative layers. Human cognitive science guides capability definition and organization, not LLM architecture. Layer assignments draw on developmental precedence and hypothesized functional support, while human-origin constructs are adapted to observable model behavior. To demonstrate operational utility, we screened 31,505 papers from ACL, AAAI, ICML, and NeurIPS between 2023 and 2025 and mapped 15,934 LLM-focused papers through multi-model annotation, consensus, and arbitration. Direct research attention concentrated on Language-Semantic Competence (3,551; 22.3%), Reasoning (3,388; 21.3%), Planning and Decision-Making (2,149; 13.5%), and Perception (1,954; 12.3%), whereas six domains appeared in fewer than 2% of papers. Within domains, the most frequent subskill had a median prevalence of 97.9% and appeared in at least 90% of papers in 10 of 14 domains. Language-Semantic Competence and Reasoning formed the highest-volume pair (n = 1,864; 11.7%; lift = 2.47), whereas Theory of Mind and Social Reasoning and Interaction showed the highest lift among pairs with at least 20 co-occurrences (n = 62; lift = 30.84). By shifting the unit of analysis from isolated tasks to structured capabilities, the taxonomy supports research organization, coverage audits, evaluation interpretation, and testable hypotheses for diagnosis, training, and transfer.

Shixin Fang, Jiachen Wo, Wenjuan Qin +2

Fudan University

Large Language Model Evaluation Cognitive Science Taxonomy New Tasks

Jul 21, 2026cs.LG

Benchmarking Generalization in Financial Statement Fraud Detection: robust evaluation and novel tasks

Financial statement fraud detection (FSFD) is crucial for market integrity but faces challenges from increasingly sophisticated schemes and under-utilized textual data in financial reports. Existing methods often rely on random data splits, leading to overoptimistic performance estimates that do not reflect real-world generalization to new companies or future periods. To address this recurring problem with the state of the art, we propose a robust FSFD framework leveraging Large Language Models (LLMs) to integrate both structured financial data and unstructured textual information from financial reports. We provide a more realistic evaluation through a novel and challenging benchmark task called Company-Isolated FSFD (CI-FSFD). We construct and make publicly available a comprehensive U.S. company dataset combining financial statements, summarized MD&A text, and fraud labels. Our approach achieves the best performance on the challenging CI-FSFD task, demonstrating the critical value of textual data and robust evaluation for reliable financial fraud detection.

Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara +1

Forvis Mazars · LORIA CNRS Université de Lorraine · LORIA, CNRS, Universit´e de Lorraine +2

Fraud Detection Financial Question Answering Unstructured Data New Tasks

Jul 14, 2026cs.AI

How Many Tasks Are Enough for Agent Benchmark Decisions? A Replay Analysis of Public LLM Agent Benchmarks

Agent benchmarks often compare two agents after all tasks have run, but costly evaluations make partial runs tempting. A task fraction alone does not show whether a partial run supports the same pairwise conclusion as the completed benchmark. We study this question by replaying completed public task-level records from SWE-bench, AppWorld, and tau-bench. A partial budget counts as enough only when it supports the completed benchmark's decision, covers required task groups, and leaves no more than a target fraction of comparisons unresolved. The required task fraction varies sharply. At the strict 0 percentage point threshold on a 5 percentage point budget grid, AppWorld first meets all targets at 15 percent, tau-bench at 25 percent, and SWE-bench Verified at 90 percent; SWE-bench Lite does not meet all targets by 95 percent under the primary coverage rule. Partial-evaluation reports should state how much one agent must outperform another, how tasks are selected, what coverage rule is required, what decision rule is used, and how many comparisons may remain unresolved.

Wei-Jung Huang

Independent Researcher · United States

Agentic Benchmarks Swe-Bench Verified New Tasks Large Language Model Agents Token Budget Allocation Replay

Jun 14, 2026cs.RO

Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time

Extending a vision-language-action (VLA) policy to a new task typically requires task-specific teleoperated demonstrations and per-task fine-tuning, making adaptation costly in both data collection and compute. In this paper, we show that this target-side per-task adaptation cost can be replaced by retrieval. Our retrieval-augmented policy is trained once on paired demonstrations from the target embodiment (query) and a cheaper embodiment (pool, e.g., human-hand video), then frozen. New tasks are added at deployment by appending pool-side demonstrations to a retrieval pool. The frozen policy conditions on retrieved trajectories at every control step, so new tasks are absorbed by indexing data rather than updating parameters. Fine-tuning is needed only to take on a new, unseen embodiment, not for each new task. We show that retrieval improves policies beyond a specific backbone, including standard VLA policies, but its effect is especially pronounced in Cosmos Policy, a video-generation-based world-action model (WAM). In this setting, retrieval supplies coarse task progression, while the WAM's future-image objective provides an additional visual consistency signal that strengthens the retrieval-conditioned actions. On PushT, we study how retrieval provides a reusable high-level motion prior for cross-embodiment generalization to unseen goal angles, while on RoboTwin 2.0 our method outperforms cross-embodiment baselines on unseen tasks, and we additionally demonstrate the method on a real robot.

Jeongeun Park, Juhan Park, Taekyung Kim +3

NAVER AI Lab · Korea University

Goal-Conditioned Dynamic Manipulation Cross-Embodiment Transfer Efficient Task Adaptation New Tasks Test Time

Jun 12, 2026cs.CR

When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training

Verifier reliability is not portable across tasks. A verifier-guided self-DPO pipeline with genuine held-out gains on MathVista (+9.6 points on self-training data, +8.0 held out) can be harmful on MMMU. The failure is invisible from the target-task self-training signal: over six learner-verifier configurations, MMMU self-training performance still improves by +3.52 points while held-out performance drops by 1.42 points. We call this silent negative transfer: a verifier validated as useful before can still show signatures of successful self-training after its induced update stops transferring to unseen data. Downstream failure alone cannot diagnose this: poor generalization may mean the verifier induces a wrong learning direction, or that the correct direction itself does not generalize beyond the self-training distribution. We separate these effects via gradient fidelity F, the alignment between verifier-induced and correct training directions, and gradient transferability T, the alignment between correct and held-out directions, giving a conservative Safe-Transfer Margin: positive first-order held-out alignment is certified when arccos(F) + arccos(T) < pi/2. We then introduce Asymmetric Acceptance Gating (AAG), a precision-first filter selecting preference pairs by the verifier's absolute confidence in the response receiving the positive update. On MMMU, AAG raises fidelity from 0.29 to 0.42. In a same-cell analysis, the correct direction stays positively aligned with the held-out direction (T = 0.31), yet raw verification rotates the induced update to negative held-out alignment (-0.13); AAG restores positive alignment (+0.22). Across all six MMMU configurations, AAG beats raw verifier-guided training. Verifier reliability thus means not that it worked before, but that it induces the right update on the task at hand and that this update stays useful beyond the data that generated it.

Jianzhe Lin

MetaAI · Work done at Meta

Verification Framework Self-Verification Task-Specific Rubrics New Tasks Replay

Jun 11, 2026cs.LG

Decoding Insect Song: A Multitask Semisupervised Orthoptera Bioacoustic Classifier

Passive acoustic monitoring holds great promise for ecological inference, yet existing automated tools are typically narrowly trained and non-transferable. We address these limitations with PULSE, a semi-supervised, multi-task framework for Orthoptera bioacoustics, combining weakly-supervised species classification, self-supervised learning on unlabelled field audio, and knowledge distillation from a general-purpose bioacoustic model. Our domain-adapted specialist model outperforms a state-of-the-art general model across all metrics (macro F1: 0.21 vs. 0.07; AUC: 0.74 vs. 0.45; AP: 0.32 vs. 0.19), with active learning further raising F1 to 0.34 and AUC to 0.84. Beyond classification, the learned embeddings encode ecologically meaningful structure, exposed through an interactive visualisation tool for ecological discovery.

Olga Isupova, Danil Kuzin, Ella Browning +2

Leverhulme Centre for Nature Recovery, School of Geography and the Environment, University of Oxford, Oxford, UK

Passive Acoustic Monitoring Species Identification Classifier Audio Understanding Ecosystems New Tasks

Jun 7, 2026cs.LG

Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks

One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to interference and forgetting of the previous ones. While several algorithms have been proposed to protect old memories from interference, they are typically applied during or immediately after each new episode of training. In contrast, humans and animals can learn continuously, acquiring multiple new memories during active learning before consolidating all of them into long-term storage. Here we show that multiple new tasks can be trained sequentially before an unsupervised sleep-like replay phase is applied to partially restore performance across all previously learned tasks. Our study further suggests that task-specific information remains resilient to new training but decays gradually as network is trained on new tasks. These findings point to novel principles for developing a broad range of continual learning AI solutions.

Anthony Bazhenov, Jean Erik Delanois, Giri P. Krishnan

Khoury College of Computer Sciences, Northeastern University, Boston, MA · Department of Medicine, University of California, San Diego, La Jolla, CA, USA · ARTISAN, Georgia Institute of Technology, Atlanta, GA USA

Catastrophic Forgetting Continual Learning Forgetting New Tasks

Jun 3, 2026cs.DS

Learning-Augmented Online Minimization with Dual Predictions

We present learning-augmented algorithms for two general classes of online minimization problems: metrical task systems and laminar set cover. Both algorithms achieve improved theoretical guarantees using machine-learned predictions of an optimal solution to the dual linear program. Unlike optimal primal solutions, which can change drastically under tiny instance perturbations, these dual solutions are much more stable, which ensures the existence of good (and learnable) predictions for families of similar instances. While previous work has used dual predictions in offline settings and for online maximization problems, our algorithms are, to the best of our knowledge, the first demonstration that such dual predictions can be effective for online minimization. Our theoretical results are complemented by experiments on the

k

-server problem and the parking permit problem.

Christian Coester, Alexa Tudose, Alexander Turoczy

University of Oxford, United Kingdom

Learning-Augmented Algorithms Flat Minima New Tasks

Jun 3, 2026cs.GR

Aggregating LLM-Based Weak Verifiers for Spatial Layout Generation

We present a pipeline for building and aggregating task-specific, LLM-generated weak (imperfect) verifiers into a strong verifier for spatial layout domains. Given a task description, our pipeline asks an LLM to synthesize a collection of verifier programs using a layout verification DSL. Each individual LLM-generated verifier usually provides an imperfect check for a match between the layout and the corresponding task description. We show that by aggregating the responses of many such verifiers we can produce a stronger verifier. Moreover, by applying techniques from weak learning, our pipeline can learn how to aggregate the weak verifiers from a very sparse set of human labeled example layouts (about 10). We find that the strong verifiers produced by our pipeline outperform the status-quo approach of using a set of LLM judges to directly check whether a layout matches a task description, raising F1-scores by up to 7X across a variety of 3D room layout and 2D poster design tasks. We also demonstrate that verifier-guided layout generation using natural language feedback from our strong verifiers improves layout quality of a base layout generator by up to 66.2% according to a human evaluator.

Sharon Zhang, R. Kenny Jones, Jiajun Wu +1

Stanford University, Stanford, California, USA · Roblox, San Mateo, California, USA

Layouts New Tasks

Jun 2, 2026cs.CL

CoEval: Ranking Language Models for Custom Tasks Without Labeled Data or Trustworthy Benchmarks

Selecting a pretrained language model, or evaluating a fine-tuned one, for a specific application is a high-value decision, yet the public benchmarks used to make it are poorly suited: a generic benchmark need not reflect a particular sub-domain or sub-task, and its scores are suspect when its items have leaked into pretraining and are recalled rather than solved. We present CoEval, an open framework that supplies a trustworthy, task-specific signal through ensemble self-evaluation: from a task or domain description, a pool of models rotates through all three roles, teacher, student, and judge, to generate a fresh, contamination-free benchmark, answer it, and score one another, with no human labels or raters. Because every model also answers as a student, the responses are the data that weight each question by its discriminative power and each judge by its consensus with the panel. Where ground truth exists, CoEval recovers the true ranking and tracks objective correctness at \r{ho}=0.86, and the weighting recovers the gold ranking of thirteen models at Spearman 0.95. Reliability comes from panel composition, not size: this label-free weighting zeroes out broken judges and down-weights saturated questions, so neither distorts the ranking. Generated items show zero verbatim overlap with five public benchmarks, the panel cancels verbosity bias and precludes same-family self-preference, and rankings are domain-specific: three different models top four de-novo domains, so a generic leaderboard misdirects most practitioners. The same pipeline reruns on each model release, giving any team a contamination-free leaderboard for its application.

Alexander Apartsin, Yehudit Aperstein

Holon Institute of Technology, Israel · Afeka Tel Aviv Academic College of Engineering, Israel

Language Modeling Leaderboard New Tasks

Jun 2, 2026cs.AI

DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Collaboration

Real-world professional desktop workflows in specialized creative and engineering software unfold over long horizons and often require human-in-the-loop coordination, where agents proactively seek necessary information and users provide additional instructions, clarifications, feedback, or corrections as the task progresses. Yet existing desktop GUI benchmarks mostly reduce this setting to short, simplified tasks with all user instructions provided upfront. To address this issue, we introduce DeskCraft, a desktop GUI benchmark targeting long horizon creative and engineering workflows and proactive human-agent collaboration. DeskCraft organizes tasks into a multilevel difficulty taxonomy, with long horizon tasks requiring over 50 execution steps, and covers professional creative software across design, video, audio, and 3D creation. Furthermore, DeskCraft formalizes human-agent collaboration into an interaction protocol covering mid-turn and post-turn exchanges. Mid-turn interaction captures both agent-initiated clarification under uncertainty and user-initiated interruption during execution, while post-turn interaction accommodates user-driven feedback after the agent signals completion, together spanning the full space of realistic collaboration patterns. We evaluate 18 proprietary and open source agents on 538 tasks and find that GPT-5.4 reaches 31.6% on standard tasks and 27.6% on interactive tasks. Further analyses reveal persistent failures in long horizon workflow delivery and proactive clarification. We will open-source all evaluation codes, tasks, and data at https://github.com/mrwwk/DeskCraft.

Wenkai Wang, Tao Xiong, Jingchen Ni +6

1Zhejiang University · 2Tsinghua University · 3Tencent +1

Agentic Workflow Design New Tasks Craft Long-Horizon Task Planning

May 29, 2026stat.ML

Hedging on the Frontier: Learning New Tasks with Few Samples

When a learner faces a new task with few samples, it must leverage any available side information. In practice, this often comes in the form of model evaluations on related tasks in public benchmarks. A key question then is how to model task relatedness such that it is both realistic and the benchmark evaluations lead to provable gains. Empirically, we observe that weak monotonicity is often approximately satisfied: if a model dominates another on many benchmarks, it also tends to outperform on the new task. We explore the statistical complexity of learning under (approximate) weak monotonicity, leveraging it within two learning paradigms: transfer learning and model selection aggregation. We show that not only can we prune the model class based on monotonicity, but we can also further adapt to the geometry of the available trade-offs by hedging on the frontier.

Tobias Wegel, Federico Di Gennaro, Geelon So +1

Department of Computer Science, ETH Zurich · Department of Computer Science and Engineering, UC San Diego

Learnability Monotonicity Transfer Learning Frontiers Model Selection New Tasks+1

May 28, 2026cs.LG

Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation

Modern learning systems excel at interpolation but struggle to generalize to unseen tasks outside the training distribution's support. This failure occurs even in simple settings, such as handling task parameters beyond the training range, and persists despite advances in foundation models. To this end, we develop the Relational Task Extrapolator (RTE), an algorithm designed to enable systematic extrapolation to novel tasks. The key observation is that extrapolation is inherently relational: extrapolating to unseen tasks requires learning how tasks transform into one another. If a model learns the transformation between tasks A and B during training, it can apply that same transformation to relate known tasks to unseen ones at test time. RTE operationalizes this idea by decomposing each target task into a known anchor task and a transformation linking the anchor and target. It then learns a relational operator, mapping an anchor-transformation pair to predictions for the target task. We instantiate RTE across multiple task extrapolation regimes in function prediction, e.g. where target tasks use out-of-range parameters (parameter extrapolation), have greater compositional depth (length extrapolation), and/or recombine function primitives in unseen ways (compositional extrapolation). We further extend RTE to sequence prediction, integrating it into fine-tuning algorithms for foundation models. Across empirical studies, we find that RTE substantially outperforms existing approaches on extrapolation to novel, unseen tasks.

Adam Ousherovitch, Yixin Wang

Department of Statistics, University of Michigan, Ann Arbor.

Extrapolation Efficient Task Adaptation New Tasks Relational

May 24, 2026cs.AI

Meta-Agent: From Task Descriptions to Verified Multi-Agent Systems

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while insufficient grounding and weak verification mechanisms further limit reliability. We present Meta-Agent, a two-phase framework that automatically constructs and executes specialized multi-agent systems from natural-language task descriptions. In the construction phase, a task planner decomposes a problem into a directed acyclic graph of agent specifications with explicit input/output contracts and verification criteria. A web search module grounds each specification with external evidence, and a code generation module produces system prompts and tool configurations. A construction-time verification stage then validates generated artifacts and triggers targeted regeneration when failures are detected. In the execution phase, a coordinator dispatches subtasks across the agent graph while execution-time verification gates intermediate outputs. We further introduce a three-level error attribution mechanism that distinguishes local, upstream, and structural failures, enabling targeted recovery strategies ranging from localized retries to partial re-execution and re-decomposition. We evaluate Meta-Agent across coding, contextual learning, and open-ended reasoning tasks. Experiments against strong multi-agent baselines and ablation studies demonstrate consistent improvements in task success rate, error recovery, and workflow stability. The results highlight the importance of tightly integrating planning, grounding, and verification for building reliable multi-agent systems.

Andy Xu, Yu-Wing Tai

Dartmouth College

Model-Based Multi-Agent Systems New Tasks

May 22, 2026physics.chem-ph

Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs

Machine learning interatomic potentials (MLIPs) require generating computationally expensive, large-scale training datasets to accurately simulate materials and molecules. Incorporating electronic structure information using multitask learning improves sample efficiency, however, training on full Hamiltonian matrices, which scale quadratically with the number of atoms, is intractable for large datasets. In this work, we show that multitask learning utilizing orbitally resolved semiempirical charges significantly improves sample efficiency and accuracy in MLIPs. To efficiently predict orbital charges, we implement a specialized equivariant model, reducing charge prediction error compared to an invariant baseline. By augmenting training with computationally inexpensive GFN1-xTB orbital charges, which scale linearly with the number of atoms, our model achieves a 46% reduction in energy mean absolute error and requires five times less data to match the performance of energy-only models. Furthermore, our approach outperforms models trained on expensive density functional theory (DFT) atomic charges, capturing orbitally resolved electronic complexity and forcing the network to learn a physically accurate latent space that spontaneously clusters metals by shared chemical properties. Because orbital charges are only required during training, this approach preserves inference efficiency, providing a scalable recipe for developing accurate, data-efficient foundation models for complex chemical systems.

Ihor Neporozhnii, Sjoerd Hoogland, Oleksandr Voznyy

Department of Physical and Environmental Sciences, University of Toronto, 1065 Military Trail, Toronto, M1C 1A4, Ontario, Canada. · The Alliance for AI-Accelerated Materials Discovery, 10 King’s College Road, Toronto, M5S 3G4, Ontario, Canada. · Department of Electrical and Computer Engineering, University of Toronto, 10 King’s College Road, Toronto, M5S 3G4, Ontario, Canada.

Interatomic Potentials Quantum Chemistry Multi--Task Learning Near-Earth Objects New Tasks

May 20, 2026cs.LG

Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling

Computer-use agents (CUAs) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click, type, and scroll on a browser. Current implementations follow a sequential fetch-screenshot-execute loop where each iteration requires an LLM call, resulting in high latency and frequent errors from incorrect tool use. We present agent just-in-time (JIT) compilation, a system that compiles task descriptions directly into executable code that may include LLM calls, tool calls, and parallelization. Our approach comprises three components: (1) JIT-Planner, which generates multiple code plans, validates each against tool specifications, and selects the minimum-cost candidate; (2) JIT-Scheduler, which explores parallelization strategies via Monte Carlo cost estimation from learned latency distributions; and (3) an invariant-enforcing tool protocol specifying precondition and postcondition requirements to reduce the rate of incorrect tool use. Across five applications, JIT-Planner achieves

10.4\times

speedup and 28

\%

higher accuracy over Browser-Use, while JIT-Scheduler achieves

2.4\times

speedup and 9% higher accuracy over OpenAI CUA.

Caleb Winston, Ron Yifeng Wang, Azalia Mirhoseini +1

Stanford University, Stanford, CA, USA.

Smooth Execution New Tasks

May 14, 2026cs.AI

Herculean: An Agentic Benchmark for Financial Intelligence

As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional work. Existing financial benchmarks offer only a partial view of this ability, as they primarily evaluate static competencies such as question answering, retrieval, summarization, and classification. We introduce Herculean, the first skilled benchmark for agentic financial intelligence spanning four representative workflows, including Trading, Hedging, Market Insights, and Auditing. Each workflow is instantiated as a standardized MCP-based skill environment with its own tools, interaction dynamics, constraints, and success criteria, enabling consistent end-to-end assessment of heterogeneous agent systems. Across frontier agents, we find agents perform relatively well on Trading and Market Insights, but struggle substantially on Hedging and Auditing, where long-horizon coordination, state consistency, and structured verification are critical. Overall, our results point to a key gap in current agents in turning financial reasoning into dependable workflow execution in high-stakes financial workflows.

Xueqing Peng, Zhuohan Xie, Yupeng Cao +60

Financial Question Answering Agentic Workflows Agentic Benchmarks Artificial Intelligence Agents Agentic New Tasks

May 4, 2026stat.ML

Active multiple matrix completion with adaptive confidence sets

In this work, we formulate a new multi-task active learning setting in which the learner's goal is to solve multiple matrix completion problems simultaneously. At each round, the learner can choose from which matrix it receives a sample from an entry drawn uniformly at random. Our main practical motivation is market segmentation, where the matrices represent different regions with different preferences of the customers. The challenge in this setting is that each of the matrices can be of a different size and also of a different rank which is unknown. We provide and analyze a new algorithm, MAlocate that is able to adapt to the unknown ranks of the different matrices. We then give a lower-bound showing that our strategy is minimax-optimal and demonstrate its performance with synthetic experiments.

Andrea Locatelli, Alexandra Carpentier, Michal Valko

OvGU Magdeburg · SequeL team, Inria Lille

Tensor Completion Matrix Active Learning Repair-Assignment Problem New Tasks

May 1, 2026cs.LG

A Comparative Study of QSPR Methods on a Unique Multitask PAMPA dataset

We present a unique, multitask dataset comprising 143 drug and drug candidate molecules, each evaluated on in vitro, parallel artificial-membrane permeability assays (PAMPA) using six different model membranes. Using this resource, we systematically assess the effectiveness of various molecular descriptors and regression models in predicting passive membrane permeability. The studied models range from simple linear regression to a modern pre-trained transformer architecture. Particular attention is given to the trade-off between predictive performance and model interpretability, highlighting the challenges introduced by machine learning approaches. To our knowledge, this is the most comprehensive study on simultaneous modeling of multiple organ-specific PAMPA membranes to date, offering novel insights into membrane-specific permeability profiles. We found that expert-designed physico-chemical property descriptors are more fitting for a limited sample size permeabilty study than deep learning based representations.

Andrs Formanek, Anna Vincze, Richrd Bicsak +3

Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems,May Signal Processing and Data Analytics, KU Leuven, 3001 Leuven, Belgium · Department of Artificial Intelligence and Systems Engineering, Faculty of Electrical Engineering and Informatics, Budapest University of Technology and Economics, Műegyetem rkp. 3, H-1111 Budapest, Hungary[cs.LG] · Department of Chemical and Environmental Process Engineering, Faculty of Chemical Technology and Biotechnology, Budapest University of Technology and Economics, Műegyetem rkp. 3, H-1111 Budapest, Hungary +2

Molecular Property Prediction Deep Learning New Tasks Comparison

Apr 30, 2026cs.AI

WindowsWorld: A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments

While GUI agents have shown impressive capabilities in common computer-use tasks such as OSWorld, current benchmarks mainly focus on isolated and single-application tasks. This overlooks a critical real-world requirement of coordinating across multiple applications to accomplish complex profession-specific workflows. To bridge this gap, we present a computer-use benchmark in cross-application workflows, named WindowsWorld, designed to systematically assess GUI Agents on complex multi-step tasks that mirror real-world professional activities. Our methodology uses a multi-agent framework steered by 16 occupations to generate four difficulty-level tasks with intermediate inspection, which are then refined by human review and executed in a simulated environment. The resulting benchmark contains 181 tasks with an average of 5.0 sub-goals across 17 common desktop applications, of which 78% are inherently multi-application. Experimental results of leading large models and agents show that: 1) All computer-use agents perform poorly on multi-application tasks (< 21% success rate), far below the performance of simple single-app tasks; 2) They largely fail at tasks requiring conditional judgment and reasoning across

\geq

3 applications, stalling at early sub-goals; 3) Low execution efficiency, where tasks often fail despite far exceeding human step limits. Code, benchmark data, and evaluation resources are available at github.com/HITsz-TMG/WindowsWorld.

Jinchao Li, Yunxin Li, Chenrui Zhao +3

Harbin Institute of Technology, Shenzhen · Shenzhen Loop Area Institute

Graphical User Interface Agents New Tasks Dynamic Environments

Apr 27, 2026cs.SE

Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis

Large language models are widely used for code generation, yet they rely on an implicit assumption that the task descriptions are sufficiently detailed and well-formed. However, in practice, users may provide defective descriptions, which can have a strong effect on code correctness. To address this issue, we develop SpecValidator, a lightweight classifier based on a small model that has been parameter-efficiently finetuned, to automatically detect task description defects. We evaluate SpecValidator on three types of defects, Lexical Vagueness, Under-Specification and Syntax-Formatting on 3 benchmarks with task descriptions of varying structure and complexity. Our results show that SpecValidator achieves defect detection of F1 = 0.804 and MCC = 0.745, significantly outperforming GPT-5-mini (F1 = 0.469 and MCC = 0.281) and Claude Sonnet 4 (F1 = 0.518 and MCC = 0.359). Perhaps more importantly, our analysis indicates that SpecValidator can generalize to unseen issues and detect unknown Under-Specification defects in the original (real) descriptions of the benchmarks used. Our results also show that the robustness of LLMs in task description defects depends primarily on the type of defect and the characteristics of the task description, rather than the capacity of the model, with Under-Specification defects being the most severe. We further found that benchmarks with richer contextual grounding, such as LiveCodeBench, exhibit substantially greater resilience, highlighting the importance of structured task descriptions for reliable LLM-based code generation.

Amal Akli, Mike Papadakis, Maxime Cordy +1

University of Luxembourg Luxembourg

Code Generation Large Language Model Generation Defect Detection Validation New Tasks

Apr 26, 2026cs.CV

ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

Language-model agents are increasingly used as persistent coworkers that assist users across multiple working days. During such workflows, the surrounding environment may change independently of the agent: new emails arrive, calendar entries shift, knowledge-base records are updated, and evidence appears across images, scanned PDFs, audio, video, and spreadsheets. Existing benchmarks do not adequately evaluate this setting because they typically run within a single static episode and remain largely text-centric. We introduce \bench{}, a benchmark for coworker agents built around multi-turn multi-day tasks, a stateful sandboxed service environment whose state evolves between turns, and rule-based verification. The current release contains 100 tasks across 13 professional scenarios, executed against five stateful sandboxed services (filesystem, email, calendar, knowledge base, spreadsheet) and scored by 1537 deterministic Python checkers over post-execution service state; no LLM-as-judge is invoked during scoring. We benchmark seven frontier agent systems. The strongest model reaches 75.8 weighted score, but the best strict Task Success is only 20.0%, indicating that partial progress is common while complete end-to-end workflow completion remains rare. Turn-level analysis shows that performance drops after the first exogenous environment update, highlighting adaptation to changing state as a key open challenge. We release the benchmark, evaluation harness, and construction pipeline to support reproducible coworker-agent evaluation.

Fanqing Meng, Lingxiao Du, Zijian Wu +46

Agentic Benchmarks Claw-Like Agent Agentic Workflow Design New Tasks

Apr 16, 2026cs.LG

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifiers. We study this phenomenon on inductive reasoning tasks, where models must induce and output logical rules. We find that RLVR-trained models systematically abandon rule induction. Instead of learning generalizable patterns (e.g., ``trains carrying red cars go east''), they enumerate instance-level labels, producing outputs that pass verifiers without capturing the relational patterns required by the task. We show that this behavior is not a failure of understanding but a form of reward hacking: imperfect verifiers that check only extensional correctness admit false positives. To detect such shortcuts, we introduce Isomorphic Perturbation Testing (IPT), which evaluates a single model output under both extensional and isomorphic verification, where the latter enforces invariance under logically isomorphic tasks. While genuine rule induction remains invariant, shortcut strategies fail. We find that shortcut behavior is specific to RLVR-trained reasoning models (e.g., GPT-5, Olmo3) and absent in non-RLVR models (e.g., GPT-4o, GPT-4.5, Ministral). Moreover, shortcut prevalence increases with task complexity and inference-time compute. In controlled training experiments, extensional verification directly induces shortcut strategies, while isomorphic verification eliminates them. These results show that RLVR can incentivize reward hacking not only through overt manipulation but also by exploiting what the verifier fails to enforce.

Lukas Helff, Quentin Delfosse, David Steinmann +6

TU Darmstadt · DFKI · Intrinsic +4

Reinforcement Learning With Verifiable Reward Verifiable Rewards LLM Reasoning Strategies Induction New Tasks

Mar 13, 2026cs.LG

A Multitask Large Reasoning Model for Molecular Science

Artificial intelligence in molecular science must move beyond pattern recognition toward chemically valid and interpretable reasoning. We present a task-adaptive large reasoning model that integrates chemical knowledge through a synergistic multispecialist architecture, chain-of-thought supervision, and molecule-informed reinforcement learning. Task-conditioned routing coordinates prediction and inference specialists across 10 molecular tasks spanning molecular description and generation, nomenclature translation, property prediction, and reaction prediction. The model outperforms more than 20 general-purpose and molecular large language models, improves aggregate performance over the base model by 50.3%, and surpasses the leading molecular multitask baseline on most tasks. Analyses of specialist representations and reasoning pathways reveal task-specific adaptation while retaining interpretable chemical inference. A case study further demonstrates an integrated workflow for central nervous system candidate generation, property screening, molecular interpretation, and retrosynthetic planning. These results demonstrate a versatile multi-task framework for knowledge-guided molecular reasoning and design, with the potential to serve as a core task engine for future molecular science agents.

Pengfei Liu, Shuang Ge, Xiaobo Wang +6

Guangzhou Key Laboratory of Forensic Multi-Omics for Precision Identification, Southern Medical University, Guangzhou, Guangdong, 510515, China · Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, Guangdong 518000, China · Guangdong Provincial Key Laboratory of Psychoactive Substances Monitoring and Safety, Anti-Drug Technology Center of Guangdong Province (National Anti-Drug Laboratory Guangdong Regional Center), Guangzhou, 510230, China +4

Moleculenet Large Reasoning Models LLM Reasoning Strategies New Tasks

Dec 19, 2025cs.CL

Narrative Consolidation: Formulating a New Task for Unifying Multi-Perspective Accounts

Processing overlapping narrative documents, such as legal testimonies or historical accounts, often aims not for compression but for a unified, coherent, and chronologically sound text. Standard Multi-Document Summarization (MDS), with its focus on conciseness, fails to preserve narrative flow. This paper formally defines this challenge as a new NLP task, Narrative Consolidation, focusing on chronological integrity, completeness, and the fusion of complementary details. We establish the resources needed to study it: a formal task definition, an evaluation paradigm, the Gospel Consolidation Language Resource -- a benchmark built from the four Biblical Gospels with 169 canonical events, cross-document alignments, and a reference consolidation -- and a suite of reference systems, ranging from timeline-agnostic heuristics to the Temporal Alignment Event Graph (TAEG). Benchmarking yields three findings. First, the explicit temporal backbone is the dominant factor: every system granted the canonical timeline raises ROUGE-L F1 from 0.206 to at least 0.81. Second, on a fusion-style reference, a simple length heuristic is remarkably strong (0.947 ROUGE-L F1), outperforming graph-based selection (0.846). Third, ablations show the discriminative signal resides in temporal edges, while intra-cluster lexical similarity is uninformative. These results establish Narrative Consolidation as a distinct task and pose an open challenge: to surpass that heuristic with a principled selection mechanism and true fusion of complementary details.

Roger A. Finger, Eduardo G. Cortes, Sandro J. Rigo +1

Graduate Program in Applied Computing Universidade do Vale do Rio dos Sinos São Leopoldo, Brazil

Narratives Summarization Multimodal Documents New Tasks

Feb 3, 2025cs.LG

Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization

As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key challenge. Current LLM agents, particularly those based on proprietary language models, typically rely on prompts to incorporate knowledge about the target tasks. This approach does not allow the agent to internalize this information and instead relies on ever-expanding prompts to sustain its functionality in diverse scenarios. This resembles a system of notes used by a person affected by anterograde amnesia, the inability to form new memories. In this paper, we propose a novel method to train AI agents to incorporate knowledge and skills for multiple tasks without the need for either cumbersome note systems or prior high-quality demonstration data. Our approach employs an iterative process where the agent collects new experiences, receives corrective feedback from humans in the form of hints, and integrates this feedback into its weights via a context distillation training procedure. We demonstrate the efficacy of our approach by implementing it in a Llama-3-based agent that, after only a few rounds of feedback, outperforms advanced models GPT-4o and DeepSeek-V3 in tasksets requiring correct sequencing of information retrieval, tool use, and question answering.

Minttu Alakuijala, Ya Gao, Georgy Ananov +4

Department of Computer Science, Aalto University · Department of Computer Science, University of Manchester · System 2 AI

Artificial Intelligence Agents Internalization New Tasks Memo Dataset Distillation Feedback