- TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen · Apr 8, 2026 · Citations: 0
Red Team Automatic Metrics Long Horizon
As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces.
- When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang, Yankai Chen, Yue Zhou · Apr 1, 2026 · Citations: 0
Critique Edit Simulation Env Long Horizon
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as adding requirement or revising goals, during mid-task execution…
- SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
Philip Schroeder, Thomas Weng, Karl Schmeckpeper, Eric Rosen, Stephen Hart · Mar 30, 2026 · Citations: 0
Demonstrations Simulation Env Long Horizon
To address this limitation, we introduce SOLE-R1 (Self-Observing LEarner), a video-language reasoning model explicitly designed to serve as the sole reward signal for online RL.
- Signals: Trajectory Sampling and Triage for Agentic Interactions
Shuguang Chen, Adil Hafeez, Salman Paracha · Apr 1, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
We propose a lightweight, signal-based framework for triaging agentic interaction trajectories.
- ReDAct: Uncertainty-Aware Deferral for LLM Agents
Dzianis Piatrashyn, Nikita Kotelevskii, Kirill Grishchenkov, Nikita Glazkov, Ivan Nasonov · Apr 8, 2026 · Citations: 0
Simulation Env Long Horizon
Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems.
- FrontierFinance: A Long-Horizon Computer-Use Benchmark of Real-World Financial Tasks
Michael Krumdick, Varshini Reddy, Shivani Chaudhary, William Day, Maarij Ahmed · Apr 7, 2026 · Citations: 0
Rubric Rating Long Horizon
To address this, we introduce FrontierFinance, a long-horizon benchmark of 25 complex financial modeling tasks across five core finance models, requiring an average of over 18 hours of skilled human labor per task to complete.
- DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling
Shicheng Liu, Yucheng Jiang, Sajid Farook, Camila Nicollier Sanchez, David Fernando Castro Pena · Apr 7, 2026 · Citations: 0
Human Eval Long Horizon
Deep research with Large Language Model (LLM) agents is emerging as a powerful paradigm for multi-step information discovery, synthesis, and analysis.
- Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
He Du, Qiming Ge, Jiakai Hu, Aijun Yang, Zheng Cai · Mar 30, 2026 · Citations: 0
Critique Edit Long Horizon
We present Kernel-Smith, a framework for high-performance GPU kernel and operator generation that combines a stable evaluation-driven evolutionary agent with an evolution-oriented post-training recipe.
- Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation
Arthur Jakobsson, Abhinav Mahajan, Karthik Pullalarevu, Krishna Suresh, Yunchao Yao · Apr 23, 2026 · Citations: 0
Automatic MetricsSimulation Env Long Horizon
To mitigate this, we present a novel approach that leverages learned simulation priors to inform goal-conditioned dynamic manipulation of ropes for efficient and accurate task execution.
- Self-Debias: Self-correcting for Debiasing Large Language Models
Xuan Feng, Shuai Zhao, Luwei Xiao, Tianlong Gu, Bo An · Apr 9, 2026 · Citations: 0
Pairwise Preference Long Horizon
Unlike standard preference optimization which applies broad penalties, Self-Debias employs a fine-grained trajectory-level objective subject to dynamic debiasing constraints.
- Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
Shiwan Zhao, Zhihu Wang, Xuyang Zhao, Jiaming Zhou, Caiyue Xu · Apr 9, 2026 · Citations: 0
Pairwise Preference Long Horizon
Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods, distillation, and multi-stage pipelines.
- The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle
Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido, Alexander P. Christensen · Mar 30, 2026 · Citations: 0
Critique Edit Tool Use
Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin.
- FlowForge: A Staged Local Rollout Engine for Flow-Field Prediction
Xiaowen Zhang, Ziming Zhou, Fengnian Zhao, David L. S. Hung · Apr 21, 2026 · Citations: 0
Automatic Metrics Long Horizon
We introduce FlowForge, a staged local rollout engine that predicts future flow fields by compiling a locality-preserving update schedule and executing it with a shared lightweight local predictor.
- Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents
Khushal Sethi · Apr 9, 2026 · Citations: 0
Automatic Metrics Long Horizon
We introduce TrACE (Trajectorical Adaptive Compute via agrEement), a training-free controller that allocates LLM calls adaptively across agent timesteps by measuring inter-rollout action agreement.
- MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents
Shu Wang, Edwin Yu, Oscar Love, Tom Zhang, Tom Wong · Apr 6, 2026 · Citations: 0
Automatic Metrics Long Horizon
Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over…
- OSCAR: Orchestrated Self-verification and Cross-path Refinement
Yash Shah, Abhijit Chakraborty, Naresh Kumar Devulapally, Vishnu Lokhande, Vivek Gupta · Apr 2, 2026 · Citations: 0
Automatic Metrics Long Horizon
We introduce a suite of trajectory-level assessments, including a cross-chain divergence-at-hallucination (CDH) metric, for principled comparison of localization methods.
- S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
Jack Young · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval.
- Asymmetric Actor-Critic for Multi-turn LLM Agents
Shuli Jiang, Zhaoyang Zhang, Yi Zhang, Shuo Yang, Wei Xia · Mar 31, 2026 · Citations: 0
Automatic Metrics Long Horizon
In many real-world applications, agents must succeed in one-shot settings where retries are impossible.
- QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation
Mathilde Kappel, Mahdi Khoramshahi, Louis Annabi, Faiz Ben Amar, Stéphane Doncieux · Apr 24, 2026 · Citations: 0
Simulation Env Long Horizon
To do so, we propose a method based on Quality-Diversity algorithms that leverages sparse reward exploration in order to generate a set of diverse and high-performing trajectory primitives for a given manipulation task.
- Reliable Self-Harm Risk Screening via Adaptive Multi-Agent LLM Systems
Meghana Karnam, Ananya Joshi · Apr 24, 2026 · Citations: 0
Llm As Judge Long Horizon
Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression.
- TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
Xinliang Frederick Zhang, Lu Wang · Apr 9, 2026 · Citations: 0
Pairwise Preference Long Horizon
Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences.
- Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
Seyed Moein Abtahi, Rasa Rahnema, Hetkumar Patel, Neel Patel, Majid Fekri · Apr 23, 2026 · Citations: 0
Automatic Metrics Long Horizon
The transition from stateless language model inference to persistent, multi session autonomous agents has revealed memory to be a primary architectural bottleneck in the deployment of production grade agentic systems.
- PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
Zhifei Xie, Zongzheng Hu, Fangda Ye, Xin Zhang, Haobo Chai · Apr 9, 2026 · Citations: 0
Automatic Metrics Long Horizon
Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive agent: depth, complexity, ambiguity, precision and real-time constraints.
- Full-Duplex-Bench-v3: Benchmarking Tool Use for Full-Duplex Voice Agents Under Real-World Disfluency
Guan-Ting Lin, Chen Chen, Zhehuai Chen, Hung-yi Lee · Apr 6, 2026 · Citations: 0
Automatic Metrics Tool Use
We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use.
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Chenxi Wang, Zhuoyun Yu, Xin Xie, Wuguannan Yao, Runnan Fang · Apr 6, 2026 · Citations: 0
Automatic Metrics Long Horizon
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…
- $\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution
Muyu He, Adit Jain, Anand Kumar, Vincent Tu, Soumyadeep Bakshi · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from delayed feedback, and adapting when early mistakes compound.
- Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Meng Chu, Xuan Billy Zhang, Kevin Qinghong Lin, Lingdong Kong, Jize Zhang · Apr 24, 2026 · Citations: 0
Simulation Env Long Horizon
Agents that manipulate objects, navigate software, coordinate with others, or design experiments require predictive environment models, yet the term world model carries different meanings across research communities.
- Joint Optimization of Reasoning and Dual-Memory for Self-Learning Diagnostic Agent
Bingxuan Li, Simo Du, Yue Guo · Apr 8, 2026 · Citations: 0
Automatic Metrics Long Horizon
We propose SEA, a self-learning diagnostic agent with cognitively inspired dual-memory module.
- SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning
Zhengyang Ai, Zikang Shan, Xiaodong Ai, Jingxian Tang, Hangkai Hu · Apr 8, 2026 · Citations: 0
Automatic Metrics Long Horizon
Extensive experiments in math reasoning across three base models and five benchmarks demonstrate that SHAPE achieves an average accuracy gain of 3% with 30% reduced token consumption.
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song, Mao Zheng · Apr 2, 2026 · Citations: 0
Automatic Metrics Long Horizon
Evaluated across five benchmarks and two model scales, SRPO achieves both the rapid early improvement of SDPO and the long-horizon stability of GRPO.
- LEO: Graph Attention Network based Hybrid Multi Sensor Extended Object Fusion and Tracking for Autonomous Driving Applications
Mayank Mayank, Bharanidhar Duraisamy, Florian Geiss · Apr 2, 2026 · Citations: 0
Automatic Metrics Long Horizon
Evaluations on the Mercedes-Benz DRIVE PILOT SAE L3 dataset demonstrate real-time computational efficiency suitable for production systems; additional validation on public datasets such as View of Delft (VoD) further confirms cross-dataset…
- Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming
Qianfan Zhang, Tianyu Guo, Xuandi Ren, Jiale Chen, Ming Ding · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
During RL training, we observe an approximately log-linear relationship between validation accuracy and the average number of generated reasoning tokens over successive checkpoints, and show two ways to shift this training trajectory:…
- TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
Lingjie Chen, Ruizhong Qiu, Yuyu Fan, Yanjun Zhao, Hanghang Tong · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive…
- AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
Zhaopeng Feng, Liangcai Su, Zhen Zhang, Xinyu Wang, Xiaotian Zhang · Mar 29, 2026 · Citations: 0
Automatic Metrics Long Horizon
As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck.
- Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
Jiawei Chen, Ruoxi Xu, Boxi Cao, Ruotong Pan, Yunfei Zhang · Apr 9, 2026 · Citations: 0
Simulation Env Long Horizon
However, existing benchmarks remain constrained to isolated scenarios, narrow action spaces, or synthetic data, failing to capture the holistic nature of authentic human behavior.
- From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems
Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank Köster, Sven Hallerbach · Apr 2, 2026 · Citations: 0
Simulation Env Long Horizon
While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards.
- Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
Wenhao Yuan, Chenchen Lin, Jian Chen, Jinfeng Xu, Xuehe Wang · Apr 9, 2026 · Citations: 0
Automatic Metrics Long Horizon
In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory.
- Cognitive Loop of Thought: Reversible Hierarchical Markov Chain for Efficient Mathematical Reasoning
Jia-Chen Zhang, Zheng Zhou, Yu-Jie Xiong · Apr 8, 2026 · Citations: 0
Automatic Metrics Long Horizon
Inspired by human cognitive processes, we introduce a backward verification mechanism at each hierarchical layer.
- AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
Yuanfu Sun, Kang Li, Dongzhe Fan, Jiajin Liu, Qiaoyu Tan · Apr 7, 2026 · Citations: 0
Automatic Metrics Tool Use
To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference.
- Novel Memory Forgetting Techniques for Autonomous AI Agents: Balancing Relevance and Efficiency
Payal Fofadiya, Sunil Tiwari · Apr 2, 2026 · Citations: 0
Automatic Metrics Long Horizon
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation.
- HippoCamp: Benchmarking Contextual Agents on Personal Computers
Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen · Apr 1, 2026 · Citations: 0
Automatic Metrics Tool Use
We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management.
- Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
Ashish Rana, Chia-Chien Hung, Qumeng Sun, Julian Martin Kunkel, Carolin Lawrence · Mar 31, 2026 · Citations: 0
Automatic Metrics Long Horizon
Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues.
- Hierarchical Chain-of-Thought Prompting: Enhancing LLM Reasoning Performance and Efficiency
Xingshuai Huang, Derek Li, Bahareh Nikpour, Parsa Omidi · Mar 31, 2026 · Citations: 0
Automatic Metrics Long Horizon
Extensive evaluations across diverse LLMs and mathematical reasoning benchmarks show that Hi-CoT consistently improves average accuracy by 6.2% (up to 61.4% on certain models and tasks) while reducing reasoning trace length by 13.9%…
- Iterative Model-Learning Scheme via Gaussian Processes for Nonlinear Model Predictive Control of (Semi-)Batch Processes
Tai Xuan Tan, Alexander Mitsos, Eike Cramer · Apr 24, 2026 · Citations: 0
Long Horizon
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- CLVAE: A Variational Autoencoder for Long-Term Customer Revenue Forecasting
Jeffrey Näf, Riana Valera Mbelson, Markus Meierer · Apr 24, 2026 · Citations: 0
Long Horizon
Across multiple real-world datasets and prediction horizons, the proposed model improves upon the latest benchmarks.
- From graphemic dependence to lexical structure: a Markovian perspective on Dante's Commedia
Angelo Maria Sabatini · Apr 24, 2026 · Citations: 0
Long Horizon
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
Jichao Wang, Liuyang Bian, Yufeng Zhou, Han Xiao, Yue Pan · Apr 24, 2026 · Citations: 0
Long Horizon
As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation.
- Selective Contrastive Learning For Gloss Free Sign Language Translation
Changhao Lai, Rui Zhao, Xuewen Zhong, Jinsong Su, Yidong Chen · Apr 24, 2026 · Citations: 0
Long Horizon
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Reliability Auditing for Downstream LLM tasks in Psychiatry: LLM-Generated Hospitalization Risk Scores
Shevya Pandya, Shinjini Bose, Ananya Joshi · Apr 23, 2026 · Citations: 0
Long Horizon
We propose an approach for reliability auditing downstream LLM tasks by structuring evaluation around the impact of prompt design and the inclusion of medically insignificant inputs on predicted hospitalization risk scores, which is often…
- OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
Wenbo Hu, Xin Chen, Yan Gao-Tian, Yihe Deng, Nanyun Peng · Apr 9, 2026 · Citations: 0
Long Horizon
Extensive evaluations across 18 diverse benchmarks demonstrate its superior performance over strong open-source and leading proprietary frontier models.
- ClawBench: Can AI Agents Complete Everyday Online Tasks?
Yuxuan Zhang, Yubo Wang, Yipeng Zhu, Penghui Du, Junwen Miao · Apr 9, 2026 · Citations: 0
Long Horizon
AI agents may be able to automate your inbox, but can they automate other routine aspects of your life?
- When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
Ruotao Xu, Yixin Ji, Yu Luo, Jinpeng Li, Dong Li · Apr 9, 2026 · Citations: 0
Long Horizon
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning
Yifei Gong, Xing Wu, Wenda Liu, Kang Tu · Apr 9, 2026 · Citations: 0
Long Horizon
We propose ToolCAD, a novel agentic CAD framework deploying LLMs as tool-using agents for text-to-CAD generation.
- Data Selection for Multi-turn Dialogue Instruction Tuning
Bo Li, Shikun Zhang, Wei Ye · Apr 9, 2026 · Citations: 0
Long Horizon
MDS outperforms strong single-turn selectors, dialogue-level LLM scorers, and heuristic baselines on three multi-turn benchmarks and an in-domain Banking test set, achieving the best overall rank across reference-free and reference-based…
- DTCRS: Dynamic Tree Construction for Recursive Summarization
Guanran Luo, Zhongquan Jian, Wentao Qiu, Meihong Wang, Qingqiang Wu · Apr 8, 2026 · Citations: 0
Long Horizon
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.