Tag: Long Horizon

Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng · Feb 25, 2026 · Citations: 0

• Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks.
• This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data, and the direct adoption of generic post-training pipelines that overlook the unique challenges of GUI agents.

Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren Hunt, Zijian Wang · Feb 25, 2026 · Citations: 0

• Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration.

Shunsuke Ubukata · Feb 25, 2026 · Citations: 0

Tomoya Kawabe, Rin Takano · Feb 25, 2026 · Citations: 0

• We present a hierarchical multi-agent LLM-based planner with prompt optimization: an upper layer decomposes tasks and assigns them to lower-layer agents, which generate PDDL problems solved by a classical planner.
• When plans fail, the system applies TextGrad-inspired textual-gradient updates to optimize each agent's prompt and thereby improve planning accuracy.

Chenyv Liu, Wentao Tan, Lei Zhu, Fengling Li, Jingjing Li, Guoli Yang · Feb 25, 2026 · Citations: 0

• Reinforcement learning enhances physical grounding through exploration yet typically relies on external reward signals that remain isolated from the agent's internal states.
• Evaluations on challenging robot manipulation tasks from simulation benchmarks and real-world settings demonstrate that SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher s

Kangning Shen, Jingyuan Zhang, Chenxi Sun, Wencong Zeng, Yang Yue · Feb 25, 2026 · Citations: 0

• Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.
• Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.

Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han · Feb 25, 2026 · Citations: 0

• Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks.
• Through this fine-grained analysis, we distill a unified perspective on ARL and propose SAMPO, a stable agentic policy optimization method designed to mitigate the dominant sources of instability in ARL.

Yue Yang, Shuo Cheng, Yu Fang, Homanga Bharadhwaj, Mingyu Ding, Gedas Bertasius · Feb 25, 2026 · Citations: 0

• We introduce a 21-task simulation benchmark consisting of two challenging suites: LIBERO-Long++ and Ultra-Long.
• Furthermore, real-world evaluations across 8 long-horizon tasks demonstrate an average success rate of 85%.

Xiaoke Huang, Bhavul Gauri, Kam Woh Ng, Tony Ng, Mengmeng Xu, Zhiheng Liu · Feb 25, 2026 · Citations: 0

• On cross-family OOD evaluation, VecGlypher substantially outperforms both general-purpose LLMs and specialized vector-font baselines for text-only generation, while image-referenced generation reaches a state-of-the-art performance, with ma

Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti · Feb 24, 2026 · Citations: 0

• However, a critical gap remains for their deployment in safety-critical domains: the lack of formal guarantees that generated samples will satisfy hard constraints.
• We address this by proposing a safety filtering framework that acts as an online shield for any pre-trained generative model.

Dmitrii Pantiukhin, Ivan Kuznetsov, Boris Shapkin, Antonia Anna Jost, Thomas Jung, Nikolay Koldunov · Feb 24, 2026 · Citations: 0

• Here we present PANGAEA-GPT, a hierarchical multi-agent framework designed for autonomous data discovery and analysis.
• Unlike standard Large Language Model (LLM) wrappers, our architecture implements a centralized Supervisor-Worker topology with strict data-type-aware routing, sandboxed deterministic code execution, and self-correction via execution feedbac

Yining Hong, Huang Huang, Manling Li, Li Fei-Fei, Jiajun Wu, Yejin Choi · Feb 24, 2026 · Citations: 0

• Drawing upon human reflective practitioners, we introduce Reflective Test-Time Planning, which integrates two modes of reflection: \textit{reflection-in-action}, where the agent uses test-time scaling to generate and score multiple candidat
• We also include retrospective reflection, allowing the agent to re-evaluate earlier decisions and perform model updates with hindsight for proper long-horizon credit assignment.

Victor Reijgwart, Cesar Cadena, Roland Siegwart, Lionel Ott · Feb 24, 2026 · Citations: 0

Dengjia Zhang, Xiaoou Liu, Lu Cheng, Yaqing Wang, Kenton Murray, Hua Wei · Feb 24, 2026 · Citations: 0

• Large language models (LLMs) are increasingly deployed as multi-step decision-making agents, where effective reward design is essential for guiding learning.
• We introduce SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards, a reinforcement learning framework that incorporates uncertainty directly into the reward design.

Yanna Jiang, Delong Li, Haiyu Deng, Baihe Ma, Xu Wang, Qin Wang · Feb 24, 2026 · Citations: 0

• Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably.
• This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies.

Hyeonje Choi, Jeongsoo Lee, Hyojun Lee, Jay-Yoon Lee · Feb 24, 2026 · Citations: 0

• We introduce \ToolMATH, a math-grounded benchmark that evaluates tool-augmented language models in realistic multi-tool environments where the output depends on calling schema-specified tools and sustaining multi-step execution.
• It turns math problems into a controlled, correctness-checkable benchmark with tool sets, enabling systematic evaluation of model reliability under (1) large, overlapping tool catalogs and (2) the absence of the intended capability.

Che Wang, Fuyao Zhang, Jiaming Zhang, Ziqi Zhang, Yinghui Wang, Longtao Huang · Feb 24, 2026 · Citations: 0

• Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution.
• Existing defenses typically rely on strict filtering or refusal mechanisms, which suffer from a critical limitation: over-refusal, prematurely terminating valid agentic workflows.

W. Frederick Zimmerman · Feb 24, 2026 · Citations: 0

Alex Stein, Furong Huang, Tom Goldstein · Feb 24, 2026 · Citations: 0

• Held-out in-domain accuracy under asymmetric evaluation improves from 46.0\% to 62.0\%, and average (maj@8) accuracy on public document-free math benchmarks improves from 20.2\% to 35.4\%.

Yue Pan, Xingyao Wang, Hanyue Zhang, Liwei Liu, Changxin Li, Gang Yang · Feb 23, 2026 · Citations: 0

• The model's high sensitivity was further corroborated by additional follow-up data, confirming its efficacy in predicting HF deterioration and its potential to secure patient safety in remote, home-based settings.