Prépublication
· 2026 arXiv
EN
Data agents built on ReAct-style loops now execute complex analytical workflows over structured data, yet their intermediate reasoning still runs almost entirely through text. Human analysts instead move between numbers, tables, and charts, reading visual evid...
Xinzhe Wang, Xudong Weng et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with context: longer drafts offer greater amortization when reliable,...
Emile Anand, Mohammed Rehan Parwani et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Modern distributed microservice deployments generate massive volumes of heterogeneous, multi-format observability logs across physically and logically partitioned infrastructure. Isolating root causes during cascading failures remains an arduous task for Site...
Jitendra Solanki, Anand Todkar et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Current evaluation of LLM-generated debate largely focuses on argumentative quality, leaving the value structure of generated arguments underexamined. We introduce a diagnostic metric framework for comparing how values are expressed and organized in human-refe...
Maoyuan Li, Haoyuan Li et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the kn...
Saaket Agashe, Yuzhe Yang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
RTL repair benchmarks should measure whether a model can fix broken RTL given a specification. To this end, we construct and hash-bind RTLRepairDataset, 5,784 (broken, fixed) training pairs; RTLRepairBench, 459 held-out cases with 374 syntactic and 85 behavior...
Yeyin Eva Zhu, Rishabh Ranawat
#cs.AI
Prépublication
· 2026 arXiv
EN
Meteorological downscaling is crucial for high-resolution regional climate forecasting and disaster early warning. While neural operators have emerged as a promising paradigm for modeling complex spatiotemporal mappings, existing frameworks often struggle with...
Yiqiang Ye, Yichi Wang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
A seemingly reasonable push in Sokoban can make the puzzle unsolvable. To avoid such mistakes, an agent has to anticipate the consequences of its actions before execution, especially when feedback from the real environment is sparse or actions are irreversible...
Jiaxin Ge, Junyi Zhang et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
The goal of a world model is to capture the dynamics of an environment. This has the great appeal that it allows agents to plan and simulate a course of actions with the help of a world model. For these uses to be reliable, however, the learned dynamics must b...
Heejeong Nam, Divyat Mahajan et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
LLM agents that compute the right answer can still answer wrongly. Agent harnesses increasingly keep long tool outputs out of the context window, saving them to files that the agent searches or reads on demand. We ask where this costs accuracy with a real scie...
Ke Zhang, Sahchit Chundur et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Frontier agents retrieve structural metadata well and compute geometry from coordinates less reliably. We ask how much of a benchmark score reflects that gap and how much reflects the evaluation configuration around the model. We study ProteinGeoBench, a suite...
Matt Turk, Brandon L. Neel et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and can introduce substantial security risks. We therefore propos...
Zhaoyang Wang, Qianhui Wu et al.
#cs.AI