Prépublication
· 2026 arXiv
EN
While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a setting where agents interpret underspecified requests to construct and iteratively revise...
Wenqian Zhang, Yangyi Huang et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Multimodal reinforcement learning with verifiable rewards (RLVR) provides reliable task-level supervision, yet offers limited guidance for localizing errors in visual reasoning. On-policy self-distillation (OPSD) complements this supervision with dense token-l...
Shiao Xie, Siyu Chen et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-robot approaches to multi-robot settings often fails to ensure safety and efficiency, espec...
Zehao Wang, Jianpeng Yao et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a five-axis metric: First-Attempt Performance, Efficiency, Succ...
Zekai Li, Jiayi Yu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities can degrade previously acquired ones, resulting in catastrophic forgetting. As a trajectory unfolds, different stages...
Rui Shi, Xunjian Yin et al.
#cs.LG
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
Systems that combine several large language models (LLMs) often use one context for many questions. When the context is passed between models as text, the receiving model processes all of its tokens again for every question. Avoiding this cost requires a conte...
Huawei Lin, Jinting Liu et al.
#cs.CL
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
We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associations while modifying...
Anamaria-Roberta Hartl, Levente Zólyomi et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
Many modern language models have adopted hybrid architectures that incorporate both linear-time recurrence and softmax attention. Modern recurrence layers provide a highly expressive mixing mechanism while ensuring high throughput by compressing contextual inf...
Xingyu Shen, Yingfa Chen et al.
#cs.CL
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