Can AI agents organize scientific investigations that lead to well-supported conclusions? To evaluate this capability, we introduce PhysClosureBench, a benchmark of 50 expert-verified, goal-specified research tasks spanning strong-field, attosecond, and neighboring physics areas. Each task specifies the research object...
Yi-Jia Mao, Song-Bin Dai, Tao Chen et al.· 0 citations
Large Language Model agents operate through closed-loop action policies whose decision space is defined by an agent harness. We investigate how this operating space shapes agent behavior and policy learning in computer-aided design (CAD), a professional domain characterized by persistent state, geometric constraints, a...
Yu-Feng Peng, Yi-Xin Zhang, Zi-Yi Liu et al.· 0 citations
Multi-objective optimization involves diverse preferences over conflicting objectives. Rather than returning a finite set of trade-off solutions, preference-conditioned Pareto set learning seeks to map a specified preference directly to a corresponding Pareto optimal solution. Yet in many real-world scenarios, optimiza...
Data agents use code to process heterogeneous files and derive analytical insights. Scaling their training faces costly environment curation, privacy and intellectual-property restrictions, and difficulty verifying open-ended findings without known generative truth. Our core insight is to specify the world behind the f...
Zhanli Li, Zeyuan Xu, Chaoxu Pang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A standard decidable regime used in practice is identified under which exhaustive simulation yields a terminating search procedure with the desired guarantees, and the limit of this recovery is shown: a chain of accepted updates can raise the bounded score in every round while the true score falls.
Brian B. Moser, Stanislav Frolov, T. Nauen et al.· 1 citation
Real-world tasks are often complex and noisy, posing substantial challenges for LLM agents. Yet existing evaluations lack a systematic framework for jointly characterizing potential perturbation targets and types. We use this two-dimensional view to conduct a unified study that quantifies the robustness of current fron...
Yuan-Jian Xu, Jin-Yi Han, Jia-Ning Hao et al.· 0 citations
Learning intrinsic dynamics---the relationship between actions and their consequences---is essential for world models. However, visual variations unrelated to the underlying control process can obscure this relationship in learned representations. We investigate the connection between action predictability, defined as...
Jia-Min Shi, Yuan-Hong Zhang, Zhi-Yang Liu et al.· 0 citations
Scientific inquiry involves iterative cycles of exploration, hypothesis generation, and reasoning over observations to uncover relationships in complex systems. Large language models (LLMs) have demonstrated strong capabilities in several components of this process, including inductive reasoning, hypothesis generation,...
Marta Kne\v{z}evi\'c, Seyed Parsa Neshaei, Jibril Frej et al.· 0 citations
Looped Transformers improve parameter efficiency by repeatedly applying the same Transformer layers. However, generating each token still involves sequential computation and repeated access to model weights, leading to high decoding latency. Recent pipelined self-speculative decoding methods reduce this delay by drafti...
Machine learning (ML) for analog IC design is constrained by limited open data and the absence of standardized evaluation: results reported in different papers are typically obtained on bespoke, often closed, datasets and with ad-hoc metrics, leaving comparisons across methods unreliable. We address both gaps with a la...
M. Leibl, F. Azevedo, S. Uhlich et al.· 0 citations
Mathematical agents are commonly evaluated by answer accuracy or proof acceptance. We introduce ClaimScope, a 72-task benchmark for auditing proposed claims through a verdict, scope, counterexample, and repair. Tasks cover optimizer-state transport, finite-horizon affine recurrences, and exact $2\times2$ linear algebra...
Diffusion models (DMs) have steadily demonstrated outstanding performance in high-fidelity, controllable generation across diverse scenarios, following the "pretraining-finetuning" paradigm established in LLMs. Despite these advances, conventional DMs still face critical limitations in sophisticated reasoning, autonomo...
Zhi-Yuan Ma, Jia-Bao Wei, Tian-Yu Wang et al.· IEEE Transactions on Pattern...· 0 citations
