Paper Archive

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/3/2026 huggingface

Scaling interactive and verifiable environments is critical for training terminal agents. As frontier models become more capable, environments synthesized from scratch become less challenging and thus provide limited learning signals. Recent co-evolution methods iteratively synthesize environments n...

[object Object], [object Object], [object Object], [object Object] 9/3/2026 huggingface

Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work in the outcome-blind setting, where ground-truth success signals are not available. Multi-criteria rubrics are a popular way to supply such a rewar...

[object Object], [object Object] 9/3/2026 huggingface

Hybrid LLMs pair softmax attention with linear-attention layers such as Gated DeltaNet (GDN), whose recurrent state summarizes the context in fixed size. Early community 4-bit quantizations of Qwen3.8-27B (48 GDN layers, 16 attention layers) left the GDN block in 8- or 16-bit precision -- especially...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/3/2026 huggingface

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedbac...

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 9/3/2026 huggingface

Streaming video understanding requires multimodal large language models (MLLMs) to process continuous visual inputs and respond to user queries under strict causality and bounded memory. Existing approaches typically compress historical observations into an external memory bank and retrieve query-re...

Chin-Yang Lin, Yang-Che Sun, Cheng Sun, Fu-En Yang, Min-Hung Chen, Yen-Yu Lin, Wei-Chen Chiu, Yu-Lun Liu 9/3/2026 arxiv

Online 3D reconstruction models perform poorly on long videos. This happens because regressing poses relative to a fixed first-frame anchor forces extrapolation far beyond the training distribution. Small drifts accumulate and amplify into significant geometric collapse. However, we observe that per...

Adeela Islam, Zorah Lähner, Vittorio Murino, Vladislav Golyanik 9/3/2026 arxiv

While data-driven 3D shape correspondence estimation has recently seen substantial progress, robust matching under partial observations and strong non-isometric deformations remains challenging. Existing learning-based approaches often rely on hand-crafted descriptors or template-based representatio...

Lihao Liu, Peng Tang, Kunwar Yashraj Singh, Shabnam Ghadar 9/3/2026 arxiv

Evolutionary prompt optimizers such as GEPA suffer from prompt bloat: each iteration appends rules and caveats, producing prompts up to 3$\times$ longer yet no more accurate. We trace this to three deficiencies - incomplete error observation, limited search diversity, and unreliable selection - and ...

Angel Y. He, David Parker 9/3/2026 arxiv

We introduce the first Probably Approximately Correct (PAC) learning framework for general-sum concurrent stochastic games (CSGs) with transition uncertainty, while addressing the challenge of Nash equilibrium (NE) existence. Our algorithm maintains data-driven $L^1$ confidence sets over transition ...

Varun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan, Anand Bhattad 9/3/2026 arxiv

Evaluating physical reasoning in video models is difficult because absolute motion measurements depend on frame rate, object scale, and camera calibration, all of which are often ambiguous or unavailable in generated video. We propose a different approach. When two objects in the same scene obey the...