Ax Shuyang Liu, Yang Chen, Rahul Krishna, Saurabh Sinha, Jatin Ganhotra, Reyhan Jabbarvand 3/10/2026

Process-Centric Analysis of Agentic Software Systems

arXiv paper on evaluating agentic systems via process-centric analysis of trajectories and reasoning patterns rather than outcomes alone. Foundational agent analysis framework.

Ax Yulun Jiang, Liangze Jiang, Damien Teney, Michael Moor, Maria Brbic 3/10/2026

Meta-RL Induces Exploration in Language Agents

LaMer: Meta-RL framework enabling LLM agents to actively explore and learn from trial-and-error in multi-turn tasks. Research on agent training methodology.

Ax Naufal Suryanto, Muzammal Naseer, Pengfei Li, Syed Talal Wasim, Jinhui Yi, Juergen Gall, Paolo Ceravolo, Ernesto Damiani 3/10/2026

RedSage: A Cybersecurity Generalist LLM

Open-source cybersecurity LLM trained on 11.8B tokens of curated domain data; supports diverse security workflows while protecting sensitive data.

Ax Meng Ding, Zeqing Zhang, Di Wang, Lijie Hu 3/10/2026

In-Run Data Shapley for Adam Optimizer

Data Shapley attribution method for adaptive optimizers like Adam, extending in-run attribution beyond SGD's linear structure.

Ax Luke Alexander, Eric Leonen, Sophie Szeto, Artemii Remizov, Ignacio Tejeda, Jarod Alper, Giovanni Inchiostro, Vasily Ilin 3/10/2026

Semantic Search over 9 Million Mathematical Theorems

Semantic search system over 9M mathematical theorems using embeddings to retrieve specific results for mathematicians and theorem-proving agents.

Ax Yicheng Di, Zhanjie Zhang, Yun Wang, Jinren Liu, Jiaqi Yan, Jiyu Wei, Xiangyu Chen, Yuan Liu 3/10/2026

LMMRec: LLM-driven Motivation-aware Multimodal Recommendation

LLM-driven recommendation system using multimodal motivation modeling to improve content preference prediction by incorporating review text and heterogeneous data.

Ax Yang Zhang, Danyang Li, Yuxuan Li, Xin Zhang, Tianyu Xie, Mingming Cheng, Xiang Li 3/10/2026

CrystaL: Spontaneous Emergence of Visual Latents in MLLMs

CrystaL enables latent chain-of-thought reasoning in multimodal LLMs without predefined supervision, improving vision-language integration.

Ax Peiyuan Zhang, Matthew Noto, Wenxuan Tan, Chengquan Jiang, Will Lin, Wei Zhou, Hao Zhang 3/10/2026

Attn-QAT: 4-Bit Attention With Quantization-Aware Training

First systematic 4-bit quantization-aware training study for attention mechanisms enabling end-to-end FP4 computation on emerging GPUs.

Ax Zeyneb N. Kaya, Nick Rui 3/10/2026

Test-Time Meta-Adaptation with Self-Synthesis

MASS: meta-learning framework enabling LLMs to self-adapt at test time by generating synthetic training data for improved downstream performance.

Ax Levy Chaves, Chao Zhou, Rebekka Burkholz, Eduardo Valle, Sandra Avila 3/10/2026

Bridging Domains through Subspace-Aware Model Merging

Research on merging task-specific models into consolidated ones, analyzing parameter competition and domain generalization effects.

Ax Jiajun Xu, Jiageng Mao, Ang Qi, Weiduo Yuan, Alexander Romanus, Helen Xia, Vitor Campagnolo Guizilini, Yue Wang 3/10/2026

FuzzingRL: Reinforcement Fuzz-Testing for Revealing VLM Failures

FuzzingRL approach using reinforcement learning for fuzz testing Vision Language Models to automatically generate failure-inducing queries.