12 papers
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
Bowei He, Yankai Chen, Xiaokun Zhang +4
Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesi…
Measurement-Gated Provenance Attenuation for Frozen EEG Representations
Anuar Aimoldin, Yankai Chen, Ayana Mussabayeva +2
Frozen EEG representations retain acquisition signatures as well as neural activity. Source predictability alone does not identify what should be removed: it can reflect measuremen…
ANIMASK: What the Model Contributes to Role Play in Simulated Story Worlds
Xiucheng Zhang, Zhuoning Xu, Hanjun Luo +3
When a language model plays a character, the observed behavior reflects both the assigned persona and the default dispositions of the actor model itself. Existing evaluations test…
SCAFFOLD: Self-Improving Web Agents via Recursive Parametric Skill Abstraction
Bowei He, Xiaokun Zhang, Meng Ding +1
Web agents need to navigate visually rich, long-horizon interfaces that change across sites, yet most previous agents still learn each task in isolation and discard the procedural…
Overview of FinMMEval 2026 Task 2: Multilingual Financial Short-Answer Question Answering
Zhuohan Xie, Xueqing Peng, Georgi Georgiev +18
FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question with financial statements and n…
Overview of FinMMEval 2026 Task 1: Multilingual Financial Multiple-Choice Question Answering
Zhuohan Xie, Yuyang Dai, Rania Elbadry +18
FinMMEval 2026 Task 1 evaluates multilingual financial multiple-choice question answering in English, Chinese, Arabic, and Hindi. The task tests whether systems can select the corr…
Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
Bowei He, Yankai Chen, Xiaokun Zhang +1
Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such…
FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents
Muhammad Usman Safder, Ayesha Gull, Rania Elbadry +7
Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as "preserve capital" or "avoid speculative…
FinReporting: An Agentic Workflow for Localized Reporting of Cross-Jurisdiction Financial Disclosures
Fan Zhang, Mingzi Song, Rania Elbadry +20
Financial reporting systems increasingly leverage Large Language Models (LLMs) to extract and summarize corporate disclosures. However, most existing approaches assume a single-mar…
The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project
Huamin Chen, Xunzhuo Liu, Bowei He +5
Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, rout…
Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation
Bowei He, Yankai Chen, Xiaokun Zhang +4
Knowledge distillation from Large Language Models (LLMs) to smaller models has emerged as a critical technique for deploying efficient AI systems. However, current methods for dist…
Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
Yankai Chen, Xinni Zhang, Yifei Zhang +6
Brain-Computer Interfaces (BCIs) offer a direct communication pathway between the human brain and external devices, holding significant promise for individuals with severe neurolog…