5 papers
FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents
Dongyi Lv, Fushun E, Aichen Cai +8
Rejection sampling fine-tuning (RFT) is widely used to train code agents by generating trajectories on verifiable software engineering tasks, retaining those that pass the tests, a…
Modular TTT: Rethinking Test-Time Training as Composable Modules
Bohao Tang, Zhen Qin, Yuqi Pan +3
Test-time training (TTT) views sequence modeling as an online learning problem in which fast weights are updated by an internal learning rule. Despite the growing number of TTT var…
Multi-Source Retrieval and Reasoning for Legal Sentencing Prediction
Junjie Chen, Haitao Li, Qilei Zhang +7
Legal judgment prediction (LJP) aims to predict judicial outcomes from case facts and typically includes law article, charge, and sentencing prediction. While recent methods perfor…
LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
Haitao Li, Yifan Chen, Shuo Miao +13
While Large Language Models (LLMs) have demonstrated impressive general capabilities, their direct application in the legal domain is often hindered by a lack of precise domain kno…
Visual Programmability: A Guide for Code-as-Thought in Chart Understanding
Bohao Tang, Yan Ma, Fei Zhang +6
Chart understanding presents a critical test to the reasoning capabilities of Vision-Language Models (VLMs). Prior approaches face critical limitations: some rely on external tools…