5 papers
From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
Yuxin Jiang, Yufei Wang, Qiyuan Zhang +6
Reinforcement learning with verifiable rewards (RLVR) succeeds in reasoning tasks (e.g., math and code) by checking the final verifiable answer (i.e., a verifiable dot signal). How…
SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
Chaofan Tao, Jierun Chen, Yuxin Jiang +11
We present SWE-Lego, a supervised fine-tuning (SFT) recipe designed to achieve state-ofthe-art performance in software engineering (SWE) issue resolving. In contrast to prevalent m…
Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
Yiming Du, Baojun Wang, Yifan Xiang +11
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue hi…
Instruction-Tuning Data Synthesis from Scratch via Web Reconstruction
Yuxin Jiang, Yufei Wang, Chuhan Wu +8
The improvement of LLMs' instruction-following capabilities depends critically on the availability of high-quality instruction-response pairs. While existing automatic data synthet…
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
Qiyuan Zhang, Yufei Wang, Yuxin Jiang +8
LLM-as-a-Judge, which generates chain-of-thought (CoT) judgments, has become a widely adopted auto-evaluation method. However, its reliability is compromised by the CoT reasoning's…