activity
20242026
collaborators

11 papers

cs.CL2026

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning

Ziqi Jia, Yalu Ouyang, Bo Pang +5

Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods suffer from insuf…

cs.AI2026

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

Ye Liu, Srijan Bansal, Bo Pang +6

Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy fr…

cs.CL2025

SSR: Socratic Self-Refine for Large Language Model Reasoning

Haizhou Shi, Ye Liu, Bo Pang +6

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limitin…

cs.AI2025

Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement

Hiroaki Hayashi, Bo Pang, Wenting Zhao +6

Large language model (LLM) based agents are increasingly used to tackle software engineering tasks that require multi-step reasoning and code modification, demonstrating promising…

cs.AI2025

Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math

Bo Pang, Deqian Kong, Silvio Savarese +2

Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two…

cs.LG2025

CoDA: Coding LM via Diffusion Adaptation

Haolin Chen, Shiyu Wang, Can Qin +12

Diffusion language models promise bidirectional context and infilling capabilities that autoregressive coders lack, yet practical systems remain heavyweight. We introduce CoDA, a 1…