works on

From the 1 of 12 linked papers with an AI index.

collaborators

12 papers

cs.CL2026

ToFu: A White-Box, Token-Efficient Agent Harness for Researchers

Junhao Ruan, Yuan Ge, Bei Li +7

ToFu is an open‑source, white‑box agentic harness that lets researchers automate codebase reading, file editing, command execution, and tool integration with high token efficiency…

cs.AI2026

Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning

Tianyuan Shi, Canbin Huang, Bei Li +4

Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answer rather th…

cs.CL2026

SpanNorm: Reconciling Training Stability and Performance in Deep Transformers

Chao Wang, Bei Li, Jiaqi Zhang +8

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, lead…

cs.LG2026

Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

Xinyu Liu, Kechen Jiao, Chunyang Xiao +10

On-policy distillation (OPD) has become a promising paradigm for reasoning-oriented post-training of large language models (LLMs), especially when combined with reinforcement learn…

cs.CL2026

LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance

Yuchun Fan, Bei Li, Peiguang Li +9

Reinforcement learning has proven effective for enhancing multi-step reasoning in large language models (LLMs), yet its benefits have not fully translated to multilingual contexts.…

cs.CL2026

MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks

Junhao Ruan, Abudukeyumu Abudula, Bei Li +8

Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational retrieval benchmarks suffer…