activity
20192026
most citedLingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

184 citations · 222 across the 37 of their papers we have counts for

collaborators
Showing cs.AIShow all

7 papers · 1 filter

cs.AI2026

RISE: Recursive Improvement via Self-Extrapolating Policy Distillation

Yang Li, Semih Yavuz, Shafiq Joty

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suf…

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.AI2026

Reward Modeling for Multi-Agent Orchestration

King Yeung Tsang, Zihao Zhao, Vishal Venkataramani +5

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by lim…

cs.AI2026

MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems

Vishal Venkataramani, Haizhou Shi, Zixuan Ke +6

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate step…

cs.AI2026

MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks

Zixuan Ke, Yifei Ming, Austin Xu +7

While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from…

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…