184 citations · 582 across the 57 of their papers we have counts for
61 papers
TEX: Test-Time Scaling Testing Agents via Execution-based Cross-Validation
Akash Gokul, Srijan Bansal, Yingbo Zhou +1
Test-case generation is critical but remains challenging for language models. Existing test-time scaling methods either isolate candidates or aggregate traces, which do not scale t…
Understanding the Synergy between SFT, RLVR, and OPD in LLM Post-Training
Emre Can Acikgoz, Yang Li, Zeyu Leo Liu +4
Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD) into multi-stage pipelines,…
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
Yefan Zhou, Yang Li, Zeyu Leo Liu +2
Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory is disti…
EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?
Zixuan Ke, Vaidehi Patil, Haizhou Shi +9
Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness con…
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…
Learning Generalizable Behaviors for Terminal Agents
Yihang Yao, Bo Pang, Xuan Phi Nguyen +3
Terminal agents are a compelling application of large language models (LLMs), with the potential to integrate deeply into users' daily workflows. Reinforcement learning (RL) is a k…
Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models
Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3
This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models. It is a training paradigm that combines and specializes various existing and novel paral…
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…
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…
Learning from Language Feedback via Variational Policy Distillation
Yang Li, Erik Nijkamp, Semih Yavuz +1
Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self…
VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?
Srijan Bansal, Jiao Fangkai, Yilun Zhou +3
As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle fa…
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…
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…
SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization
Revanth Gangi Reddy, Ye Liu, Wenting Zhao +7
Maintaining large-scale, multilingual codebases hinges on accurately localizing issues, which requires mapping natural-language error descriptions to the relevant functions that ne…
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…
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…
Retrofitting Small Multilingual Models for Retrieval: Matching 7B Performance with 300M Parameters
Lifu Tu, Yingbo Zhou, Semih Yavuz
Training effective multilingual embedding models presents unique challenges due to the diversity of languages and task objectives. Although small multilingual models (<1 B paramete…
VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
Rui Meng, Ziyan Jiang, Ye Liu +10
Multimodal embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering over different modalities. How…
Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
Raghuveer Thirukovalluru, Rui Meng, Ye Liu +7
Contrastive learning (CL) is a prevalent technique for training embedding models, which pulls semantically similar examples (positives) closer in the representation space while pus…
SweRank: Software Issue Localization with Code Ranking
Revanth Gangi Reddy, Tarun Suresh, JaeHyeok Doo +7
Software issue localization, the task of identifying the precise code locations (files, classes, or functions) relevant to a natural language issue description (e.g., bug report, f…
Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings
Austin Xu, Srijan Bansal, Yifei Ming +2
The large language model (LLM)-as-judge paradigm has been used to meet the demand for a cheap, reliable, and fast evaluation of model outputs during AI system development and post-…
Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Lifu Tu, Rui Meng, Shafiq Joty +2
Large language models (LLMs) have demonstrated strong capabilities in text understanding and generation. However, they often lack factuality, producing a mixture of true and false…
CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval
Ye Liu, Rui Meng, Shafiq Joty +4
Despite the success of text retrieval in many NLP tasks, code retrieval remains a largely underexplored area. Most text retrieval systems are tailored for natural language queries,…
JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking
Tong Niu, Shafiq Joty, Ye Liu +3
Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While lar…