257 citations · 1k across the 96 of their papers we have counts for
100 papers
Post-Training, Finetuning, and Steering:A Field Guide for Curating Training Data
Maria Attarian, Yifan Ruan, Claas Voelcker +5
While Vision-Language-Action models have enabled impressive cross-task transfer in zero-shot settings, \emph{adaptation} methods are often necessary to achieve consistent performan…
Position: Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL
Dongsu Lee, Sooraj Sathish, Joonkyung Kim +2
We argue that cooperative multi-agent reinforcement learning (MARL) should treat test-time coordination as part of the problem definition rather than a deployment artifact. Our foc…
Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
Dongsu Lee, Haoran Xu, Amy Zhang
Offline multi-agent reinforcement learning (MARL) faces a persistent trade-off. Expressive generative policies can represent multi-modal coordination in the data, but cannot distin…
Foresight: Iterative Reasoning About Clues that Matter for Navigation
Arthur Zhang, Carl Qi, Donne Su +3
Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and inferring which environmental cues are relevant for reaching the goal. F…
Trajectory-Refined Distillation
Li Jiang, Haoran Xu, Yichuan Ding +1
On-policy distillation (OPD) has become a central post-training tool for large language models (LLMs), providing dense per-token teacher supervision along the student's own rollout…
Exploiting Local Dynamics Regularity for Reusable Skills in Offline Hierarchical RL
Sarthak Dayal, Abhinav Peri, Carl Qi +4
Hierarchical Reinforcement Learning (HRL) promises to solve long-horizon Reinforcement Learning (RL) tasks more efficiently than non-hierarchical counterparts by discovering and re…
Reinforcement Learning via Value Gradient Flow
Haoran Xu, Kaiwen Hu, Somayeh Sojoudi +1
We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) i…
Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces
Manas Pathak, Xingyao Chen, Shuozhe Li +2
Should we trust Large Language Models (LLMs) with high accuracy? LLMs achieve high accuracy on reasoning benchmarks, but correctness alone does not reveal the quality of the reason…
The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
Seth Karten, Jake Grigsby, Tersoo Upaa +28
We present the PokeAgent Challenge, a large-scale benchmark for decision-making research built on Pokemon's multi-agent battle system and expansive role-playing game (RPG) environm…
A Recipe for Stable Offline Multi-agent Reinforcement Learning
Dongsu Lee, Daehee Lee, Amy Zhang
Despite remarkable achievements in single-agent offline reinforcement learning (RL), multi-agent RL (MARL) has struggled to adopt this paradigm, largely persisting with on-policy t…
Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models
Pranaya Jajoo, Harshit Sikchi, Siddhant Agarwal +3
Behavioral Foundation Models (BFMs) produce agents with the capability to adapt to any unknown reward or task. These methods, however, are only able to produce near-optimal policie…
Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning
Carl Qi, Xiaojie Wang, Silong Yong +6
Reasoning about failures is crucial for building reliable and trustworthy robotic systems. Prior approaches either treat failure reasoning as a closed-set classification problem or…
Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion
Dan Haramati, Carl Qi, Tal Daniel +3
We propose a hierarchical entity-centric framework for offline Goal-Conditioned Reinforcement Learning (GCRL) that combines subgoal decomposition with factored structure to solve l…
Factored Latent Action World Models
Zizhao Wang, Chang Shi, Jiaheng Hu +4
Learning latent actions from action-free video has emerged as a powerful paradigm for scaling up controllable world model learning. Latent actions provide a natural interface for u…
Learning Robust Reasoning through Guided Adversarial Self-Play
Shuozhe Li, Vaishnav Tadiparthi, Kwonjoon Lee +6
Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupte…
CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models
Shuozhe Li, Jincheng Cao, Bodun Hu +3
Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while un…
Multi-agent Coordination via Flow Matching
Dongsu Lee, Daehee Lee, Amy Zhang
This work presents MAC-Flow, a simple yet expressive framework for multi-agent coordination. We argue that requirements of effective coordination are twofold: (i) a rich representa…
Unifying Agent Interaction and World Information for Multi-agent Coordination
Dongsu Lee, Daehee Lee, Yaru Niu +3
This work presents a novel representation learning framework, *interaction-world* latent (IWoL), to facilitate *team coordination* in multi-agent reinforcement learning (MARL). Bui…
Correct Reasoning Paths Visit Shared Decision Pivots
Dongkyu Cho, Amy B. Z. Zhang, Bilel Fehri +4
Chain-of-thought (CoT) reasoning exposes the intermediate thinking process of large language models (LLMs), yet verifying those traces at scale remains unsolved. In response, we in…
Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
Viraj Joshi, Zifan Xu, Bo Liu +2
Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which de…
ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
Ruiyang Zhou, Shuozhe Li, Amy Zhang +1
Self-improvement via RL often fails on complex reasoning tasks because GRPO-style post-training methods rely on the model's initial ability to generate positive samples. Without gu…
Guiding Diffusion with Deep Geometric Moments: Balancing Fidelity and Variation
Sangmin Jung, Utkarsh Nath, Yezhou Yang +5
Text-to-image generation models have achieved remarkable capabilities in synthesizing images, but often struggle to provide fine-grained control over the output. Existing guidance…
Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning
Caleb Chuck, Fan Feng, Carl Qi +4
Hindsight relabeling is a powerful tool for overcoming sparsity in goal-conditioned reinforcement learning (GCRL), especially in certain domains such as navigation and locomotion.…
Multimodal Language Models as Text-to-Image Model Evaluators
Jiahui Chen, Candace Ross, Reyhane Askari-Hemmat +5
The steady improvements of text-to-image (T2I) generative models lead to slow deprecation of automatic evaluation benchmarks that rely on static datasets, motivating researchers to…