Search Results for author:
Found 21 papers, 15 papers with code
Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
In this work, we propose to scale test-time interaction, an untapped dimension of test-time scaling that increases the agent's interaction horizon to enable running rich behaviors such as exploration, backtracking, and dynamic re-planning within a single rollout.
Self-Challenging Language Model Agents
In this paper, we propose the Self-Challenging framework for training an agent on high-quality tasks that are generated by itself.
Learning Adaptive Parallel Reasoning with Language Models
Scaling inference-time computation has substantially improved the reasoning capabilities of language models.
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks.
Digi-Q: Learning Q-Value Functions for Training Device-Control Agents
To make the VLM features amenable for representing the Q-function, we need to employ an initial phase of fine-tuning to amplify coverage over actionable information needed for value function.
Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents
We validate PAE on challenging vision-based web navigation, using both real-world and self-hosted websites from WebVoyager and WebArena. To the best of our knowledge, this work represents the first effective learning system to apply autonomous task proposal with RL for agents that generalizes real-world human-annotated benchmarks with SOTA performances.
KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data
Building generalist robotic systems involves effectively endowing robots with the capabilities to handle novel objects in an open-world setting.
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
This paper introduces a novel autonomous RL approach, called DigiRL, for training in-the-wild device control agents through fine-tuning a pre-trained VLM in two stages: offline RL to initialize the model, followed by offline-to-online RL.
Aligning Large Language Models with Representation Editing: A Control Perspective
To achieve alignment for specific objectives, we introduce external control signals into the state space of this language dynamical system.
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Finally, our framework uses these task rewards to fine-tune the entire VLM with RL.
Autonomous Evaluation and Refinement of Digital Agents
We show that domain-general automatic evaluators can significantly improve the performance of agents for web navigation and device control.
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
In this paper, we develop a framework for building multi-turn RL algorithms for fine-tuning LLMs, that preserves the flexibility of existing single-turn RL methods for LLMs (e. g., proximal policy optimization), while accommodating multiple turns, long horizons, and delayed rewards effectively.
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
In this work, we propose a new hybrid RL algorithm that combines an on-policy actor-critic method with offline data.
Test-Time Distribution Normalization for Contrastively Learned Vision-language Models
Advances in the field of vision-language contrastive learning have made it possible for many downstream applications to be carried out efficiently and accurately by simply taking the dot product between image and text representations.
BT^2: Backward-compatible Training with Basis Transformation
In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling.
$BT^2$: Backward-compatible Training with Basis Transformation
In this way, the new representation can be directly compared with the old representation, in principle avoiding the need for any backfilling.
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient
We consider a hybrid reinforcement learning setting (Hybrid RL), in which an agent has access to an offline dataset and the ability to collect experience via real-world online interaction.
TCDM: Transformational Complexity Based Distortion Metric for Perceptual Point Cloud Quality Assessment
The goal of objective point cloud quality assessment (PCQA) research is to develop quantitative metrics that measure point cloud quality in a perceptually consistent manner.
GAPX: Generalized Autoregressive Paraphrase-Identification X
Paraphrase Identification is a fundamental task in Natural Language Processing.
Improve Discourse Dependency Parsing with Contextualized Representations
Recent works show that discourse analysis benefits from modeling intra- and inter-sentential levels separately, where proper representations for text units of different granularities are desired to capture both the meaning of text units and their relations to the context.
Data Driven Modeling of Turbocharger Turbine using Koopman Operator
The objective of this paper is to develop a model to predict the transient and steady-state behavior of the turbine using the Koopman operator which can be helpful for control design and analysis.
