32 citations · 112 across the 94 of their papers we have counts for
21 papers · 1 filter
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Haoxiang Zhang, Qinglin Chen, Hiroaki Hayashi +9
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction. For group-relative ob…
Fork Where the Model Changes Its Mind: Belief-Shift Branching for Tree-Structured Reinforcement Learning
Bin Lei, Yu Li, Prafulla Kumar Choubey +7
Tree-structured rollouts give critic-free reinforcement learning with verifiable rewards (RLVR) step-level credit: fork a chain at an intermediate point, and sibling outcome differ…
BehaviorBench: Modeling Real-World User Decisions from Behavioral Traces
Liangwei Yang, Jielin Qiu, Zixiang Chen +9
Many decision-support settings require systems that adapt to individual users, but evaluation data for this problem remain limited. Existing benchmarks for user understanding often…
Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
Romain Cosentino, Sarath Shekkizhar, Adam Earle +1
Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study w…
Echoing: Identity Failures when LLM Agents Talk to Each Other
Sarath Shekkizhar, Romain Cosentino, Adam Earle +1
As large language model (LLM) based agents interact autonomously with one another, a new class of failures emerges that cannot be predicted from single agent performance: behaviora…
Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math
Bo Pang, Deqian Kong, Silvio Savarese +2
Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two…
SCUBA: Salesforce Computer Use Benchmark
Yutong Dai, Krithika Ramakrishnan, Jing Gu +8
We introduce SCUBA, a benchmark designed to evaluate computer-use agents on customer relationship management (CRM) workflows within the Salesforce platform. SCUBA contains 300 task…
UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar +10
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value o…
SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
Xuan-Phi Nguyen, Shrey Pandit, Revanth Gangi Reddy +4
Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances…
MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers
Ziyang Luo, Zhiqi Shen, Wenzhuo Yang +7
The Model Context Protocol has emerged as a transformative standard for connecting large language models to external data sources and tools, rapidly gaining adoption across major A…
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models
Zhiwei Liu, Jielin Qiu, Shiyu Wang +9
The rapid rise of Large Language Models (LLMs)-based intelligent agents underscores the need for robust, scalable evaluation frameworks. Existing methods rely on static benchmarks…
UserBench: An Interactive Gym Environment for User-Centric Agents
Cheng Qian, Zuxin Liu, Akshara Prabhakar +9
Large Language Models (LLMs)-based agents have made impressive progress in reasoning and tool use, enabling them to solve complex tasks. However, their ability to proactively colla…
Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D
Artemis Panagopoulou, Le Xue, Honglu Zhou +6
Real-world decision-making often begins with identifying which modality contains the most relevant information for a given query. While recent multimodal models have made impressiv…
A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems
Zixuan Ke, Fangkai Jiao, Yifei Ming +9
Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making. With the rapid advancement of large language models (LLMs), reaso…
ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
Jianguo Zhang, Thai Hoang, Ming Zhu +13
Large Action models are essential for enabling autonomous agents to perform complex tasks. However, training such models remains challenging due to the diversity of agent environme…
PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data
Juntao Tan, Liangwei Yang, Zuxin Liu +11
Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI m…
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Haolin Chen, Yihao Feng, Zuxin Liu +8
Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. While prompt-based methods like Chain-of-…
Asynchronous Tool Usage for Real-Time Agents
Antonio A. Ginart, Naveen Kodali, Jason Lee +3
While frontier large language models (LLMs) are capable tool-using agents, current AI systems still operate in a strict turn-based fashion, oblivious to passage of time. This synch…
PRACT: Optimizing Principled Reasoning and Acting of LLM Agent
Zhiwei Liu, Weiran Yao, Jianguo Zhang +13
We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the…
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Tianbao Xie, Danyang Zhang, Jixuan Chen +14
Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing access…
AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning
Jianguo Zhang, Tian Lan, Rithesh Murthy +15
Autonomous agents powered by large language models (LLMs) have garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presen…