相关论文: CLEANER: Self-Purified Trajectories Boost Agentic …

We investigated Agentic RL with large language models on the \textsc{TravelPlanner} benchmark. Our approach, \textsc{Planner-R1}, achieved a \textbf{56.9\%} final-pass rate with only 180 training queries, a $2.7\times$ improvement over…

Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reasoning attainable in a…

Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…

Reinforcement learning with verifiable rewards (RLVR) scales the reasoning ability of large language models (LLMs) but remains bottlenecked by limited labeled samples for continued data scaling. Reinforcement learning with intrinsic rewards…

Many applications of large language models (LLMs) require deductive reasoning, yet models frequently produce incorrect or redundant inference steps. We frame natural language inference as a search problem where the final answer is the valid…

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation.…

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant…

Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning (RL) has emerged as a powerful paradigm for training these agents to perform…

Trajectory planning is vital for autonomous driving, ensuring safe and efficient navigation in complex environments. While recent learning-based methods, particularly reinforcement learning (RL), have shown promise in specific scenarios, RL…

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable…

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…

Large language models (LLMs) empowered by chain-of-thought reasoning have achieved impressive accuracy on complex tasks but suffer from excessive inference costs and latency when applied uniformly to all problems. We propose SABER…

As robots increasingly operate in dynamic human-centric environments, improving their ability to detect, explain, and recover from action-related issues becomes crucial. Traditional model-based and data-driven techniques lack adaptability,…

Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…

Recent advances in self-refinement have demonstrated significant potential for improving the outputs of large language models (LLMs) through iterative refinement. However, most existing self-refinement methods rely on a reactive process…

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the…

The advent of large language models (LLMs) has transformed information access and reasoning through open-ended natural language interaction. However, LLMs remain limited by static knowledge, factual hallucinations, and the inability to…

Compiler auto-tuning optimizes pass sequences to improve performance metrics such as Intermediate Representation (IR) instruction count. Although recent advances leveraging Large Language Models (LLMs) have shown promise in automating…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…