Related papers: AT$^2$PO: Agentic Turn-based Policy Optimization v…
Controlling energy systems usually involves manually designed policies for decision-making, which can be complex and time-consuming to develop. This process requires interdisciplinary collaboration among multiple domain experts, resulting…
Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel states. We propose…
Proactive large language model (LLM) agents aim to actively plan, query, and interact over multiple turns, enabling efficient task completion beyond passive instruction following and making them essential for real-world, user-centric…
Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning hallucinations and require…
Optimizing large language models (LLMs) for multi-turn conversational outcomes remains a significant challenge, especially in goal-oriented settings like AI marketing or sales agents who facilitate transactions via messaging platforms. The…
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…
Recent advances in group-based reinforcement learning (RL) have driven frontier large language models (LLMs) in single-turn tasks like mathematical reasoning. However, their scalability to multi-turn LLM agent training remains limited.…
Multi-turn tool-integrated reasoning enables Large Language Models (LLMs) to solve complex tasks through iterative information retrieval. However, current reinforcement learning (RL) frameworks for search-augmented reasoning predominantly…
Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a…
Recent advances in large language models (LLMs) have popularized test-time scaling, where models generate additional reasoning tokens before producing final answers. These approaches have demonstrated significant performance improvements on…
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…
Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking, generating redundant content regardless of task difficulty. Inspired by the dual process theory in cognitive…
Trust region methods rigorously enabled reinforcement learning (RL) agents to learn monotonically improving policies, leading to superior performance on a variety of tasks. Unfortunately, when it comes to multi-agent reinforcement learning…
Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual…
Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarchical deployments with a Planner, Coordinator, and…
Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…
Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy updates, recent research has increasingly shifted toward…
Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capability of large language models (LLMs), enabling autonomous agents that can conduct effective multi-turn and tool-integrated reasoning. While instructions…
Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent applications require user-conditioned behavior: the same query may call for different planning…
Large Language Reasoning Models have demonstrated remarkable success on static tasks, yet their application to multi-round agentic planning in interactive environments faces two fundamental challenges. First, the intractable credit…