Related papers: WebArbiter: A Principle-Guided Reasoning Process R…

Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However, traditional RAG systems are limited by static workflows…

Process Reward Models (PRMs) aim to improve multi-step reasoning in Large Language Models (LLMs) by supervising intermediate steps and identifying errors. However, building effective PRMs remains challenging due to the lack of scalable,…

Reinforcement learning (RL) requires access to a reward function that incentivizes the right behavior, but these are notoriously hard to specify for complex tasks. Preference-based RL provides an alternative: learning policies using a…

Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application…

Verifiers--functions assigning rewards to agent behavior--have been key to AI progress in math, code, and games. However, extending gains to domains without clear-cut success criteria remains a challenge: while humans can recognize desired…

The rapid advancement of Large Vision Language Models (LVLMs) has demonstrated excellent abilities in various visual tasks. Building upon these developments, the thinking with images paradigm has emerged, enabling models to dynamically edit…

Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, planning remains a bottleneck, as existing methods struggle…

Large language models (LLMs) have recently shown strong reasoning abilities in domains like mathematics, coding, and scientific problem-solving, yet their potential for ranking tasks, where prime examples include retrieval, recommender…

Process-supervised reward models (PRMs) excel at providing step-by-step verification for large language model (LLM) outputs in domains like mathematics and coding. However, their application to fields lacking ground-truth answers, such as…

Practical deployment of multi-agent systems (MAS) demands strong performance at test time, motivating methods that guide search during inference and selectively spend compute to improve quality. We present the Multi-Agent System Process…

Recent advances in GUI agents have achieved remarkable grounding and action-prediction performance, yet existing models struggle with unreliable reward signals and limited online trajectory generation. In this paper, we introduce Orcust, a…

Agentic search requires large language models (LLMs) to perform multi-step search to solve complex information-seeking tasks, imposing unique challenges on their reasoning capabilities. However, what constitutes effective reasoning for…

Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…

Large reasoning models (LRMs) have recently shown promise in solving complex math problems when optimized with Reinforcement Learning (RL). But conventional approaches rely on outcome-only rewards that provide sparse feedback, resulting in…

As language models regularly make mistakes when solving math problems, automated identification of errors in the reasoning process becomes increasingly significant for their scalable oversight. In this paper, we introduce ProcessBench for…

Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities. However, their reliance on static internal knowledge limits their performance on complex, knowledge-intensive…

Reward models (RMs) are crucial for the training and inference-time scaling up of large language models (LLMs). However, existing reward models primarily focus on human preferences, neglecting verifiable correctness signals which have shown…

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…

Time-series reasoning remains a significant challenge in multimodal large language models (MLLMs) due to the dynamic temporal patterns, ambiguous semantics, and lack of temporal priors. In this work, we introduce TimeMaster, a reinforcement…

Aligning Multimodal Large Language Models (MLLMs) requires reliable reward models, yet existing single-step evaluators can suffer from lazy judging, exploiting language priors over fine-grained visual verification. While rubric-based…