相关论文: Seir\^enes: Adversarial Self-Play with Evolving Di…

Vision-language models (VLMs) have shown remarkable abilities by integrating large language models with visual inputs. However, they often fail to utilize visual evidence adequately, either depending on linguistic priors in vision-centric…

While Large Language Models (LLMs) achieve high performance on standard mathematical benchmarks, their problem-solving abilities depend on the context and textual formatting. We introduce the Robust Reasoning Benchmark (RRB), a pipeline of…

Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to master autonomous search for complex question answering. However, particularly within multi-turn search scenarios, this interaction introduces a critical challenge:…

LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve together. However, in practice, existing LLM self-play methods do not scale well…

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment…

Reinforcement learning (RL) offers a principled way to enhance the reasoning capabilities of large language models, yet its effectiveness hinges on training signals that remain informative as models evolve. In practice, RL progress often…

Unified Multimodal Models (UMMs) exhibit strong understanding, yet this capability often fails to effectively guide generation. We identify this as a Cognitive Gap: the model lacks the understanding of how to enhance its own generation…

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…

Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates…

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…

Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery but pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs that may…

Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…

In-Context Reinforcement Learning (ICRL) enables Large Language Models (LLMs) to learn online from external rewards directly within the context window. However, a central challenge in ICRL is reward estimation, as models typically lack…

Recent advances in reasoning models and agentic AI systems have led to an increased reliance on diverse external information. However, this shift introduces input contexts that are inherently noisy, a reality that current sanitized…

Test-time inference has emerged as a powerful paradigm for enabling language models to ``think'' longer and more carefully about complex challenges, much like skilled human experts. While reinforcement learning (RL) can drive…

Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation, yet existing research has mostly evaluated their adherence to…

Recent work shows that large multimodal models (LMMs) can self-improve from unlabeled data via self-play and intrinsic feedback. Yet existing self-evolving frameworks mainly reward final outcomes, leaving intermediate reasoning weakly…

The reasoning abilities of large language models (LLMs) have been substantially improved by reinforcement learning with verifiable rewards (RLVR). At test time, collaborative reasoning through Multi-Agent Debate (MAD) has emerged as a…

The development of reasoning capabilities represents a critical frontier in large language models (LLMs) research, where reinforcement learning (RL) and process reward models (PRMs) have emerged as predominant methodological frameworks.…

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…