Related papers: PreFlect: From Retrospective to Prospective Reflec…

Large Language Models (LLMs) offer a promising basis for creating agents that can tackle complex tasks through iterative environmental interaction. Existing methods either require these agents to mimic expert-provided trajectories or rely…

Pre-trained Language Models (PLMs) have achieved great success on Machine Reading Comprehension (MRC) over the past few years. Although the general language representation learned from large-scale corpora does benefit MRC, the poor support…

Reinforcement Learning (RL)-based post-training has significantly advanced the complex reasoning capabilities of language models, fostering sophisticated self-reflection processes. However, this ``slow thinking'' paradigm presents a…

Long-horizon tasks requiring multi-step reasoning and dynamic re-planning remain challenging for large language models (LLMs). Sequential prompting methods are prone to context drift, loss of goal information, and recurrent failure cycles,…

Expert-level scientific reasoning remains challenging for large language models, particularly on benchmarks such as Humanity's Last Exam (HLE), where rigid tool pipelines, brittle multi-agent coordination, and inefficient test-time scaling…

While large language models (LLMs) are proficient at question-answering (QA), it is not always clear how (or even if) an answer follows from their latent "beliefs". This lack of interpretability is a growing impediment to widespread use of…

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL) methods lack the…

Language agents can adapt from experience in interactive environments, but current reflection-based methods can only self-correct within a single task instance. Whether such experience can be distilled into reusable lessons that improve…

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual reflections of the same LLM onto itself exhibit degeneration of…

The integration of Large Language Models (LLMs) into robotics has unlocked unprecedented capabilities in high-level task planning. However, most current systems operate in an open-loop fashion, where LLMs act as one-shot planners, rendering…

Large language models (LLMs) have achieved remarkable success in a wide range of natural language processing tasks and can be adapted through prompting. However, they remain suboptimal in multi-turn interactions, often relying on incorrect…

Training large language models as retrieval-augmented reasoning agents typically combines reinforcement learning with an SFT cold start distilled from a stronger model. However, this paradigm overlooks two fundamental factors: the…

The rise of Large Language Models (LLMs) has sparked interest in their application to sequential recommendation tasks as they can provide supportive item information. However, due to the inherent complexities of sequential recommendation,…

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

Search agents have achieved significant advancements in enabling intelligent information retrieval and decision-making within interactive environments. Although reinforcement learning has been employed to train agentic models capable of…

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…

Recent advancements in Large Language Models (LLMs) have significantly improved their problem-solving capabilities. However, these models still struggle when faced with complex multi-step reasoning tasks. In this paper, we propose the…

Large language models excel on static benchmarks, but their ability as self-learning agents in dynamic environments remains unclear. We evaluate three prompting strategies: self-reflection, heuristic mutation, and planning across dynamic…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…

Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus on reactive responses, overlooking the complexities of…