Retrieval-augmented generation (RAG) systems combine large language models (LLMs) with external knowledge retrieval, making them highly effective for knowledge-intensive tasks. A crucial but often under-explored component of these systems is the reranker. Since irrelevant documents in RAG systems can mislead the generator, the reranker plays a vital role in refining retrieved documents to enhance generation quality and explainability. However, it is challenging to determine the appropriate number of documents ($k$) that the reranker should select: too few may result in missing critical information, while too many introduce noise and inefficiencies. Although recent studies have explored LLM-based rerankers, they primarily leverage internal model knowledge and overlook the rich supervisory signals that LLMs can provide, such as using response quality as feedback for optimizing reranking decisions. In this paper, we propose DynamicRAG, a novel RAG framework where the reranker dynamically adjusts both the order and number of retrieved documents based on the query. We model the reranker as an agent optimized through reinforcement learning (RL), using rewards derived from LLM output quality. Across seven knowledge-intensive datasets, DynamicRAG demonstrates superior performance, achieving state-of-the-art results among models of same parameter sizes. The model, data and code are available at https://github.com/GasolSun36/DynamicRAG.

Embodied AI in Machine Learning - is it Really Embodied? Matej Hoffmann and Shubhan Parag Patni Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague Introduction Embodied Artificial Intelligence (Embodied AI) is gaining momentum in the machine learning communities with the goal of leveraging current progress in AI (deep learning, transformers, large language and visual - language models) to empower robots. In this chapter we put this work in the context of "Good Old - Fashioned Artifi cial Intelligence" (GOFAI) (Haugeland, 1989) and the behavior - based or embodied alternatives (R. A. Brooks 1991; Pfeifer and Scheier 2001). We claim that the AI - powered robots are only weakly embodied and inherit some of t he problems of GOFAI. Moreover, we review and critically discuss the possibility of cross - embodiment learning (Padalkar et al. 2024). We identify fundamental roadblocks and propose directions on how to make progress. GOFAI - powered robots never really worked Artificial Intelligence (AI) in the 1950's and 1960's, later called "Good Old - Fashioned Artificial Intelligence" (GOFAI) by Haugeland(1989), held that the key to intelligence is computation with symbols that represent the world. The keywords were algorithm ic nature, symbolic computation and representation. GOFAI was very successful in formal domains (like chess), where the state of the world is discrete and directly accessible and standard AI techniques (like search) can be applied. While the focus has been on abstract "thinking", when entering the real world, a relationship had to be established between the dynamic, continuous, partially accessible reality out there and the internal world representation. That is, reality had to be sensed and mapped onto the internal world model, in which the "thinking" was performed. Finally, whatever action was selected, it had to be executed in the real world.

As Large Language Models (LLMs) integrate into our social and economic interactions, we need to deepen our understanding of how humans respond to LLMs opponents in strategic settings. We present the results of the first controlled monetarily-incentivised laboratory experiment looking at differences in human behaviour in a multi-player p-beauty contest against other humans and LLMs. We use a within-subject design in order to compare behaviour at the individual level. We show that, in this environment, human subjects choose significantly lower numbers when playing against LLMs than humans, which is mainly driven by the increased prevalence of `zero' Nash-equilibrium choices. This shift is mainly driven by subjects with high strategic reasoning ability. Subjects who play the zero Nash-equilibrium choice motivate their strategy by appealing to perceived LLM's reasoning ability and, unexpectedly, propensity towards cooperation. Our findings provide foundational insights into the multi-player human-LLM interaction in simultaneous choice games, uncover heterogeneities in both subjects' behaviour and beliefs about LLM's play when playing against them, and suggest important implications for mechanism design in mixed human-LLM systems.

As AI tools increasingly shape how we write, they may also quietly reshape how we perceive ourselves. This paper explores the psychological impact of co-writing with AI on people's locus of control. Through an empirical study with 462 participants, we found that employment status plays a critical role in shaping users' reliance on AI and their locus of control. Current results demonstrated that employed participants displayed higher reliance on AI and a shift toward internal control, while unemployed users tended to experience a reduction in personal agency. Through quantitative results and qualitative observations, this study opens a broader conversation about AI's role in shaping personal agency and identity.

Heterogeneous Networks (HetNets) pose critical challenges for intelligent management due to the diverse user requirements and time-varying wireless conditions. These factors introduce significant decision complexity, which limits the adaptability of existing Deep Reinforcement Learning (DRL) methods. In many DRL algorithms, especially those involving value-based or actor-critic structures, the critic component plays a key role in guiding policy learning by estimating value functions. However, conventional critic models often use shallow architectures that map observations directly to scalar estimates, limiting their ability to handle multi-task complexity. In contrast, recent progress in inference-time scaling of Large Language Models (LLMs) has shown that generating intermediate reasoning steps can significantly improve decision quality. Motivated by this, we propose ReaCritic, a large reasoning transformer-based criticmodel scaling scheme that brings reasoning ability into DRL. ReaCritic performs horizontal reasoning over parallel state-action inputs and vertical reasoning through deep transformer stacks. It is compatible with a broad range of value-based and actor-critic DRL algorithms and enhances generalization in dynamic wireless environments. Extensive experiments demonstrate that ReaCritic improves convergence speed and final performance across various HetNet settings and standard OpenAI Gym control tasks.

Large language models (LLMs), inspired by neuroscience, exhibit behaviors that often evoke a sense of personality and intelligence-yet the mechanisms behind these effects remain elusive. Here, we operationalize Conceptual Blending Theory (CBT) as an experimental framework, using prompt-based methods to reveal how LLMs blend and compress meaning. By systematically investigating Prompt-Induced Transitions (PIT) and Prompt-Induced Hallucinations (PIH), we uncover structural parallels and divergences between artificial and biological cognition. Our approach bridges linguistics, neuroscience, and empirical AI research, demonstrating that human-AI collaboration can serve as a living prototype for the future of cognitive science. This work proposes prompt engineering not just as a technical tool, but as a scientific method for probing the deep structure of meaning itself.

Reinforcement learning from human feedback (RLHF) is a critical technique for training large language models. However, conventional reward models based on the Bradley-Terry model (BTRM) often suffer from overconfidence when faced with inconsistent labels or out-of-distribution samples, leading to reward hacking, where the policy model blindly optimizes for proxy rewards while degrading true performance. This paper proposes the Probabilistic Uncertain Reward Model (PURM), which generalizes the Bradley-Terry model to learn the reward distributions that emerged from the preference data. We theoretically derive the loss function of PURM and introduce a novel method that uses the overlap between distributions to quantify uncertainty. Empirical results show that PURM outperforms existing methods with more accurate reward and sound uncertainty estimations, and sustains effective learning for more optimization steps and obtain higher maximum win rate in RLHF. The data and code of this paper are released at https://anonymous.4open.science/r/Probabilistic-Uncertain-Reward-Model/

This paper explores syllable sequence prediction in Abugida languages using Transformer-based models, focusing on six languages: Bengali, Hindi, Khmer, Lao, Myanmar, and Thai, from the Asian Language Treebank (ALT) dataset. We investigate the reconstruction of complete syllable sequences from various incomplete input types, including consonant sequences, vowel sequences, partial syllables (with random character deletions), and masked syllables (with fixed syllable deletions). Our experiments reveal that consonant sequences play a critical role in accurate syllable prediction, achieving high BLEU scores, while vowel sequences present a significantly greater challenge. The model demonstrates robust performance across tasks, particularly in handling partial and masked syllable reconstruction, with strong results for tasks involving consonant information and syllable masking. This study advances the understanding of sequence prediction for Abugida languages and provides practical insights for applications such as text prediction, spelling correction, and data augmentation in these scripts.

Semantic feature norms have been foundational in the study of human conceptual knowledge, yet traditional methods face trade-offs between concept/feature coverage and verifiability of quality due to the labor-intensive nature of norming studies. Here, we introduce a novel approach that augments a dataset of human-generated feature norms with responses from large language models (LLMs) while verifying the quality of norms against reliable human judgments. We find that our AI-enhanced feature norm dataset, NOVA: Norms Optimized Via AI, shows much higher feature density and overlap among concepts while outperforming a comparable human-only norm dataset and word-embedding models in predicting people's semantic similarity judgments. Taken together, we demonstrate that human conceptual knowledge is richer than captured in previous norm datasets and show that, with proper validation, LLMs can serve as powerful tools for cognitive science research.

The emergence of large reasoning models (LRMs) has transformed Natural Language Processing by excelling in complex tasks such as mathematical problem-solving and code generation. These models leverage chain-of-thought (CoT) processes, enabling them to emulate human-like reasoning strategies. However, the advancement of LRMs is hindered by the lack of comprehensive CoT datasets. Current resources often fail to provide extensive reasoning problems with coherent CoT processes distilled from multiple teacher models and do not account for multifaceted properties describing the internal characteristics of CoTs. To address these challenges, we introduce OmniThought, a large-scale dataset featuring 2 million CoT processes generated and validated by two powerful LRMs as teacher models. Each CoT process in OmniThought is annotated with novel Reasoning Verbosity (RV) and Cognitive Difficulty (CD) scores, which describe the appropriateness of CoT verbosity and cognitive difficulty level for models to comprehend these reasoning processes. We further establish a self-reliant pipeline to curate this dataset. Extensive experiments using Qwen2.5 models of various sizes demonstrate the positive impact of our proposed scores on LRM training effectiveness. Based on the proposed OmniThought dataset, we further train and release a series of high-performing LRMs, specifically equipped with stronger reasoning abilities and optimal CoT output length and difficulty level. Our contributions significantly enhance the development and training of LRMs for solving complex tasks.