Reinforcement Learning Fine-Tuning (RLFT) has achieved notable success in tasks with objectively verifiable answers (e.g., code generation, mathematical reasoning), yet struggles with open-ended subjective tasks like role-playing dialogue. Traditional reward modeling approaches, which rely on independent sample-wise scoring, face dual challenges: subjective evaluation criteria and unstable reward signals.Motivated by the insight that human evaluation inherently combines explicit criteria with implicit comparative judgments, we propose Comparative Policy Optimization (CPO). CPO redefines the reward evaluation paradigm by shifting from sample-wise scoring to comparative group-wise scoring.Building on the same principle, we introduce the CharacterArena evaluation framework, which comprises two stages:(1) Contextualized Multi-turn Role-playing Simulation, and (2) Trajectory-level Comparative Evaluation. By operationalizing subjective scoring via objective trajectory comparisons, CharacterArena minimizes contextual bias and enables more robust and fair performance evaluation. Empirical results on CharacterEval, CharacterBench, and CharacterArena confirm that CPO effectively mitigates reward ambiguity and leads to substantial improvements in dialogue quality.

Active testing enables label-efficient evaluation of models through careful data acquisition. However, its significant computational costs have previously undermined its use for large models. We show how it can be successfully scaled up to the evaluation of large language models (LLMs). In particular we show that the surrogate model used to guide data acquisition can be constructed cheaply using in-context learning, does not require updating within an active-testing loop, and can be smaller than the target model. We even find we can make good data-acquisition decisions without computing predictions with the target model and further introduce a single-run error estimator to asses how well active testing is working on the fly. We find that our approach is able to more effectively evaluate LLM performance with less data than current standard practices.

The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a growing interest in attention-based model explanations. Although attention weights do not directly determine model outputs, they reflect patterns of token influence that can inform and complement established explainability techniques. This work studies the potential of utilising the information encoded in attention weights to provide meaningful model explanations by integrating them into explainable AI (XAI) frameworks that target fundamentally different aspects of model behaviour. To this end, we develop two novel explanation methods applicable to both natural language processing and computer vision tasks. The first integrates attention weights into the Shapley value decomposition by redefining the characteristic function in terms of pairwise token interactions via attention weights, thus adapting this widely used game-theoretic solution concept to provide attention-driven attributions for local explanations. The second incorporates attention weights into token-level directional derivatives defined through concept activation vectors to measure concept sensitivity for global explanations. Our empirical evaluations on standard benchmarks and in a comparison study with widely used explanation methods show that attention weights can be meaningfully incorporated into the studied XAI frameworks, highlighting their value in enriching transformer explainability.

We propose a novel method for sensitivity analysis to unobserved confounding in causal inference. The method builds on a copula-based causal graphical normalizing flow that we term $ρ$-GNF, where $ρ\in [-1,+1]$ is the sensitivity parameter. The parameter represents the non-causal association between exposure and outcome due to unobserved confounding, which is modeled as a Gaussian copula. In other words, the $ρ$-GNF enables scholars to estimate the average causal effect (ACE) as a function of $ρ$, accounting for various confounding strengths. The output of the $ρ$-GNF is what we term the $ρ_{curve}$, which provides the bounds for the ACE given an interval of assumed $ρ$ values. The $ρ_{curve}$ also enables scholars to identify the confounding strength required to nullify the ACE. We also propose a Bayesian version of our sensitivity analysis method. Assuming a prior over the sensitivity parameter $ρ$ enables us to derive the posterior distribution over the ACE, which enables us to derive credible intervals. Finally, leveraging on experiments from simulated and real-world data, we show the benefits of our sensitivity analysis method.

Causal machine learning has the potential to revolutionize decision-making by combining the predictive power of machine learning algorithms with the theory of causal inference. However, these methods remain underutilized by the broader machine learning community, in part because current empirical evaluations do not permit assessment of their reliability and robustness, undermining their practical utility. Specifically, one of the principal criticisms made by the community is the extensive use of synthetic experiments. We argue, on the contrary, that synthetic experiments are essential and necessary to precisely assess and understand the capabilities of causal machine learning methods. To substantiate our position, we critically review the current evaluation practices, spotlight their shortcomings, and propose a set of principles for conducting rigorous empirical analyses with synthetic data. Adopting the proposed principles will enable comprehensive evaluations that build trust in causal machine learning methods, driving their broader adoption and impactful real-world use.

--In this paper, we present a novel neural architecture for channel estimation (CE) in 5G and beyond, the Recurrent Equivariant UERS Estimation Network (ReQuestNet). It incorporates several practical considerations in wireless communication systems, such as ability to handle variable number of resource block (RB), dynamic number of transmit layers, physical resource block groups (PRGs) bundling size (BS), demodulation reference signal (DMRS) patterns with a single unified model, thereby, drastically simplifying the CE pipeline. Besides it addresses several limitations of the legacy linear MMSE solutions, for example, by being independent of other reference signals and particularly by jointly processing MIMO layers and differently precoded channels with unknown precoding at the receiver . ReQuestNet comprises of two sub-units, CoarseNet followed by RefinementNet. CoarseNet performs per PRG, per transmit-receive (Tx-Rx) stream channel estimation, while Refinement-Net refines the CoarseNet channel estimate by incorporating correlations across differently precoded PRGs, and correlation across multiple input multiple output (MIMO) channel spatial dimensions (cross-MIMO). Simulation results demonstrate that ReQuestNet significantly outperforms genie minimum mean squared error (MMSE) CE across a wide range of channel conditions, delay-Doppler profiles, achieving up to 10dB gain at high SNRs. Notably, ReQuestNet generalizes effectively to unseen channel profiles, efficiently exploiting inter-PRG and cross-MIMO correlations under dynamic PRG BS and varying transmit layer allocations. The advent of 5G NR and the anticipated evolution toward sixth-generation (6G) networks have ushered in an era of unprecedented connectivity, data throughput, and system complexity. These developments necessitate advanced techniques for low-power, compute-efficient, and reliable wireless communication. Orthogonal Frequency Division Multiplexing (OFDM), a foundational modulation scheme in 5G NR, creates parallel communication channels across a large time-frequency grid. To acquire channel state information (CSI), the pilot signals known as demodulation reference signal (DMRS) is used, whose time-frequency positions and values are known a priori to both transmitter and receiver. Work completed while affiliated with Qualcomm Technologies Inc., USA.

Large Language Models (LLMs) have demonstrated remarkable capabilities in processing extensive offline datasets. However, they often face challenges in acquiring and integrating complex, knowledge online. Traditional AI training paradigms, predominantly based on supervised learning or reinforcement learning, mirror a 'Piagetian' model of independent exploration. These approaches typically rely on large datasets and sparse feedback signals, limiting the models' ability to learn efficiently from interactions. Drawing inspiration from Vygotsky's sociocultural theory, this study explores the potential of socially mediated learning paradigms to address these limitations. We introduce a dynamic environment, termed the 'AI Social Gym', where an AI learner agent engages in dyadic pedagogical dialogues with knowledgeable AI teacher agents. These interactions emphasize external, structured dialogue as a core mechanism for knowledge acquisition, contrasting with methods that depend solely on internal inference or pattern recognition. Our investigation focuses on how different pedagogical strategies impact the AI learning process in the context of ontology acquisition. Empirical results indicate that such dialogic approaches-particularly those involving mixed-direction interactions combining top-down explanations with learner-initiated questioning-significantly enhance the LLM's ability to acquire and apply new knowledge, outperforming both unidirectional instructional methods and direct access to structured knowledge, formats typically present in training datasets. These findings suggest that integrating pedagogical and psychological insights into AI and robot training can substantially improve post-training knowledge acquisition and response quality. This approach offers a complementary pathway to existing strategies like prompt engineering

Relational databases (RDBs) have become the industry standard for storing massive and heterogeneous data. However, despite the widespread use of RDBs across various fields, the inherent structure of relational databases hinders their ability to benefit from flourishing deep learning methods. Previous research has primarily focused on exploiting the unary dependency among multiple tables in a relational database using the primary key - foreign key relationships, either joining multiple tables into a single table or constructing a graph among them, which leaves the implicit composite relations among different tables and a substantial potential of improvement for predictive modeling unexplored. In this paper, we propose SRP, a unified predictive modeling framework that synthesizes features using the unary dependency, retrieves related information to capture the composite dependency, and propagates messages across a constructed graph to learn adjacent patterns for prediction on relation databases. By introducing a new retrieval mechanism into RDB, SRP is designed to fully capture both the unary and the composite dependencies within a relational database, thereby enhancing the receptive field of tabular data prediction. In addition, we conduct a comprehensive analysis on the components of SRP, offering a nuanced understanding of model behaviors and practical guidelines for future applications. Extensive experiments on five real-world datasets demonstrate the effectiveness of SRP and its potential applicability in industrial scenarios. The code is released at https://github.com/NingLi670/SRP.

Large Language Models (LLMs) have shown promise in automating code generation and software engineering tasks, yet they often struggle with complex, multi-file projects due to context limitations and knowledge gaps. We propose a novel context engineering workflow that combines multiple AI components: an Intent Translator (GPT-5) for clarifying user requirements, an Elicit-powered semantic literature retrieval for injecting domain knowledge, NotebookLM-based document synthesis for contextual understanding, and a Claude Code multi-agent system for code generation and validation. Our integrated approach leverages intent clarification, retrieval-augmented generation, and specialized sub-agents orchestrated via Claude's agent framework. We demonstrate that this method significantly improves the accuracy and reliability of code assistants in real-world repositories, yielding higher single-shot success rates and better adherence to project context than baseline single-agent approaches. Qualitative results on a large Next.js codebase show the multi-agent system effectively plans, edits, and tests complex features with minimal human intervention. We compare our system with recent frameworks like CodePlan, MASAI, and HyperAgent, highlighting how targeted context injection and agent role decomposition lead to state-of-the-art performance. Finally, we discuss the implications for deploying LLM-based coding assistants in production, along with lessons learned on context management and future research directions.

Multimodal Retrieval-Augmented Generation (mRAG) has emerged as a promising solution to address the temporal limitations of Multimodal Large Language Models (MLLMs) in real-world scenarios like news analysis and trending topics. However, existing approaches often suffer from rigid retrieval strategies and under-utilization of visual information. To bridge this gap, we propose E-Agent, an agent framework featuring two key innovations: a mRAG planner trained to dynamically orchestrate multimodal tools based on contextual reasoning, and a task executor employing tool-aware execution sequencing to implement optimized mRAG workflows. E-Agent adopts a one-time mRAG planning strategy that enables efficient information retrieval while minimizing redundant tool invocations. To rigorously assess the planning capabilities of mRAG systems, we introduce the Real-World mRAG Planning (RemPlan) benchmark. This novel benchmark contains both retrieval-dependent and retrieval-independent question types, systematically annotated with essential retrieval tools required for each instance. The benchmark's explicit mRAG planning annotations and diverse question design enhance its practical relevance by simulating real-world scenarios requiring dynamic mRAG decisions. Experiments across RemPlan and three established benchmarks demonstrate E-Agent's superiority: 13% accuracy gain over state-of-the-art mRAG methods while reducing redundant searches by 37%.