The path to higher network autonomy in 6G lies beyond the mere optimization of key performance indicators (KPIs). While KPIs have enabled automation gains under TM Forum Levels 1--3, they remain numerical abstractions that act only as proxies for the real essence of communication networks: seamless connectivity, fairness, adaptability, and resilience. True autonomy requires perceiving and reasoning over the network environment as it is. Such progress can be achieved through \emph{agentic AI}, where large language model (LLM)-powered agents perceive multimodal telemetry, reason with memory, negotiate across domains, and act via APIs to achieve multi-objective goals. However, deploying such agents introduces the challenge of cognitive biases inherited from human design, which can distort reasoning, negotiation, tool use, and actuation. Between neuroscience and AI, this paper provides a tutorial on a selection of well-known biases, including their taxonomy, definition, mathematical formulation, emergence in telecom systems and the commonly impacted agentic components. The tutorial also presents various mitigation strategies tailored to each type of bias. The article finally provides two practical use-cases, which tackle the emergence, impact and mitigation gain of some famous biases in 6G inter-slice and cross-domain management. In particular, anchor randomization, temporal decay and inflection bonus techniques are introduced to specifically address anchoring, temporal and confirmation biases. This avoids that agents stick to the initial high resource allocation proposal or decisions that are recent and/or confirming a prior hypothesis. By grounding decisions in a richer and fairer set of past experiences, the quality and bravery of the agentic agreements in the second use-case, for instance, are leading to $\times 5$ lower latency and around $40\%$ higher energy saving.

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance, controlling their reasoning processes remains challenging. This work presents a steering approach for thinking LLMs by analyzing and manipulating specific reasoning behaviors in DeepSeek-R1-Distill models. Through a systematic experiment on 500 tasks across 10 diverse categories, we identify several reasoning behaviors exhibited by thinking models, including expressing uncertainty, generating examples for hypothesis validation, and backtracking in reasoning chains. We demonstrate that these behaviors are mediated by linear directions in the model's activation space and can be controlled using steering vectors. By extracting and applying these vectors, we provide a method to modulate specific aspects of the model's reasoning process, such as its tendency to backtrack or express uncertainty. Our approach offers practical tools for steering reasoning processes in thinking models in a controlled and interpretable manner. We validate our steering method using three DeepSeek-R1-Distill models, demonstrating consistent control across different model architectures.

Current approaches to enhancing LLM reasoning follows two isolated paradigms: Monitor-Generate methods like Plan-and-Solve (Wang et al., 2023) and SELF-DISCOVER (Zhou et al., 2024) excel at strategic planning but lack mechanisms to verify whether selected strategies succeed; while Generate-Verify approaches like Self-Verification (Weng et al., 2022) and SELF-REFINE (Madaan et al., 2023) iteratively refine outputs but commence generation blindly without task assessment. This separation creates inefficiencies -- strategies fail without feedback, and refinement occurs without strategic grounding. We address this gap by implementing Flavell's cognitive monitoring model (1979) from the broader Monitor-Generate-Verify framework (Oh and Gobet, 2025), operationalising it as a three-phase iterative system. On GSM8K, preliminary results show 75.42% accuracy versus 68.44% for SELF-REFINE and 67.07% for Self-Verification, while requiring fewer attempts (1.3 vs 2.0) at 27-37% increased inference cost. These initial findings suggest upfront monitoring produces higher-quality initial solutions that reduce refinement needs, though evaluation beyond arithmetic reasoning is needed to establish generalisability.

Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However, whether planning is causally driven by this reasoning remains a critical but unverified assumption. To investigate this, we build Drive-Mind, a large-scale driving Visual Question Answering (VQA) corpus with plan-aligned Chain-of-Thought (CoT), automatically generated from nuPlan. Our data generation process converts sensors and annotations into structured inputs and, crucially, separates priors from to-be-reasoned signals, enabling clean information ablations. Using DriveMind, we train representative VLM agents with Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO) and evaluate them with nuPlan's metrics. Our results, unfortunately, indicate a consistent causal disconnect in reasoning-planning: removing ego/navigation priors causes large drops in planning scores, whereas removing CoT produces only minor changes. Attention analysis further shows that planning primarily focuses on priors rather than the CoT. Based on this evidence, we propose the Reasoning-Planning Decoupling Hypothesis, positing that the training-yielded reasoning is an ancillary byproduct rather than a causal mediator. To enable efficient diagnosis, we also introduce a novel, training-free probe that measures an agent's reliance on priors by evaluating its planning robustness against minor input perturbations. In summary, we provide the community with a new dataset and a diagnostic tool to evaluate the causal fidelity of future models. End-to-end autonomous driving learns planning directly from sensor data and has attracted sustained attention in both academia and industry commaai (2025); Chen et al. (2024); Hu et al. (2023); Jiang et al. (2023). Recent studies explore Vision Language Model (VLM) driving agents that combine the reasoning capability of large language models (LLMs) with visual perception in order to approximate human driving Wen et al. (2024); Zhang et al. (2024a). Chain of Thought (CoT) Wei et al. (2022) has been shown to enhance reasoning in LLMs Feng et al. (2023), and it is increasingly adopted in VLM driving agents to make the sequence of perception, analysis, and decision explicit Sima et al. (2025); Tian et al. (2024); Wang et al. (2024). The intention is to strengthen planning while improving interpretability and controllability. In this paradigm, the model generates a response that first articulates a CoT for reasoning, followed by the final planning trajectory. Consequently, planning is taken for granted as causally driven through the preceding CoT reasoning.

Chain-of-Thought (CoT) prompting improves reasoning in large language models (LLMs), but its reliance on unstructured text limits interpretability and executability in embodied tasks. Prior work has explored structured CoTs using scene or logic graphs, yet these remain fundamentally limited: they model only low-order relations, lack constructs like inheritance or behavioral abstraction, and provide no standardized semantics for sequential or conditional planning. We propose UML-CoT, a structured reasoning and planning framework that leverages Unified Modeling Language (UML) to generate symbolic CoTs and executable action plans. UML class diagrams capture compositional object semantics, while activity diagrams model procedural control flow. Our three-stage training pipeline combines supervised fine-tuning with Group Relative Policy Optimization (GRPO), including reward learning from answer-only data. We evaluate UML-CoT on MRoom-30k, a new benchmark of cluttered room-cleaning scenarios. UML-CoT outperforms unstructured CoTs in interpretability, planning coherence, and execution success, highlighting UML as a more expressive and actionable structured reasoning formalism.

Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning. However, in standard decoder-only architectures, these reasoning steps are externalized in natural language, improving interpretability at the cost of efficiency. To capture reasoning that is not easily represented in words, many works have explored recurrent architectures that aim to internalize reasoning in latent space, potentially supporting latent CoT. In this paper, we investigate whether such reasoning structures emerge in Huginn-3.5B, a depth-recurrent Transformer that reuses layers at inference time without increasing parameter count. We examine the model's internal behavior on arithmetic tasks using a suite of probing techniques including the Logit Lens and Coda Lens. Our findings reveal limited evidence of interpretable latent CoT by tracking rank trajectories of final and intermediate result tokens. Furthermore, we uncover significant probing inconsistencies across recurrent blocks, where the interpretability of hidden states depends heavily on both the layer index and the decoding method. Finally, we empirically show that increasing recurrence depth yields only marginal gains and falls well short of models that explicitly externalize reasoning steps. The code is available at https://github.com/wenquanlu/huginn-latent-cot.

The pursuit of artificial agents that can learn to master complex environments has led to remarkable successes, yet prevailing deep reinforcement learning methods often rely on immense experience, encoding their knowledge opaquely within neural network weights. We propose a different paradigm, one in which an agent learns to play by reasoning and planning. We introduce Cogito, ergo ludo (CEL), a novel agent architecture that leverages a Large Language Model (LLM) to build an explicit, language-based understanding of its environment's mechanics and its own strategy. Starting from a tabula rasa state with no prior knowledge (except action set), CEL operates on a cycle of interaction and reflection. After each episode, the agent analyzes its complete trajectory to perform two concurrent learning processes: Rule Induction, where it refines its explicit model of the environment's dynamics, and Strategy and Playbook Summarization, where it distills experiences into an actionable strategic playbook. We evaluate CEL on diverse grid-world tasks (i.e., Minesweeper, Frozen Lake, and Sokoban), and show that the CEL agent successfully learns to master these games by autonomously discovering their rules and developing effective policies from sparse rewards. Ablation studies confirm that the iterative process is critical for sustained learning. Our work demonstrates a path toward more general and interpretable agents that not only act effectively but also build a transparent and improving model of their world through explicit reasoning on raw experience.

AI-powered code assistants are widely used to generate code completions, significantly boosting developer productivity. However, these tools typically present suggestions without explaining their rationale, leaving their decision-making process inscrutable. This opacity hinders developers' ability to critically evaluate outputs, form accurate mental models, and calibrate trust in the system. To address this, we introduce CopilotLens, a novel interactive framework that reframes code completion from a simple suggestion into a transparent, explainable interaction. CopilotLens operates as an explanation layer that reconstructs the AI agent's "thought process" through a dynamic, two-level interface. The tool aims to surface both high-level code changes and the specific codebase context influences. This paper presents the design and rationale of CopilotLens, offering a concrete framework and articulating expectations on deepening comprehension and calibrated trust, which we plan to evaluate in subsequent work.

Large language models (LLMs) often generate natural language rationales -- free-form explanations that help improve performance on complex reasoning tasks and enhance interpretability for human users. However, evaluating these rationales remains challenging. While recent work has relied on binary preference judgments from humans or LLM judges, such evaluations are often opaque and coarse-grained, offering limited insight into what makes one rationale better than another. In this work, we rethink preference evaluation for LLM-generated rationales by asking: (1) What attributes define good rationales? (2) Can human preferences be explained by these attributes? (3) Can attribute-based evaluation overcome the limitations of binary comparisons? We identify a set of key rationale attributes from prior literature and assess them using automatic metrics, LLM judgments, and human annotations. We then analyze two standard human preference datasets MT Bench and Chatbot Arena using SHAP to identify which attributes best explain human preference outcomes. Finally, we re-evaluate model-generated rationales using attribute-specific ELO scores, revealing more nuanced model comparisons and insights. Our findings suggest that fine-grained attribute evaluations can better characterize rationale quality and guide future research toward more interpretable and reliable evaluation practices.

Effective financial reasoning demands not only textual understanding but also the ability to interpret complex visual data such as charts, tables, and trend graphs. This paper introduces a new benchmark designed to evaluate how well AI models - especially large language and multimodal models - reason in finance-specific contexts. Covering 3,200 expert-level question-answer pairs across 15 core financial topics, the benchmark integrates both textual and visual modalities to reflect authentic analytical challenges in finance. To address limitations in current reasoning approaches, we propose an error-aware learning framework that leverages historical model mistakes and feedback to guide inference, without requiring fine-tuning. Our experiments across state-of-the-art models show that multimodal inputs significantly enhance performance and that incorporating error feedback leads to consistent and measurable improvements. The results highlight persistent challenges in visual understanding and mathematical logic, while also demonstrating the promise of self-reflective reasoning in financial AI systems. Our code and data can be found at https://anonymous/FinMR/CodeData.