Goal-conditioned policies are generally understood to be "feed-forward" circuits,

Large Reasoning Models (LRMs) have become a central focus in today's large language model (LLM) research, where models are designed to output a step-by-step thinking process before arriving at a final answer to handle complex reasoning tasks. Despite their promise, recent empirical studies (e.g., [Shojaee et al., 2025] from Apple) suggest that this thinking process may not actually enhance reasoning ability, where LLMs without explicit reasoning actually outperform LRMs on tasks with low or high complexity. In this work, we revisit these findings and investigate whether the limitations of LRMs persist when tool augmentations are introduced. We incorporate two types of tools, Python interpreters and scratchpads, and evaluate three representative LLMs and their LRM counterparts on Apple's benchmark reasoning puzzles. Our results show that, with proper tool use, LRMs consistently outperform their non-reasoning counterparts across all levels of task complexity. These findings challenge the recent narrative that reasoning is an illusion and highlight the potential of tool-augmented LRMs for solving complex problems.

Shojaee et al. (2025) report that Large Reasoning Models (LRMs) exhibit "accuracy collapse" on planning puzzles beyond certain complexity thresholds. We demonstrate that their findings primarily reflect experimental design limitations rather than fundamental reasoning failures. Our analysis reveals three critical issues: (1) Tower of Hanoi experiments risk exceeding model output token limits, with models explicitly acknowledging these constraints in their outputs; (2) The authors' automated evaluation framework fails to distinguish between reasoning failures and practical constraints, leading to misclassification of model capabilities; (3) Most concerningly, their River Crossing benchmarks include mathematically impossible instances for N > 5 due to insufficient boat capacity, yet models are scored as failures for not solving these unsolvable problems. When we control for these experimental artifacts, by requesting generating functions instead of exhaustive move lists, preliminary experiments across multiple models indicate high accuracy on Tower of Hanoi instances previously reported as complete failures. These findings highlight the importance of careful experimental design when evaluating AI reasoning capabilities.

Solving puzzles in natural language poses a long-standing challenge in AI. While large language models (LLMs) have recently shown impressive capabilities in a variety of tasks, they continue to struggle with complex puzzles that demand precise reasoning and exhaustive search. In this paper, we propose Logic-of-Thought (Logot), a novel framework that bridges LLMs with logic programming to address this problem. Our method leverages LLMs to translate puzzle rules and states into answer set programs (ASPs), the solution of which are then accurately and efficiently inferred by an ASP interpreter. This hybrid approach combines the natural language understanding of LLMs with the precise reasoning capabilities of logic programs. We evaluate our method on various grid puzzles and dynamic puzzles involving actions, demonstrating near-perfect accuracy across all tasks. Our code and data are available at: https://github.com/naiqili/Logic-of-Thought.

We introduce a novel gradient-based approach for solving sequential tasks by dynamically adjusting the underlying myopic potential field in response to feedback and the world's regularities. This adjustment implicitly considers subgoals encoded in these regularities, enabling the solution of long sequential tasks, as demonstrated by solving the traditional planning domain of Blocks World - without any planning. Unlike conventional planning methods, our feedback-driven approach adapts to uncertain and dynamic environments, as demonstrated by one hundred real-world trials involving drawer manipulation. These experiments highlight the robustness of our method compared to planning and show how interactive perception and error recovery naturally emerge from gradient descent without explicitly implementing them. This offers a computationally efficient alternative to planning for a variety of sequential tasks, while aligning with observations on biological problem-solving strategies.

In dialogue, the addressee may initially misunderstand the speaker and respond erroneously, often prompting the speaker to correct the misunderstanding in the next turn with a Third Position Repair (TPR). The ability to process and respond appropriately to such repair sequences is thus crucial in conversational AI systems. In this paper, we first collect, analyse, and publicly release BlockWorld-Repairs: a dataset of multi-modal TPR sequences in an instruction-following manipulation task that is, by design, rife with referential ambiguity. We employ this dataset to evaluate several state-of-the-art Vision and Language Models (VLM) across multiple settings, focusing on their capability to process and accurately respond to TPRs and thus recover from miscommunication. We find that, compared to humans, all models significantly underperform in this task. We then show that VLMs can benefit from specialised losses targeting relevant tokens during fine-tuning, achieving better performance and generalising better to new scenarios. Our results suggest that these models are not yet ready to be deployed in multi-modal collaborative settings where repairs are common, and highlight the need to design training regimes and objectives that facilitate learning from interaction. Our code and data are available at www.github.com/JChiyah/blockworld-repairs

Goal-conditioned policies are generally understood to be "feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take. However, under what circumstances such a policy can be learned and how efficient the policy will be are not well understood. In this paper, we present a circuit complexity analysis for relational neural networks (such as graph neural networks and transformers) representing policies for planning problems, by drawing connections with serialized goal regression search (S-GRS). We show that there are three general classes of planning problems, in terms of the growth of circuit width and depth as a function of the number of objects and planning horizon, providing constructive proofs. We also illustrate the utility of this analysis for designing neural networks for policy learning.

Here are the most tweeted papers that were uploaded onto arXiv during April 2021. Results are powered by Arxiv Sanity Preserver. Representation Learning for Networks in Biology and Medicine: Advancements, Challenges, and Opportunities Michelle M. Li, Kexin Huang, Marinka Zitnik Submitted to arXiv on: 11 April 2021 Abstract: With the remarkable success of representation learning in providing powerful predictions and data insights, we have witnessed a rapid expansion of representation learning techniques into modeling, analysis, and learning with networks. Biomedical networks are universal descriptors of systems of interacting elements, from protein interactions to disease networks, all the way to healthcare systems and scientific knowledge. In this review, we put forward an observation that long-standing principles of network biology and medicine -- while often unspoken in machine learning research -- can provide the conceptual grounding for representation learning, explain its current successes and limitations, and inform future advances.

We are living through an AI renaissance thought wholly unimaginable just a few decades ago -- automobiles are becoming increasingly autonomous, machine learning systems can craft prose nearly as well as human poets, and almost every smartphone on the market now comes equipped with an AI assistant. Oxford professor Michael Woolridge has spent the past quarter decade studying technology. In his new book, A Brief History of Artificial Intelligence, Woolridge leads readers on an exciting tour of the history of AI, its present capabilities, and where the field is heading into the future. No part of this excerpt may be reproduced or reprinted without permission in writing from the publisher. In his 1962 book, The Structure of Scientific Revolutions, the philosopher Thomas Kuhn argued that, as scientific understanding advances, there will be times when established scientific orthodoxy can no longer hold up under the strain of manifest failures.