Large language models (LLMs) achieve impressive results on many benchmarks, yet their capacity for planning and stateful reasoning remains unclear. We study these abilities directly, without code execution or other tools, using the 8-puzzle: a classic task that requires state tracking and goal-directed planning while allowing precise, step-by-step evaluation. Four models are tested under common prompting conditions (Zero-Shot, Chain-of-Thought, Algorithm-of-Thought) and with tiered corrective feedback. Feedback improves success rates for some model-prompt combinations, but many successful runs are long, computationally expensive, and indirect. We then examine the models with an external move validator that provides only valid moves. Despite this level of assistance, none of the models solve any puzzles in this setting. Qualitative analysis reveals two dominant deficits across all models: (1) brittle internal state representations, leading to frequent invalid moves, and (2) weak heuristic planning, with models entering loops or selecting actions that do not reduce the distance to the goal state. These findings indicate that, in the absence of external tools such as code interpreters, current LLMs have substantial limitations in planning and that further progress may require mechanisms for maintaining explicit state and performing structured search.

While Large Language Model (LLM) agents are often approached from the angle of action planning/generation to accomplish a goal (e.g., given by language descriptions), their abilities to collaborate with each other to achieve a joint goal are not well explored. To address this limitation, this paper studies LLM agents in task collaboration, particularly under the condition of information asymmetry, where agents have disparities in their knowledge and skills and need to work together to complete a shared task. We extend Einstein Puzzles, a classical symbolic puzzle, to a table-top game. In this game, two LLM agents must reason, communicate, and act to satisfy spatial and relational constraints required to solve the puzzle. We apply a fine-tuning-plus-verifier framework in which LLM agents are equipped with various communication strategies and verification signals from the environment. Empirical results highlight the critical importance of aligned communication, especially when agents possess both information-seeking and -providing capabilities. Interestingly, agents without communication can still achieve high task performance; however, further analysis reveals a lack of true rule understanding and lower trust from human evaluators. Instead, by integrating an environment-based verifier, we enhance agents' ability to comprehend task rules and complete tasks, promoting both safer and more interpretable collaboration in AI systems. https://github.com/Roihn/EinsteinPuzzles

The episode length is 150 for RoboBin and RoboKitchen and 1000 for RoboY oga. We show all goals in Figure A.1. For both W alker and Quadruped, the success criterion is based on the largest violation across all joints. Global position is not taken into account for the success computation. For reaching task, the success is based on placing the arm in the correct position within 10 cm.

While existing benchmarks probe the reasoning abilities of large language models (LLMs) across diverse domains, they predominantly assess passive reasoning, providing models with all the information needed to reach a solution. By contrast, active reasoning-where an LLM must interact with external systems to acquire missing evidence or data-has received little systematic attention. To address this shortfall, we present AR-Bench, a novel benchmark designed explicitly to evaluate an LLM's active reasoning skills. AR-Bench comprises three task families-detective cases, situation puzzles, and guessing numbers-that together simulate real-world, agentic scenarios and measure performance across commonsense, logical, and symbolic reasoning challenges. Empirical evaluation on AR-Bench demonstrates that contemporary LLMs exhibit pronounced difficulties with active reasoning: they frequently fail to acquire or leverage the information needed to solve tasks. This gap highlights a stark divergence between their passive and active reasoning abilities. Moreover, ablation studies indicate that even advanced strategies, such as tree-based searching or post-training approaches, yield only modest gains and fall short of the levels required for real-world deployment. Collectively, these findings highlight the critical need to advance methodology for active reasoning, e.g., incorporating interactive learning, real-time feedback loops, and environment-aware objectives for training. The benchmark is publicly available at: https://github.com/tmlr-group/AR-Bench.

Efficient exploration is essential for intelligent systems interacting with their environment, but existing language models often fall short in scenarios that require strategic information gathering. In this paper, we present PAPRIKA, a fine-tuning approach that enables language models to develop general decision-making capabilities that are not confined to particular environments. By training on synthetic interaction data from different tasks that require diverse strategies, PAPRIKA teaches models to explore and adapt their behavior on a new task based on environment feedback in-context without more gradient updates. Experimental results show that models fine-tuned with PAPRIKA can effectively transfer their learned decision-making capabilities to entirely unseen tasks without additional training. Unlike traditional training, our approach's primary bottleneck lies in sampling useful interaction data instead of model updates. To improve sample efficiency, we propose a curriculum learning strategy that prioritizes sampling trajectories from tasks with high learning potential. These results suggest a promising path towards AI systems that can autonomously solve novel sequential decision-making problems that require interactions with the external world.

At the beginning of 2022, a simplistic word-guessing game took the world by storm and was further adapted to many languages beyond the original English version. In this paper, we examine the strategies of daily word-guessing game players that have evolved during a period of over two years. A survey gathered from 25% of frequent players reveals their strategies and motivations for continuing the daily journey. We also explore the capability of several popular open-access large language model systems and open-source models at comprehending and playing the game in two different languages. Results highlight the struggles of certain models to maintain correct guess length and generate repetitions, as well as hallucinations of non-existent words and inflections.

Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in long inputs. However, recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information within the input sequence. In this study, we conduct extensive experiments to investigate the root causes of positional bias. Our findings indicate that the primary contributor to LLM positional bias stems from the inherent positional preferences of different models. We demonstrate that merely employing prompt-based solutions is inadequate for overcoming the positional preferences. To address this positional bias issue of a pre-trained LLM, we developed a Position-Aware Parameter Efficient Fine-Tuning (PAPEFT) approach which is composed of a data augmentation technique and a parameter efficient adapter, enhancing a uniform attention distribution across the input context. Our experiments demonstrate that the proposed approach effectively reduces positional bias, improving LLMs' effectiveness in handling long context sequences for various tasks that require externally retrieved knowledge.

Abstract: We uncover how SGD interacts with batch normalization and can exhibit undesirable training dynamics such as divergence. More precisely, we study how Single Shuffle (SS) and Random Reshuffle (RR) -- two widely used variants of SGD -- interact surprisingly differently in the presence of batch normalization: RR leads to much more stable evolution of training loss than SS. As a concrete example, for regression using a linear network with batch normalization, we prove that SS and RR converge to distinct global optima that are "distorted" away from gradient descent. Thereafter, for classification we characterize conditions under which training divergence for SS and RR can, and cannot occur. We present explicit constructions to show how SS leads to distorted optima in regression and divergence for classification, whereas RR avoids both distortion and divergence.

For the stable optimization of deep neural networks, regularization methods such as dropout and batch normalization have been used in various tasks. Nevertheless, the correct position to apply dropout has rarely been discussed, and different positions have been employed depending on the practitioners. In this study, we investigate the correct position to apply dropout. We demonstrate that for a residual network with batch normalization, applying dropout at certain positions increases the performance, whereas applying dropout at other positions decreases the performance. Based on theoretical analysis, we provide the following guideline for the correct position to apply dropout: apply one dropout after the last batch normalization but before the last weight layer in the residual branch. We provide detailed theoretical explanations to support this claim and demonstrate them through module tests. In addition, we investigate the correct position of dropout in the head that produces the final prediction. Although the current consensus is to apply dropout after global average pooling, we prove that applying dropout before global average pooling leads to a more stable output. The proposed guidelines are validated through experiments using different datasets and models.