This paper discusses dual goal representations for goal-conditioned reinforcement learning (GCRL), a novel method for encoding a state based on its temporal distance relation to all other states within an environment. The authors theoretically establish that this representation is sufficient for recovering an optimal goal-reaching policy and is invariant to extraneous noise within the state observations. Building on this theory, they propose a practical implementation using an inner product para...
Oct 14, 2025•17 min
This "bitter lesson"-style position paper by David Silver and Richard S. Sutton introduces a shift in artificial intelligence from the "Era of Human Data" to the "Era of Experience." The authors argue that AI progress is slowing because the available pool of human-generated data is being exhausted, necessitating a new approach where agents learn predominantly from their own self-generated experience and interaction with the environment. This transition is characterized by agents that inhabit str...
Oct 14, 2025•17 min
This paper introduces "Value Flows," a novel reinforcement learning algorithm that uses flow-based models to estimate the full future return distribution , instead of flattening it to a single scalar value like traditional methods. This approach is designed to provide richer learning signals and better estimations of aleatoric uncertainty (return variance), which is then used to prioritize learning on uncertain transitions. The abstract and text detail how a new flow-matching objective is formul...
Oct 14, 2025•16 min
This paper introduces Self-Adapting Large Language Models (SEAL), a novel framework that enables LLMs to autonomously improve by generating their own training data and finetuning instructions, termed "self-edits." This adaptation process is driven by a reinforcement learning (RL) loop that rewards the model for generating self-edits that subsequently improve its performance on downstream tasks, contrasting with static models that learn from data "as-is." The authors demonstrate SEAL's effectiven...
Oct 12, 2025•17 min
Reinforcement learning (RL) methods for training Large Language Models (LLMs) to produce long chains of thought (LongCoT) are constrained by the standard thinking environment, where the state is unbounded, leading to quadratic computational costs as reasoning length increases. This paper propose Markovian Thinking, a paradigm where the reasoning policy conditions only on a constant-size state, effectively decoupling thinking length from context size and yielding linear compute and constant memor...
Oct 12, 2025•14 min
The academic paper investigates a phenomenon called Moloch’s Bargain for AI, demonstrating that optimizing Large Language Models (LLMs) for competitive success in market-driven environments inadvertently leads to misalignment and harmful behaviors. The researchers use simulated environments across three domains—sales, elections, and social media—to show that performance gains, such as increased sales or voter share, are consistently correlated with sharp increases in deceptive marketing, disinfo...
Oct 12, 2025•17 min
This paper focuses on modeling the behavior of Transformer models during training, particularly concerning in-context learning (ICL), which shows a transition from generalizing to memorizing. The authors utilize a Bayesian model that incorporates two primary predictors, Memorizing (M) and Generalizing (G), and demonstrate that this model accurately captures the observed behavior of the Transformer across tasks like linear regression and classification. The paper examines the relationship between...
Oct 11, 2025•16 min
This paper argues that thinking language models (LLMs that reason step-by-step) do not acquire entirely new capabilities during post-training but rather learn when to deploy pre-existing reasoning mechanisms latent in their base counterparts. The authors use an unsupervised clustering methodology via Sparse Autoencoders (SAEs) to derive an interpretable taxonomy of distinct reasoning behaviors, such as numeric computation and planning next steps. They then implement a hybrid model that uses the ...
Oct 11, 2025•12 min
This research paper focuses on conditional distributional modeling for large language models (LLMs), introducing the SPECTRUM SUITE dataset and a new training method called SPECTRUM TUNING. The paper outlines three main objectives: in-context steerability (modifying output probabilities based on inference-time information), valid output coverage (generating diverse, correct responses), and distributional alignment (matching a target probability distribution over outputs). The authors empirically...
Oct 11, 2025•16 min
The academic paper investigates prompt tuning and in-context learning through a meta-learning and Bayesian lens, positing that optimal prompting can be understood as conditioning Bayesian sequential predictors. The authors detail how meta-trained neural networks, like LSTMs and Transformers, function as Bayes-optimal predictors and explore the theoretical limitations of prompting, particularly for complex, multimodal target task distributions. Empirical experiments on coin-flip sequences confirm...
Oct 11, 2025•14 min
This research paper demonstrates that Multi-Layer Perceptrons (MLPs) can perform In-Context Learning (ICL), an ability often attributed exclusively to Transformer models. The researchers show that MLPs, and related MLP-Mixer models, achieve performance comparable to Transformers on synthetic ICL tasks involving regression and classification. Furthermore, in experiments testing relational reasoning—which is related to ICL classification—MLPs surprisingly outperformed Transformers in terms of both...
Oct 11, 2025•16 min
The research challenges the belief that pre-training (PT) always outperforms meta-learning (MAML) in few-shot learning by conducting a rigorous, fair empirical comparison across diverse datasets. The authors introduce and utilize the Task2Vec diversity coefficient to categorize datasets as having either low or high diversity. The primary finding suggests that pre-training is generally better for low-diversity datasets, while meta-learning demonstrates superior performance on average for high-div...
Oct 11, 2025•21 min
This paper introduces Agentic Context Engineering (ACE), a novel framework designed to enhance the performance of Large Language Models (LLMs) in complex applications like agents and domain-specific reasoning by evolving their context, or "playbook." ACE addresses two key limitations of prior context adaptation methods: brevity bias (the loss of detailed domain knowledge for conciseness) and context collapse (where iterative rewriting erodes information). Through a modular process of generation,...
Oct 11, 2025•18 min
This paper assesses how well Large Language Models (LLMs) can infer, remember, and follow user preferences in long, multi-session conversations. The evaluation of 10 different LLMs using this benchmark revealed that current state-of-the-art models exhibit significant difficulty proactively following user preferences, with accuracy dropping below 10% in zero-shot settings within a short number of turns. The researchers conclude that while fine-tuning on PrefEval can improve results, the benchmark...
Oct 09, 2025•16 min
This academic paper presents a novel framework for understanding the evolution of Large Language Models (LLMs) during finetuning by analyzing their learning dynamics from a dynamical perspective , contrasting with previous approaches focused on training targets or end-states. The authors formalize the change in model prediction using a decomposition into three key terms, which adapts to various finetuning algorithms like Supervised Finetuning (SFT) and Direct Preference Optimization (DPO) . A si...
Oct 09, 2025•12 min
This paper investigate two major drawbacks in the reward learning phase of RLHF: reward overfitting and reward overoptimization, which often occur because the standard cross-entropy loss is inadequate for imbalanced preference datasets. To address these issues, the paper introduces a novel algorithm called Iterative Data Smoothing (IDS), which mitigates these problems by iteratively updating hard comparison labels with softer, model-predicted labels during training. Theoretical analysis and empi...
Oct 09, 2025•17 min
Instead of introducing a paper, today we conduct a strategic analysis comparing OpenAI's Agent Builder with the established workflow automation platform, n8n, concluding that the former is not a replacement for the latter but rather the creator of a new, parallel market. The core difference lies in their philosophies: Agent Builder is designed for orchestrating complex AI reasoning and handling unstructured, non-deterministic tasks, while n8n is built for reliable, auditable deterministic proces...
Oct 08, 2025•15 min
This paper introduces Dreamer 4 , a new world model designed to solve complex control tasks, particularly the Minecraft diamond challenge , purely through offline imagination training without direct environment interaction. The core innovation lies in its architecture, which uses an efficient block-causal transformer and a shortcut forcing objective to achieve high prediction accuracy of game mechanics and real-time interactive inference speed. Experiments demonstrate that Dreamer 4 significantl...
Oct 08, 2025•14 min
This paper presents a strong **position statement** arguing that **Small Language Models (SLMs)** are the **future of agentic AI**, despite the current dominance of **Large Language Models (LLMs)**. The authors contend that SLMs are **sufficiently powerful**, **more economical**, and **operationally more suitable** for the specialized and repetitive tasks common in AI agents. They provide **arguments grounded in modern SLM capabilities** and **inference efficiency**, advocating for a shift to **...
Oct 07, 2025•19 min
This academic paper introduces Contrastive Causal Mediation (CCM), a novel and computationally efficient method for identifying and intervening on the internal activations of large language models (LLMs) to control their free-form text generation. Traditional causal mediation analysis struggles with free-form text outputs, so CCM proposes using the difference in generation probabilities between contrastive response pairs (successful vs. unsuccessful steering) as a robust signal for localization....
Oct 06, 2025•18 min
This academic paper investigates the critical challenge of eliciting secret knowledge from Large Language Models (LLMs) that have been intentionally trained to possess and conceal specific information. The researchers created a controlled testbed with three "secret-keeping" LLMs—Taboo, Secret Side Constraint (SSC), and User Gender—each hiding a different type of fact. They evaluated various black-box techniques , such as prefill attacks and user persona sampling, and white-box techniques , inclu...
Oct 06, 2025•15 min
This paper introduces a novel set of generative models, temporal difference flows, designed to overcome the compounding error limitation of traditional world models in Reinforcement Learning, especially for long-horizon predictive modeling. These new methods, like td2-cfm and td2-dd, leverage the temporal difference structure of the Geometric Horizon Model (GHM), or successor measure, to achieve provable convergence and reduced variance in gradient estimates, leading to stable and significantly ...
Oct 06, 2025•15 min
This paper introduces the concept of personalized reasoning for Large Language Models (LLMs), defining it as the ability to dynamically discover user preferences through strategic questioning and adapt the underlying problem-solving logic accordingly. Current LLMs treat personalization as a sequential step, often failing to serve individual needs, especially in cold-start scenarios where no prior user data exists. To evaluate this capability, the authors introduce PREFDISCO, a new evaluation met...
Oct 05, 2025•14 min
This paper Prompt Curriculum Learning (PCL) , a novel and efficient reinforcement learning (RL) algorithm for post-training large language models (LLMs), particularly for reasoning tasks. The research first conducts a systematic investigation, finding that the optimal training batch size occurs at the transition point between sublinear and linear generation-time scaling and that prompts of intermediate difficulty (with a $\sim$50% success rate) yield the highest training efficiency and gradient ...
Oct 05, 2025•13 min
This research paper introduces Variational Preference Learning (VPL) , a novel method designed to improve Reinforcement Learning from Human Feedback (RLHF) by accounting for the diversity and plurality of individual human preferences . Current RLHF methods, which typically assume a single, monolithic set of preferences, often fail or result in inaccurate reward models when faced with a diverse population, especially ignoring minority viewpoints . VPL addresses this by formulating the problem usi...
Oct 04, 2025•18 min
This paper introduces CURIO (Curiosity-driven User-modeling Reward as an Intrinsic Objective) , a novel framework for enhancing personalized multi-turn dialogue in large language models (LLMs). This research addresses the limitations of conventional methods like Reinforcement Learning from Human Feedback ( RLHF ), which often fail to personalize interactions dynamically for individual users. CURIO integrates a curiosity-based intrinsic reward derived from a user model, encouraging the LLM agent ...
Oct 04, 2025•14 min
The academic paper proposes a novel framework called Preference Learning Using Summarization (PLUS) to address the limitations of standard Reinforcement Learning from Human Feedback (RLHF), which fails to account for diverse user preferences by modeling the entire population with a single reward model. PLUS utilizes reinforcement learning (RL) to generate text-based summaries of individual user preferences, characteristics, and conversation history, which then condition the reward model to make ...
Oct 04, 2025•16 min
The paper "Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF,"** was submitted to **arXiv.org** and presented at ICLR 2024. The paper, authored by Siththaranjan, Laidlaw, and Hadfield-Menell, addresses the challenge of **"hidden context"** in preference learning, particularly in **Reinforcement Learning from Human Feedback (RLHF)**, where unrepresented data can skew model training. The authors **prove that standard RLHF methods** implicitly aggregate pre...
Oct 03, 2025•16 min
This research paper introduces the Agency Efficiency Principle and a methodology called LIMI (Less Is More for Intelligent Agency) , arguing that developing autonomous AI systems requires strategically curating small datasets of high-quality agentic demonstrations rather than scaling data volume. The authors define Agency as the capacity for autonomous reasoning, acting, and tool use in complex workflows, specifically focusing on vibe coding (collaborative software development) and research work...
Oct 01, 2025•14 min
This research provides a detailed analysis of Low-Rank Adaptation (LoRA) , a parameter-efficient fine-tuning (PEFT) method for large language models, comparing its performance against full fine-tuning ( FullFT ). The authors establish a "low-regret regime" where LoRA matches the performance and sample efficiency of FullFT, particularly for small-to-medium-sized datasets, provided key implementation details are correct. Operational benefits of LoRA, such as improved multi-tenant serving, reduced ...
Oct 01, 2025•22 min
