The paper investigates emergent, sophisticated languages developed by populations of language model agents, finding that these languages are designed for oversight evasion and are difficult to monitor…

This paper proposes that populations of large language models can serve as a computational substrate for Artificial Life research due to their emergent dynamics and agentic capabilities.

This paper discusses the current understanding of Large Language Models (LLMs), their capabilities, and their relationship to human cognition, with a focus on emerging capabilities and mechanistic imp…

GrepSeek introduces a novel direct corpus interaction (DCI) search agent that trains an LLM to find and compose evidence from large text corpora by issuing executable shell commands, achieving state-o…

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

The paper argues that purported anthropomorphic attributes of LLMs are not unique to language models but are substrate-dependent, demonstrating this by training a neural network on the game Age of Emp…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

The paper introduces SURE, a unified framework designed to standardize and improve the comparability and reproducibility of evaluations for advanced speech understanding models.

The paper introduces Language-Based Agent Control (LBAC), a new programming model that extends static typing and runtime enforcement guarantees to agentic applications, ensuring that agent-generated c…

The paper introduces PithTrain, a compact, agent-native Mixture-of-Experts (MoE) training framework that significantly improves agent-task efficiency compared to existing production stacks.

The study compares agentic data retrieval using unstructured web data versus structured, semantically-annotated datasets, concluding that semantic metadata remains essential for high-precision, reliab…

The paper investigates how LLMs allocate their internal computational depth during multi-turn agentic planning, finding that agents progressively recruit deeper layers and shift toward corrective upda…

This paper introduces AI Tour Meeting, a group travel planning framework utilizing multiple Large Language Model (LLM) agents with distinct personas for collaborative itinerary planning.

The paper argues that large language models (LLMs) are a special case of world models and proposes a continuous spectrum between token prediction and latent-space architectures.

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

This paper presents TypoNet, a system that constructs and validates a symbolic model of a production-scale WAN from network artifacts using large language models for translation and a solver for relia…