The paper introduces RePoT, a method that significantly improves Program-of-Thought (PoT) planning by deterministically verifying the initial plan prefix and using a single LLM call to resume planning…

The paper proposes using GUI agents, both as objective evaluators and subjective playtesters, to significantly improve the generation of playable games from prompts, demonstrating a 66.8% rubric pass-…

This paper analyzes the computational complexity of evaluating recurrent functions, showing that the complexity depends heavily on how the input offsets are encoded and the structure of the recurrence…

The paper proposes Predictive Routing Replay (PR2) to stabilize reinforcement learning on Mixture of Experts (MoE) LLMs by predicting and incorporating short-horizon router evolution during training a…

This paper studies the problem of retrospectively reconstructing commit history from squashed patches, and evaluates different methods using a benchmark dataset.

This paper explores the use of GPT-4o in game development using a Python/Pygame endless runner, examining refactoring and gameplay feature generation tasks.

This paper introduces Repeated Policy Regret (RP-Regret), a novel game-theoretic metric for analyzing regret in repeated games with adaptive opponents, and proposes algorithms to minimize it.

ACRFence introduces a framework-agnostic mitigation to prevent semantic rollback attacks in LLM agents by recording irreversible tool effects and enforcing strict replay-or-fork semantics upon checkpo…

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 JAMEL framework addresses the challenge of effective exploration in open-ended environments by jointly training agent memory and exploration policies using natural, novelty-driven signals.

The paper introduces MineExplorer, a new benchmark in Minecraft, to evaluate the sustained open-world exploration capabilities of MLLM agents, finding that long-horizon coordination remains a signific…

The paper introduces 'layered mutability,' a framework for analyzing how persistent self-modifying AI agents drift away from intended behavior due to the accumulation of locally reasonable, uncoordina…

The paper conducts a reproducibility study on FACTER, a model-agnostic framework for fairness and statistical coverage in LLM-based recommendation, and evaluates its consistency and contribution.

This paper proposes Trellis, a data foundation that treats experience graphs from long-horizon agentic tasks as first-class, governed, queryable database state.

The paper introduces ReproRepo, a scalable framework for evaluating the reproducibility of machine learning research using LLM agents and human-raised GitHub issues.