MLINFO COLLECTION
ツール利用、計画、マルチエージェント、コード実行などエージェント実装に関係する情報です。
We present an AI-assisted mathematical addendum to Strategic Trip Planning: Striking a Balance Between Competition and Cooperation (Amar, 2018). We reconstruct selected relationships between…
Sidewinding is an efficient gait for snake robots to locomote on various terrains, by undulating the backbone curve and shifting the contact segments along it. However, relying solely on undulatory…
Personalized shopping benchmarks ask which item fits the user; we ask how far an agent may commit on that item, and pose learning the individual's auto-purchase line as a task. The boundary is…
We consider the problem of allocating indivisible goods to agents with additive valuations, under two classic notions of fairness and efficiency: envy-freeness up to any good (EFX) and Pareto…
Monte-Carlo Tree Search (MCTS) typically stores only scalar mean estimates, which makes it poorly suited for tail-risk objectives such as conditional value-at-risk (CVaR). We introduce Categorical…
Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs) and integrated circuits…
Most high-performing end-to-end autonomous driving agents (ADAs) are developed for the CARLA Leaderboard, tightly coupling them to CARLA's APIs, sensor layouts, coordinate systems, and internal…
Envy-free cake cutting asks how to divide a resource so that no agent prefers another agent's share. Finding such a division with few queries about preferences has been a longstanding challenge.
World-Action Models (WAMs) have emerged as a promising paradigm for embodied generalist policies by jointly modeling future world evolution and robot actions across diverse manipulation tasks.…
Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability, when sensor…
Groundwater in Ghana's Densu River Basin remains a key domestic water source, but multi-metal contamination threatens children's health. Previous deterministic hazard index assessments provide…
In the classical necklace splitting problem, beads of different colors lie on a line, and the goal is to divide them among $k$ agents using as few cuts as possible so that every agent receives the…
General-purpose manipulators can position ophthalmic instruments under a software Remote Centre of Motion (RCM). However, at some reachable configurations that are nonsingular for the tip task alone,…
Given an incentive-compatible mechanism for a single agent on a restricted domain of valuations, we consider its incentive-compatible extensions to the entire valuation space. We identify two extreme…
Car-following (CF) models is a fundamental component of microscopic traffic simulation and underpin the analysis of collective traffic dynamics, while its modeling becomes more challenging due to…
Model-based reinforcement learning in partially observable environments requires inferring hidden states, learning latent dynamics, and planning under the resulting belief. Practical algorithms often…
Bayesian mixtures, and Solomonoff induction in particular, provide an idealized model of prediction learned by minimizing population log loss, and they underlie universal agents such as AIXI. An…
In large language model (LLM)-based multi-agent systems, reported confidence increasingly determines the allocation of scarce downstream attention, computation, and decision influence. This makes…
Game theory identifies when a strategic action should be accepted, but not how long a live, language-based counterpart will continue to accept it. We entered the GLEE competition in its final week…
Web platforms organize collective work, including content review and community maintenance, that imposes heterogeneous effort costs on participants. Fairly distributing these burdens while leaving as…
How can a shared resource be allocated without money when agents have private, stochastic demands that can be queued for a while, and may behave strategically, or even adversarially? We introduce a…
We consider online monitoring of an AI system that produces a sequence of decisions. At each round, the system outputs a proposed decision together with a confidence score estimating the…
Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action…
Multilingual pipelines such as FineWeb2 apply one recipe across a thousand languages, leaving the failure modes of individual languages unanticipated. We use an LLM once, as a corpus debugger rather…