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。
Frontier black-box Large Language Model (LLM) agents are proficient at long-horizon reasoning and precise action generation. However, when it comes to a specific agentic task, they have no…
We present WorldStream, an open-ended 3D world model with three simultaneous capabilities: it extends playable terrain beyond any pre-specified map, acts on open-ended language in the running world,…
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through…
Training coding agents typically updates the policy while keeping the harness fixed. During training, trajectories reveal flawed repair strategies and interaction problems that vary across tasks and…
Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and environment…
Procedural generation plays a key role in synthetic data creation and game development, offering greater controllability, editability, and diversity than static mesh representations. However,…
Adapting existing manga into coherent animation that stays faithful to the source is a valuable yet challenging task. Existing methods either access the manga mainly through text, losing its…
Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the…
この論文では、現在のVision-Language-Benchmark（VLB）を超える、MLLMがアクティブな観察を実演できるようにするためのバenchmark、ActiveVisionを提案する。このActiveVisionは、人間の視覚が閉じたループであるという事実に基づいて、観察対象物の予測を実行するために、視覚と言語を相互に関連させ、対象物にアクセスする。
Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close such gaps…
Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and verifying them---especially for nonlinear, high-dimensional systems---remains an…
Diffusion language models form answers through a sequence of revisable continuous states, but multi-agent systems usually discard those states and make agents communicate only after decoding text. We…
Realistic market impact is essential for generative limit order book (LOB) models to serve as world models for trading agents. If a simulator misprices this mechanism, agents learn policies that are…
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a…
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as…
Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks…
Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with…
Retail sales forecasting underpins inventory planning, yet promotions and calendar events reshape short-term demand. Although each factor usually has historical occurrences, the complete factor…
Online vectorized map construction provides autonomous vehicles with essential, real-time semantic and geometric scene understanding. While leveraging prior maps presents an opportunity to improve…
Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on…
In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leader and the subagents is difficult because a final answer gives only indirect…
Modern image generation largely relies on specialized generative models that leave the process of image construction implicit in learned parameters. We explore an alternative: general-purpose coding…
Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after each question and redo it from scratch…
Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and…