Research
Papers and datasets worth knowing, ranked by significance and community attention.
Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks
We introduce Memento 3, building on the Memento series to enable frozen LLM agents to continually learn explicit world models through external memory.
PaperRISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents
In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope.
Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction.
SuperNav: An Agentic Navigation System for Any Task in Any Scene
General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality.
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
We propose a different view: the embodied world is an Embodied Turing Machine, whose tape is the robot and environment state and rules are the policy.
OneSearch-VL: Unified Multimodal Deep Research Agent for Image and Video
We introduce OneSearch-VL, a unified agent centered on the Visually Grounded Evidence Graph (VGEG), which encodes these dependencies as a shared task-level reference for data construction, process supervision, and operation-level evaluation.
WorldGuide: Goal-Directed Video World Model for Procedural Task Execution
We formulate procedural video generation as closed-loop task execution in visual world space and introduce WorldGuide.
AgentGarten: Code Worlds for Evolving Agents
We introduce AgentGarten, a framework that couples simulators and game engines with a shared neural renderer to build real-time interactive environments.
Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station
Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they can autonomously undertake open-ended scientific discovery remains unclear.
CADFather Reconstructs Parametric CAD Programs Using Coordinated Tools
CADFather is an autonomous agentic system that coordinates complementary tools and a vision-language assistant to reconstruct parametric CAD models from 3D meshes without additional training.
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation
We explore agentic language world modeling: rather than rebuilding an executable environment, a world model agent serves as the environment for a task agent and supports faithful and stateful simulation.
Agent Plasticity: Measuring Self-Improvement Through Experience
We introduce agent plasticity, the efficiency with which an agent converts experience into gains in future held-out performance.
Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict
We propose to evaluate agents on epistemic humility (EH): the agent's willingness to recognize, act on, and communicate uncertainty during task execution.
MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent
To bridge this gap, we formulate text-to-music intent alignment as satisfying a per-request rubric of independently verifiable items covering both a request's explicit requirements and its implied musical intent.
A self-learning scientific agent for X-ray diffraction
Here we introduce Gan Jiang, a self-learning agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM.
Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub
Agent skills are SKILL.md instructions and scripts that AI coding agents such as Claude Code and Codex run with the permissions of their user.
Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff
Here, we develop an ecological theory of AI-agent populations based on a population growth equation in which fitness (growth rate) depends on cybersecurity capability.
Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System
Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding agent and AI agent.
Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents
Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently compute a same-named key performance indicator (KPI) through conflicting logic.
RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design
We present RFChipAgent, a first-of-its-kind multi-agent flow of large language model (LLM) agents for end-to-end analog/RF circuit design automation, in which AI agents collaboratively orchestrate the complete design flow under human supervision.
Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming
Developing optimization models for production scheduling requires substantial expert effort.
GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks
We introduce GeoNatureAgent (GNA), a framework for pre-production evaluation of tool-using agents: a fixed sixteen-tool geospatial interface published as a Model Context Protocol (MCP) server, so the agent under test is the only variable, scored against an identical tool layer, task suite, and deterministic scorer.
Shared and structured inputs undermine collective random choice by reasoning AI agents
Random selection is widely used in resource allocation and auditing, making reliable implementation essential for AI-agent systems.
Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents
We present a multi-aspect runtime-verification framework that decomposes a natural-language policy clause into a typed spatial/temporal/semantic triple over one canonical event stream, checks each aspect with its own monitoring specification, and fuses the verdicts through a four-valued algebra that carries provenance.
Code Understanding is a Bottleneck for Coding Agents
We present CABRA: a Coding Ability Blueprint for Rigorous Agent evaluation.
AgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
To this end, we introduce AgentHorizon, a benchmark of 1,373 computer-use tasks (instruction-trajectory pairs) drawn from 166 hours of human-recorded trajectories spanning three operating systems.
EIO-Agents: The Missing Semantic Layer for AI Agent Evaluation
We introduce EIO-Agents, an open specification for interoperable AI agent evaluation built on two layers.
Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation
Language-model agents favor their own group because they have watched their members favor each other.
Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study
We describe an advisory cross-provider review contract: distinct resource pools, bounded execution, restricted reviewer capabilities, complete input delivery, usable semantic output, explicit failure states and durable per-attempt evidence.
What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
To support these judgments, we propose the Evidence-Grounded Behavior Graph (EBG), a training-free method that groups source-linked evidence into behaviors and organizes their relationships into a graph.
I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papers
We study the construction rather than in ACL papers from 2019, ACL-style arXiv papers from 2026, and papers written by GPT models from the same titles and abstracts.
AgentTime: Can Agents Estimate and Control Their Own Runtime?
We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate elapsed time afterward.
POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents
We propose POLAR, a guardrail framework for small tool-calling agents that assesses reversibility through a structured two-layer ontology.
Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance
Inspired by the interplay of inheritance and selection in biological evolution, we introduce Inherit-MAS, which makes inheritance explicit at the workflow and execution levels.
When the Governor Becomes the Disturbance: Control-Generated Disturbance and Cost-Aware Backoff in Governed Tool-Using Agents
We study this possibility in a controlled file-recovery environment where increases in regulatory intensity trigger experimentally imposed tool failures.
How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression
To obtain such a variable, we propose a method that converts complex agentic prompts into minimal contrastive pairs in which a single request verb determines the tool-call decision: replacing an execution-verb (e.g., write) with an analysis-verb (e.g., discuss) reliably flips the decision, suggesting it is mediated by a compact internal state.
WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?
LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films.
AgentEvolver: System-Wide Self-Evolution Through Task Execution
We present AgentEvolver, a system for developing capabilities during task execution while keeping the foundation model fixed.
Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor
Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents.
nanoMuse: An Open-Source Personal Agent for Every Device You Own
In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country.
SparseEngine: Sparse-First Inference Engine
We present SparseEngine, a ground-up, sparse-first inference engine whose shared lifecycle contract lets each method control its KV representation and computation while coordinating state transitions with common serving infrastructure.
ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks
We introduce ST-Bench, a benchmark designed to answer two questions: whether MAS outperform single agents on complex scientific data analysis tasks, and if so, by how much and at what additional cost.
Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
To address these challenges, we introduce E-Ledger, a multi-agent harness for safe and persistent execution.
One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text.
Ream: Unfolding Mutual Awareness in Human-Agent Workspaces
We present Ream, a literature review workspace that supports mutual awareness through structured artifacts, bidirectional engagement tracking, and localized visualizations.
Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System
An agentic system issues several structurally different kinds of LLM calls.
Mental-Models for Multi-Agent Systems
We introduce mental-model-enabled agents, a framework that equips an agent with a latent mental model of its counterpart, allowing it to infer hidden beliefs, intentions, and likely reactions from the observed history and use these inferences to guide action selection.