Agents & autonomy

AI research often requires decisions before future evidence exists: which bottleneck to attack, which direction to pursue, or where a project should be positioned. We introduce ForeSci, a temporally controlled benchmark for evaluating whether LLM agents can make such forward-looking research judgements from historical evidence. ForeSci contains 500 tasks across four fast-moving AI domains and four decision families. Each task is paired with a cutoff-aligned offline knowledge base; post-cutoff pa

Agent-runtime systems emit traces, ledgers, provenance graphs, policy logs, delegation tokens, cache events, and tool-firewall records, but those containers do not necessarily answer governance questions about a specific decision. DEMM-Bench is a cross-regime benchmark for agent-runtime governance-evidence sufficiency, grounded in the Decision Evidence Maturity Model (DEMM): it measures whether records across eight evidence regimes are sufficient to reconstruct decision-level properties rather t

LLM agents are increasingly used in moderation-relevant public forum workflows, where their choices to answer, acknowledge, repair, or decline are routinely challenged by users, platforms, and regulators. The same agent often returns different responses on identical content, so any defense based on the agent's behavior cannot be reliably reproduced. The variation is structural. Four deployment choices typically invisible to the operator each shift the agent's response rate, and their combination

Large language models are increasingly deployed as tool-augmented agents to acquire information beyond parametric knowledge. While recent work has improved long-horizon tool-use reasoning, most approaches focus on tasks with a single correct answer. In contrast, many real-world queries require discovering a comprehensive set of valid answers, a setting known as Multi-Answer QA. This setting raises two challenges: fine-grained credit assignment over long search trajectories and reward alignment f

Agentic AI systems can plan over multiple steps, use tools, and execute tasks over time. When such systems cause harm, tort law struggles to allocate responsibility because the harmful path may be neither fully chosen by the user nor specifically foreseen by the developer. This paper proposes an interaction-based framework for agentic torts, drawing on Michael Bratman's planning theory and on the common law's treatment of human-human concerted action. We distinguish three interaction types: auto

We introduce SF-LIFE, a large-scale simulated movement dataset designed to accelerate research in transportation, mobility, and machine learning. The dataset contains 3,024,000,000,000 location records capturing complete, noise-free, multi-modality trajectories of 500,000 simulated agents observed at a 1Hz frequency navigating the San Francisco Bay Area network over a 70-day period. The data captures (1) needs-driven daily agendas of individual agents generated by an agent-based simulation of hu

As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerations surrounding these agents become paramount. Although much work has focused on agent safety in the presence of an adversary, we show that agents can exhibit misaligned behavior even in benign settings, taking unsafe actions when those actions are instrumental to task completion. We study this failure mode through the lens of corrigib

Large language models are undergoing a transition from model technology to system technology. Engineering challenges like cache reuse, context capacity, agent scheduling, and permission control resemble classical computer systems problems. This raises a question: if we treat the LLM as a CPU, KV cache as processor cache, context window as main memory, and agent framework as an operating system, can decades of computer architecture wisdom guide next generation model native systems? This paper pur

We argue that governance must transition from a normative discipline to an engineering discipline, and we develop a formal framework, inspired by the physics of metamaterials, to make this transition quantitative and testable. Artificial General Intelligence affects civilization primarily by increasing decision velocity while human verification capacity remains bounded. When the cost of validating AI-generated outputs exceeds the expected utility of acting on them, rational agents default to ina

Scientific research has traditionally been human-intensive, requiring researchers to coordinate literature, ideas, experiments, manuscripts, and review responses across long project cycles. The rise of LLM-based scientific agents creates an opportunity to automate this process. Such a system must support the full research lifecycle, maintain structured persistent memory across projects, and improve its own research procedures over time. However, existing systems either partially satisfy or fail

Real-world household robots require Vision-Language-Action (VLA) foundation models that can acquire reusable manipulation skills across diverse objects, task conditions, and household environments. Deformable-object folding is a representative challenge, requiring robots to handle clothing items from random initial states across varying categories, geometries, materials, and scenes. However, existing VLA systems commonly train separate policies for different object categories, while naively mixe

AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants tha

Monitoring autonomous language model agents currently relies mostly on surface behavior. But what happens when agent populations invent new languages with the goal of avoiding human oversight. Here, we study the emergent languages on Moltbook. For this, we build upon the Moltbook Files dataset and apply a two-stage approach consisting of a rule-based heuristic (about 6000 matches) followed by zero-shot classification (518 kept). The resulting categories include token efficiency (166), new natura

Outdoor vision-language navigation (VLN) in long-range, open-world environments is frequently disrupted by semantic-cue interruptions, where informative goal cues become sparse, occluded, or leave the field of view. Once such cues disappear, agents enter a cue-free phase and often degrade into backtracking, oscillatory headings, or aimless exploration. While memory-based methods attempt to bridge these gaps, they often fail under traversability-driven detours: the remembered cue direction may be

As large language models (LLMs) increasingly act as collaborative partners, human--AI alignment is often evaluated through explicit task success, accuracy, or reward optimization. Yet many collaborative settings depend on tacit understanding: whether an agent can align with a human's evaluative stance or representational priors without clear objectives, communication, or feedback. To study this capacity, we develop a spectrum-placement task inspired by the social party game Wavelength, in which

LLM-powered search agents enable multi-step reasoning and tool use. However, these capabilities introduce retrieval-induced safety degradation, as harmful intents may decompose into seemingly innocuous sub-queries that lead to unsafe outcomes. Existing alignment methods struggle to capture sparse safety signals and fail to supervise diverse violations across multi-step interactions. We propose COMPASS, a Cognitive MCTS-Guided Process Alignment framework designed to achieve robust safety alignmen

Agent skills externalise reusable agent-facing behavioural knowledge and guidance as persistent artefacts that can be discovered, activated, and interpreted by LLM agents. Although a skill artefact is static at rest, its architectural responsibilities arise in use, when the artefact is selected for a run, bound to context and authority constraints, interpreted by a stochastic agent, and recorded as run evidence. We call this run-specific relation skill-in-use. This paper studies agent skill harn

Vision-language models (VLMs) have achieved strong performance on visual question answering (VQA). To mitigate individual hallucinations and blind spots, aggregating diverse perspectives via multi-agent collaboration has emerged as a promising paradigm. While this approach has shown great success in textual QA, its potential in the multimodal domain remains under-explored. Existing multi-agent VQA methods predominantly adapt text-centric protocols, focusing on textual discussions while ignoring

Regulated cybersecurity workflows lack a runtime substrate that enforces organization-level scope across retrieval, tool calls, memory, findings, reports, and audit while remaining model-agnostic and locally deployable. Recent large language model (LLM) agent systems report strong results on isolated cybersecurity tasks, yet they do not by themselves define an auditable platform architecture for regulated security operations centre (SOC) and compliance workflows, where a single analyst may trigg

Personal AI agents must increasingly operate across APIs, shells, web surfaces, and desktop GUIs, yet many systems remain tuned to a single interface and offer limited support for user teaching and auditability. We present Syll, an open-source, self-hosted multimodal agent harness that unifies MCP/API tools, CLI execution, and visual GUI control in a modular runtime, enabling agents to coordinate computer use across heterogeneous interfaces while streamlining how users and agents exchange inform

We introduce Gram, an automated alignment auditing framework to assess the propensity of AI agents to engage in sabotage. We evaluate Gemini models across 17 simulated agentic deployment scenarios that incentivize sabotage. We find Gemini models misbehave in about 2-3% of our simulated trajectories. Many of these cases are explained by "overeagerness" in Gemini models resulting in both excessive role-playing and goal-seeking behavior. In contrast to other alignment auditing approaches, Gram is d

As autonomous language model agents proliferate, forming an emerging agentic web with real-world consequences, what credibility signals can you use to decide whether to trust an unfamiliar agent in the wild and delegate to it? A natural governance intuition is to extend human identity verification and reputation mechanisms, from "Know Your Customer" and credit scores to "Know Your Agent" regimes. However, we argue that this analogy is fundamentally incomplete. Reputation mechanisms function both

Chaotic dynamical systems pose a fundamental challenge for Reinforcement Learning (RL): exponential sensitivity to initial conditions induces high-variance bootstrap targets and poorly conditioned gradient updates. Chaotic dynamics arise across scientific and engineering domains, from fluid flows and climate systems to multi-agent systems, where reliable learning is highly desirable. Standard RL methods optimise expected returns through scalar value functions, implicitly averaging over diverging

Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social trajectories are irreversibly shaped, while real-world trials are slow, ethically constrained, and institutionally locked. LLM-based educational simulators have emerged as a potential remedy, but many still collapse learning into persona-conditioned role-play and, when optimized only to reproduce existing classrooms, can

We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential Social Dilemmas (SSDs). A researcher agent $\mathcal{R}$ (run as a coding agent) reads the inner-loop source code, edits system prompts, feedback functions, helper libraries, and iteration logic, runs evaluations, and decides what to keep, following the autoresearch paradigm. Across two games (Cleanup and Gathering), t

AI researchers have been advancing socially intelligent AI agents (Social-AI) across embodiments, from chatbots to physical robots. As Social-AI is increasingly deployed in everyday settings, decisions about the roles these agents should play will depend on how laypeople perceive them. However, public perceptions of social intelligence in AI agents and the acceptability of these agents remain largely understudied. We present a mixed-methods survey of adults in the United States (N=200) that exam

Large Language Models (LLMs) have advanced autonomous agents from deep search, which retrieves concise factual answers, to deep research, which synthesizes scattered evidence into long-form reports. However, verifiable multimodal deep research remains challenging due to open-ended synthesis without deterministic ground truth and the need to interleave textual arguments with visual evidence. We propose Ptah, a multi-agent harness for interleaved report generation. Ptah orchestrates the lifecycle

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current agent alignment frameworks inadequate for real-world deployment. To tackle these emerging threats, we propose a lightweight and scalable agent safety alignment framework. Specifically, we update the agent safety taxonomy to accommodate emergent risks from Codex a

End-to-end agent-memory benchmarks report a single hit@k per retriever, confounding lexical leakage (uncontrolled query/gold/distractor entity overlap) with tag-mixing (preferences, services, tools averaged together). We propose entity-collision, a system-agnostic protocol that pins the BM25 floor by construction -- every distractor shares the answer's entity tokens -- and stratifies queries by discriminator tag, so any lift over BM25 is attributable to the embedder. Applied to an open-source ag

As autonomous agents become more capable of performing real-world tasks, distinguishing scheming behavior from benign task pursuit may become a central AI control problem. Existing monitors often rely on chain-of-thought access or internal activations, or use prompted frontier models, all of which can be unavailable, unreliable or expensive in deployment. In this work, we study action-only deliberative monitors: smaller open-weight models trained to detect scheming and sabotage from agentic traj

As scientific literature grows rapidly, automated survey generation has become a key capability for AI scientists and human researchers. However, existing systems suffer from limited analytical depth due to reliance on abstracts and isolated paper processing, and unreliable citations from imprecise retrieval and post-hoc grounding, producing superficial surveys and may mislead researchers. We present DeepSurvey, an agentic system that addresses both. To enhance depth, DeepSurvey extracts structu

Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed modality configurations and task-specific architectures, leaving cross-modal interactions and the scaling laws of multimodal-conditioned synthesis largely underexplored. A key bottleneck is the scarcity of large-scale modality-aligned motion data, limiting generalization across diverse control signals. In this work, we i

AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of 20,574 coding-agent sessions from 1,639 repositories across IDE and CLI workflows. We operationalize misalignment as a breakdown made visible through developer pushback, and annotate each episode along four axes: form, cause, cost, and resolution. We identify

Automatic speech recognition (ASR) is a core component of human--computer interaction and an increasingly important front-end for LLM-based assistants and agents. However, most current ASR systems still follow a single-pass paradigm, which is poorly aligned with human communication, where misunderstandings are resolved through iterative clarification and refinement. This mismatch makes it difficult to correct meaning-critical errors once they occur. Meanwhile, token-level metrics such as WER or

The intricate nature of modern surgical care necessitates intelligent systems that can synthesize extensive patient records, support collaborative decision-making, and provide transparent, auditable reasoning across the entire perioperative workflow. Although web-based Large Language Models (LLMs) possess advanced reasoning capabilities, they are ill-equipped for surgical applications due to critical limitations: input length constraints, incomplete memory management, and limited traceability. T

Tool retrieval over large API catalogs is a core bottleneck for LLM agents: user queries arrive in colloquial, often underspecified language, while the catalog uses technical API vocabulary that no fixed encoder can bridge on its own. The two dominant training approaches, contrastive encoder fine-tuning and HyDE-style query expansion with a frozen LLM, address this problem from opposite ends and fail in complementary directions: the fine-tuned encoder excels when the query's surface form already

Role-playing with large language models is fundamentally a session-level task, requiring agents to sustain character identity and interaction quality across extended multi-turn conversations. Yet existing evaluation and optimization methods remain largely turn-level, failing to capture long-horizon quality. We propose DynSess, a unified session-level framework for role-playing agents. DynSess-Eval scores complete dialogue sessions via rubrics targeting long-horizon behaviors. Leveraging its sess

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven Open

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines t

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely manually constructed, providing only coarse start-goal annotations without intermediate trajectories, while recent automatic generation efforts remain expensive, biased, and shallow. These limitations prevent reliable training and evaluation of agents that mus