Work Agents: Systems, Capabilities, and Optimization
As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workf...
Papers
StreamVibe: Proactive Video Agents for Evolving User Intent
Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss...
Constrained Decoding: Harmful or Beneficial? Revisiting Its Impact on LLM Performance
Constrained decoding guarantees that Large Language Models (LLMs) produce outputs conforming to predefined formats, but is often assumed to inherently degrade reasoning. We examine...
The Lexical Imprint of Pre-training Data
How much of zero-shot benchmark accuracy is captured by word-level alignment between a pre-training corpus and the benchmark target? We study this question through word-level unigr...
SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding
Perceiving human body motion is critical for multimodal systems that understand and assist people. Yet current evaluations of Multimodal Large Language Models (MLLMs) largely focus...
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (...
Thinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents
Language model agents often abandon correct work when a user challenges it, yet simply telling them to stand firm makes them ignore real mistakes. Once an agent reads a complaint, ...
EmbodiedLab: Benchmarking Embodied Agents That Act to Know
Embodied agents are expected to accomplish real-world goals by deciding for themselves how and when to interact with their surroundings. For many such goals, changing the physical ...
How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning
Financial institutions operating under data-residency constraints are restricted to open-weight models small enough to locally host, which trail frontier systems on multi-step quan...
SearchHorizonBench: A Benchmark for Search Value in AI Agents
AI agents must decide when another search is worth its cost. Answer-success probabilities capture question difficulty, while this decision requires estimating the additional benefi...
CEPO: A General Framework for Improving Prompt Optimization in Multi-Agent Systems
Multi-agent systems (MAS) require both effective coordination and specialized task execution. Existing prompt optimization approaches typically couple these functions within agent-...
Benchmarking Obstacle-Conditioned Safety in Household Robot Navigation
Safe household navigation requires robots to regulate clearance and speed according to what an obstacle is and how close it is, without unnecessary conservatism. Yet existing evalu...
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing ...
Harness-Model Collaboration for Long-Horizon Continual Learning
Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent lear...
Cross-modal Steering Vectors Exist Across Both Image and Text Generation
Are concepts and mechanisms unified across modalities in current AI models, or instead implemented separately for each one? We operationalize this broad question of modality unific...
On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
Diffusion language models (DLMs) promise parallel text generation, but in practice face an unresolved speed-quality trade-off. Exact decoding fills in only one masked position per ...
Rollback: Experience Backtracking in World Models for Policy Improvement
Action-conditioned world models offer a scalable alternative to costly real-world interaction for improving robot policies. However, existing world-model-based methods largely trea...
Rethinking Verification in Agent Harnesses
Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to imp...
Intrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
Animals have a remarkable capacity for autonomy---driven by intrinsic motivation---without external sensory cues or extrinsic objectives, yet the computational mechanisms behind th...
RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions
Scaling vision-language-action (VLA) models is constrained by scarce action-labeled demonstrations and incompatible control spaces across robot embodiments. We present RynnVLA-Late...
DynaFlow: Learning Free-Form Multi-Agent Orchestration
Multi-agent systems often rely on predefined collaboration structures, limiting their ability to adapt to diverse task requirements. We introduce DynaFlow, a framework that integra...
Δτ-Bench: Pushing Agents Toward a Moving Capability
In this paper, we introduce Δτ-Bench, an executable agent benchmark that models the structural evolution of large tool ecosystems. In Δτ-Bench, independently evolving services cont...
AgentProofBench: Benchmarking Reusable Verifiers for Web Agents
Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution. We introduce AgentProofBench, which connects paired tests of a fro...
ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fu...