Category
20,515 papers
This work builds LinguaGuardBench from the 1,220 labelled steps of TS-Bench AgentDojo-Traj, translating only the user instruction into German, French, Turkish, Swahili and Amharic, and keeps every tool call, observation and label byte-identical, so any change in a verdict is attributable to language alone.
On-policy distillation consolidates specialist models into one student at the price of rollouts, teacher passes and gradient steps for every teacher. We show that the consolidation does not need training: with forward passes only, the capabilities of separately tuned specialists can be aggregated into one model that is...
Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, scripts, and system state. However, native GUI/code coordination cannot be obtained by prompt-level tool composition. In our preliminary experiments, naively addi...
Across eight multimodal benchmarks, SCOPED consistently outperforms the backbone and mixed-capability RL, demonstrating the effectiveness of skill-decoupled on-policy expert distillation for integrating independently acquired capabilities.
Reach audiences
Advertise in front of researchers, engineers, and readers.
TRACE, a topology-aware, prediction-adaptive objective that uses a target skeleton to define required local connections, and introduces a topology-aware skeleton carrier that preserves both foreground and class-specific topology, enabling reliable definition of these connections.
Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy for memory quality. We show this evaluation paradigm is incomplete: it conflates memory correctness with retrieval and generation quality, producing both false positives w...
Across a diverse set of domains, it is demonstrated that imperfect competition successfully sustains necessary agent profit margins while maintaining high task success rates at low costs.
Large language models (LLMs) are increasingly used in computational social science to assign scalar scores to social and psychological constructs. However, studies use different rating scales, and whether their scores remain comparable across scale designs is understudied. To address this gap, we define and systematica...
Current humanoid dexterous manipulation remains largely confined to end-effectors and simple grasps, falling short of humans'ability to engage the entire body by bracing and sliding bulky objects against the arms and torso. We introduce Whole-Body Dexterity (WBD), a general framework that uses the robot's body and appe...
This work introduces a motion- and gravity-aware framework under the Learning Using Privileged Information (LUPI) paradigm, and suggests that LUPI offers a practical way to inject motion and physical priors into feed-forward 3D reconstruction without increasing test-time complexity.
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However, agentic techniques such as context compaction and subagent forking may produce trajectories spanning multiple sessions, creating a mismatch between th...
Test-time context optimization adapts frozen language models through textual feedback, but ordinary conditional generation provides no separate control over how strongly to reinforce the distributional changes induced by a context update. We introduce EMO, a training-free framework inspired by expectation--maximization...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
