PreAct compiles successful agent executions into verifiable state-machine programs for 8.5-13x faster replay on repeated tasks, with an independent evaluator check before storing each program.
hub
Os-copilot: Towards generalist computer agents with self-improvement
25 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
25
Pith papers citing it
5
external citations · external index
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
Proposes COM-as-Action paradigm for deterministic software manipulation, introduces ComCADBench benchmark and ComActor agent that achieves SOTA performance over GUI baselines.
AndroidDaily supplies 350 verifiable tasks on 94 closed-source Android apps evaluated by GRADE (87.37% human agreement), with the strongest model achieving 62% success.
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps
FORGE uses a reasoning-action-observation loop and Dynamic Forest of Agents to perform scalable LLM-based binary analysis, finding 1,274 vulnerabilities across 591 of 3,457 real-world firmware binaries at 72.3% precision and broader coverage than prior methods.
AndroidWorld is a dynamic, reproducible Android benchmark that generates unlimited natural-language tasks for autonomous agents and shows current agents succeed on only 30.6 percent of them.
COMFYCLAW introduces skill evolution via graph editing, automatic reversion, VLM verification, and distillation of runs into reusable Agent Skills, achieving higher average scores than a verifier-only baseline across benchmarks.
OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compete with much larger ones.
unix-ctf procedurally generates 656 Unix CTF tasks across 155 techniques; fine-tuning Qwen3-8B on them raises solve rate from 11.6% to 43.6% on a 15-skill holdout and yields +33 pp in Forensics on InterCode-CTF.
Controlled experiments show structured reasoning traces and higher-density math-domain samples improve mathematical reasoning more than pure executable code, with internal routing patterns reflecting these data effects.
SkillDroid compiles LLM-guided GUI trajectories into parameterized skill templates and replays them via a matching cascade, reaching 85.3% success rate with 49% fewer LLM calls and improving from 87% to 91% over 150 rounds while the stateless baseline drops to 44%.
A kernel-level single-forward-pass logit probe classifies agent actions as safe or dangerous with zero learned parameters and matches or beats Llama Guard 3 on external safety benchmarks.
AgentProg reframes interaction history as a program with variables and control flow, plus a belief state for partial observability, achieving SOTA success rates on long-horizon GUI benchmarks while baselines degrade.
A benchmark with 886 real-world field work tasks across factories, warehouses, and retail, plus an evaluation method for multimodal AI agents.
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
SeeClick improves visual GUI agents via GUI grounding pre-training on automatically curated data and introduces the ScreenSpot benchmark, with results indicating that stronger grounding boosts downstream task performance.
Personal agents require edge deployment to preserve high-fidelity local context and zero-latency loops, as claimed through three structural shifts away from cloud-centric designs.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
VisionClaw couples continuous egocentric vision on smart glasses with speech-driven AI agents to enable hands-free real-world tasks, with lab and field studies showing faster completion and a shift toward opportunistic delegation.
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
InfantAgent-Next integrates tool-based and vision agents in a modular architecture and reports 7.27% accuracy on OSWorld, exceeding Claude-Computer-Use while also testing on GAIA and SWE-Bench.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
PreAct compiles successful agent executions into verifiable state-machine programs for 8.5-13x faster replay on repeated tasks, with an independent evaluator check before storing each program.
-
ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm
Proposes COM-as-Action paradigm for deterministic software manipulation, introduces ComCADBench benchmark and ComActor agent that achieves SOTA performance over GUI baselines.
-
AndroidDaily: A Verifiable Benchmark for Mobile GUI Agents on Real-World Closed-Source Applications
AndroidDaily supplies 350 verifiable tasks on 94 closed-source Android apps evaluated by GRADE (87.37% human agreement), with the strongest model achieving 62% success.
-
ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis
ScaleWoB generates 100+ synthetic interactive GUI environments and 1000+ verifiable tasks as web pages, releasing a 120-task mobile benchmark where state-of-the-art agents achieve 27.92% success (17.82% on long-horizon tasks) versus 92.08% for humans, with synthetic results generalizing to real apps
-
Feedback-Driven Execution for LLM-Based Binary Analysis
FORGE uses a reasoning-action-observation loop and Dynamic Forest of Agents to perform scalable LLM-based binary analysis, finding 1,274 vulnerabilities across 591 of 3,457 real-world firmware binaries at 72.3% precision and broader coverage than prior methods.
-
AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
AndroidWorld is a dynamic, reproducible Android benchmark that generates unlimited natural-language tasks for autonomous agents and shows current agents succeed on only 30.6 percent of them.
-
COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows
COMFYCLAW introduces skill evolution via graph editing, automatic reversion, VLM verification, and distillation of runs into reusable Agent Skills, achieving higher average scores than a verifier-only baseline across benchmarks.
-
OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation
OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compete with much larger ones.
-
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning
unix-ctf procedurally generates 656 Unix CTF tasks across 155 techniques; fine-tuning Qwen3-8B on them raises solve rate from 11.6% to 43.6% on a 15-skill holdout and yields +33 pp in Forensics on InterCode-CTF.
-
What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code
Controlled experiments show structured reasoning traces and higher-density math-domain samples improve mathematical reasoning more than pure executable code, with internal routing patterns reflecting these data effects.
-
SkillDroid: Compile Once, Reuse Forever
SkillDroid compiles LLM-guided GUI trajectories into parameterized skill templates and replays them via a matching cascade, reaching 85.3% success rate with 49% fewer LLM calls and improving from 87% to 91% over 150 rounds while the stateless baseline drops to 44%.
-
ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems
A kernel-level single-forward-pass logit probe classifies agent actions as safe or dangerous with zero learned parameters and matches or beats Llama Guard 3 on external safety benchmarks.
-
AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management
AgentProg reframes interaction history as a program with variables and control flow, plus a belief state for partial observability, achieving SOTA success rates on long-horizon GUI benchmarks while baselines degrade.
-
FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks
A benchmark with 886 real-world field work tasks across factories, warehouses, and retail, plus an evaluation method for multimodal AI agents.
-
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
-
SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
SeeClick improves visual GUI agents via GUI grounding pre-training on automatically curated data and introduces the ScreenSpot benchmark, with results indicating that stronger grounding boosts downstream task performance.
-
Beyond Scaling: Agents Are Heading to the Edge
Personal agents require edge deployment to preserve high-fidelity local context and zero-latency loops, as claimed through three structural shifts away from cloud-centric designs.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
-
VisionClaw: Always-On AI Agents through Smart Glasses
VisionClaw couples continuous egocentric vision on smart glasses with speech-driven AI agents to enable hands-free real-world tasks, with lab and field studies showing faster completion and a shift toward opportunistic delegation.
-
A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions
A survey of 87 agents for computer use and 33 datasets that introduces a three-dimensional taxonomy across domain, interaction, and agent perspectives and identifies six research gaps.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
-
InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
InfantAgent-Next integrates tool-based and vision agents in a modular architecture and reports 7.27% accuracy on OSWorld, exceeding Claude-Computer-Use while also testing on GAIA and SWE-Bench.
-
Large Language Model-Brained GUI Agents: A Survey
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
- FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents