TClone introduces low-latency forking of live GUI environments via sibling containers, copy-on-write sharing, and asynchronous checkpointing, achieving 1.9x and 1.5x lower task latency than KVM and CRIU.
Agent alpha: Tree search unifying generation, exploration and evaluation for computer-use agents.arXiv preprint arXiv:2602.02995
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
HPML projects multi-agent update fields onto the closest metric-gradient potential flow via Hodge decomposition, yielding Lyapunov potentials and equilibrium-gap bounds.
VPSD-RL discovers exact and approximate value-preserving Lie-group operators in continuous RL to stabilize learning via transition augmentation and consistency regularization.
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
VisCritic uses visual comparison of pre- and post-action GUI screenshots via a Siamese vision transformer and Action-Aware Critic Head to provide process rewards, improving agent performance on benchmarks.
A 13M-parameter intent-conditioned reward model trained on 398K multi-OS GUI steps scores candidate actions and lifts Agent S3 OSWorld success by 6.9 points without extra LLM calls.
Survey framing LLM agents as model-plus-harness systems, decomposing harness responsibilities, mapping them to tasks, and highlighting open challenges in evaluation, safety, and co-evolution.
citing papers explorer
-
TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents
TClone introduces low-latency forking of live GUI environments via sibling containers, copy-on-write sharing, and asynchronous checkpointing, achieving 1.9x and 1.5x lower task latency than KVM and CRIU.
-
Metric-Gradient Projection for Stable Multi-Agent Policy Learning
HPML projects multi-agent update fields onto the closest metric-gradient potential flow via Hodge decomposition, yielding Lyapunov potentials and equilibrium-gap bounds.
-
Operator-Guided Invariance Learning for Continuous Reinforcement Learning
VPSD-RL discovers exact and approximate value-preserving Lie-group operators in continuous RL to stabilize learning via transition augmentation and consistency regularization.
-
NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
NonZero introduces an interaction score and bandit-formalized proposal rule for local agent deviations in multi-agent MCTS, delivering a sublinear local-regret guarantee and improved sample efficiency on game benchmarks without full joint-action enumeration.
-
VisCritic: Visual State Comparison as Process Reward for GUI Agents
VisCritic uses visual comparison of pre- and post-action GUI screenshots via a Siamese vision transformer and Action-Aware Critic Head to provide process rewards, improving agent performance on benchmarks.
-
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
A 13M-parameter intent-conditioned reward model trained on 398K multi-OS GUI steps scores candidate actions and lifts Agent S3 OSWorld success by 6.9 points without extra LLM calls.
-
From Question Answering to Task Completion: A Survey on Agent System and Harness Design
Survey framing LLM agents as model-plus-harness systems, decomposing harness responsibilities, mapping them to tasks, and highlighting open challenges in evaluation, safety, and co-evolution.