DUDE framework reduces web agents' susceptibility to deceptive UIs by 53.8% on a new 1,407-scenario benchmark while preserving task performance.
hub Canonical reference
arXiv preprint arXiv:2408.07199 , year=
Canonical reference. 100% of citing Pith papers cite this work as background.
16
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
WORC improves multi-agent LLM reasoning to 82.2% average accuracy by predicting and compensating for the weakest agent via targeted extra sampling rather than uniform reinforcement.
RL expands the capability boundary of LLM agents on compositional tool-use tasks, shown by non-converging pass curves at large k with increasing T, while SFT regresses it and the effect is absent on simpler tasks.
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
GEAR adaptively reweights GRPO advantages in LLM RL by using divergence spikes from self-distillation to define semantic segments and modulate local credit.
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
DynaWeb introduces a model-based RL framework that trains web agents via imagined rollouts in a learned web world model interleaved with real expert trajectories, yielding consistent gains on WebArena and WebVoyager benchmarks.
Mobile-R1 introduces a hierarchical three-stage curriculum that combines format alignment, verifiable action feedback, and multi-turn environment training to improve exploration and self-correction in VLM-based mobile agents, plus a new Chinese GUI dataset and benchmark.
StraTA improves LLM agent success rates to 93.1% on ALFWorld and 84.2% on WebShop by sampling a compact initial strategy and training it jointly with action execution via hierarchical GRPO-style rollouts.
Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a future roadmap.
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.
Empirical study finds background semantics, random pruning, and recency-based allocation improve token efficiency for GUI visual agents.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
citing papers explorer
-
Don't Click That: Teaching Web Agents to Resist Deceptive Interfaces
DUDE framework reduces web agents' susceptibility to deceptive UIs by 53.8% on a new 1,407-scenario benchmark while preserving task performance.
-
Weak-Link Optimization for Multi-Agent Reasoning and Collaboration
WORC improves multi-agent LLM reasoning to 82.2% average accuracy by predicting and compensating for the weakest agent via targeted extra sampling rather than uniform reinforcement.
-
Does RL Expand the Capability Boundary of LLM Agents? A PASS@(k,T) Analysis
RL expands the capability boundary of LLM agents on compositional tool-use tasks, shown by non-converging pass curves at large k with increasing T, while SFT regresses it and the effect is absent on simpler tasks.
-
Group-in-Group Policy Optimization for LLM Agent Training
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
-
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
GEAR adaptively reweights GRPO advantages in LLM RL by using divergence spikes from self-distillation to define semantic segments and modulate local credit.
-
QuantClaw: Precision Where It Matters for OpenClaw
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
-
DynaWeb: Model-Based Reinforcement Learning of Web Agents
DynaWeb introduces a model-based RL framework that trains web agents via imagined rollouts in a learned web world model interleaved with real expert trajectories, yielding consistent gains on WebArena and WebVoyager benchmarks.
-
Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training
Mobile-R1 introduces a hierarchical three-stage curriculum that combines format alignment, verifiable action feedback, and multi-turn environment training to improve exploration and self-correction in VLM-based mobile agents, plus a new Chinese GUI dataset and benchmark.
-
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
StraTA improves LLM agent success rates to 93.1% on ALFWorld and 84.2% on WebShop by sampling a compact initial strategy and training it jointly with action execution via hierarchical GRPO-style rollouts.
-
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
Skill1 trains a single RL policy to co-evolve skill selection, utilization, and distillation in language model agents from one task-outcome reward, using low-frequency trends to credit selection and high-frequency variation to credit distillation, outperforming baselines on ALFWorld and WebShop.
-
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a future roadmap.
-
RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
RoboAgent chains basic vision-language capabilities inside a single VLM via a scheduler and trains it in three stages (behavior cloning, DAgger, RL) to improve embodied task planning.
-
Rethinking Token Pruning for Historical Screenshots in GUI Visual Agents: Semantic, Spatial, and Temporal Perspectives
Empirical study finds background semantics, random pruning, and recency-based allocation improve token efficiency for GUI visual agents.
-
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.