Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.
hub
Agentoccam: A sim- ple yet strong baseline for llm-based web agents
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
abstract
Autonomy via agents using large language models (LLMs) for personalized, standardized tasks boosts human efficiency. Automating web tasks (like booking hotels within a budget) is increasingly sought after. Fulfilling practical needs, the web agent also serves as an important proof-of-concept example for various agent grounding scenarios, with its success promising advancements in many future applications. Prior research often handcrafts web agent strategies (e.g., prompting templates, multi-agent systems, search methods, etc.) and the corresponding in-context examples, which may not generalize well across all real-world scenarios. On the other hand, there has been limited study on the misalignment between a web agent's observation/action representation and the pre-training data of the LLM it's based on. This discrepancy is especially notable when LLMs are primarily trained for language completion rather than tasks involving embodied navigation actions and symbolic web elements. Our study enhances an LLM-based web agent by simply refining its observation and action space to better align with the LLM's capabilities. This approach enables our base agent to significantly outperform previous methods on a wide variety of web tasks. Specifically, on WebArena, a benchmark featuring general-purpose web interaction tasks, our agent AgentOccam surpasses the previous state-of-the-art and concurrent work by 9.8 (+29.4%) and 5.9 (+15.8%) absolute points respectively, and boosts the success rate by 26.6 points (+161%) over similar plain web agents with its observation and action space alignment. We achieve this without using in-context examples, new agent roles, online feedback or search strategies. AgentOccam's simple design highlights LLMs' impressive zero-shot performance on web tasks, and underlines the critical role of carefully tuning observation and action spaces for LLM-based agents.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
Skim profiles website patterns offline to enable fast-path speculative execution for web agents, cutting median cost by 1.9x and latency by 33.4% with no accuracy loss on benchmarks.
SkillMigrator reduces LLM-action counts by 8-10% on WebArena and Mind2Web by transferring web skills via layout-matched transferable interaction patterns.
DRIVE disentangles reasoning and interaction skills for web agents via dual-level modeling and scene-aware coordination, reaching 52.8% success on WebArena tasks.
WebFactory is a fully automated RL pipeline that compresses LLM-encoded internet knowledge into grounded web agents, achieving performance comparable to human-annotated training but using synthetic data from only 10 websites.
Plan-and-Act trains a dedicated Planner on synthetic plan-annotated trajectories to generate high-level plans that an Executor follows, reaching 57.58% success on WebArena-Lite and 81.36% on WebVoyager.
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.
BaRA improves valid link discovery and multimodal artifact extraction in budget-constrained web data collection via BFS liveness checks, rule-based validation, and self-reflection.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
citing papers explorer
-
Prismata: Confining Cross-Site Prompt Injection in Web Agents
Prismata cuts web-agent prompt-injection attack success from 85.5% to 0.7% via Biba-inspired DOM trust labeling and mechanical least-privilege confinement without site annotations.
-
Skim: Speculative Execution for Fast and Efficient Web Agents
Skim profiles website patterns offline to enable fast-path speculative execution for web agents, cutting median cost by 1.9x and latency by 33.4% with no accuracy loss on benchmarks.
-
Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
SkillMigrator reduces LLM-action counts by 8-10% on WebArena and Mind2Web by transferring web skills via layout-matched transferable interaction patterns.
-
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
DRIVE disentangles reasoning and interaction skills for web agents via dual-level modeling and scene-aware coordination, reaching 52.8% success on WebArena tasks.
-
WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
WebFactory is a fully automated RL pipeline that compresses LLM-encoded internet knowledge into grounded web agents, achieving performance comparable to human-annotated training but using synthetic data from only 10 websites.
-
Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks
Plan-and-Act trains a dedicated Planner on synthetic plan-annotated trajectories to generate high-level plans that an Executor follows, reaching 57.58% success on WebArena-Lite and 81.36% on WebVoyager.
-
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.
-
BaRA: Budget-constrained and Reliable Web Data Collection Agent
BaRA improves valid link discovery and multimodal artifact extraction in budget-constrained web data collection via BFS liveness checks, rule-based validation, and self-reflection.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
-
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.