Pith. sign in

REVIEW 8 cited by

Towards Enterprise-Ready Computer Using Generalist Agent

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.01861 v3 pith:METG6ECD submitted 2025-02-24 cs.DC cs.AIcs.MA

Towards Enterprise-Ready Computer Using Generalist Agent

classification cs.DC cs.AIcs.MA
keywords agentagenticcomputerenterpriseenterprise-readygeneralistperformancerapid
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper presents our ongoing work toward developing an enterprise-ready Computer Using Generalist Agent (CUGA) system. Our research highlights the evolutionary nature of building agentic systems suitable for enterprise environments. By integrating state-of-the-art agentic AI techniques with a systematic approach to iterative evaluation, analysis, and refinement, we have achieved rapid and cost-effective performance gains, notably reaching a new state-of-the-art performance on the WebArena and AppWorld benchmarks. We detail our development roadmap, the methodology and tools that facilitated rapid learning from failures and continuous system refinement, and discuss key lessons learned and future challenges for enterprise adoption.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Prismata: Confining Cross-Site Prompt Injection in Web Agents

    cs.CR 2026-07 conditional novelty 7.5

    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.

  2. X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention

    cs.AI 2026-05 unverdicted novelty 7.0

    X-SYNTH synthesizes enterprise context from human behavioral attention traces modeled as Digital Twin Signatures using seven per-individual attention filters, raising true lead rate from 9.5% to 61.9% on a sales ident...

  3. X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Digital Human Attention

    cs.AI 2026-05 unverdicted novelty 7.0

    X-SYNTH synthesizes enterprise context from digital human attention using Digital Twin Signatures and seven attention filters, raising true lead rate from 9.5% to 61.9% while cutting false lead rate to 18.8%.

  4. Learning and Reusing Policy Decompositions for Hierarchical Generalized Planning with LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    HCL-GP learns parameterized policies and reuses extracted components to achieve 98% accuracy on AppWorld benchmark tasks for LLM agents, outperforming static synthesis by 15.8 points on challenges.

  5. Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web Agents

    cs.CL 2026-05 unverdicted novelty 5.0

    Empirical evaluation of four natural language plan representations in a static planner-executor framework shows that plan formulation and the underlying LLM both affect LLM web-agent robustness and task success on har...

  6. Governance by Construction for Generalist Agents

    cs.AI 2026-05 unverdicted novelty 5.0

    CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.

  7. Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis

    cs.AI 2026-04 unverdicted novelty 5.0

    Agent Mentor analyzes semantic trajectories in agent logs to identify undesired behaviors and derives corrective prompt instructions, yielding measurable accuracy gains on benchmark tasks across three agent setups.

  8. Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents

    cs.AI 2026-07 conditional novelty 4.0

    A narrative synthesis of 27 agent evaluation papers identifies six recurring failure clusters and finds that agent failures compound non-linearly with task length, sub-skills do not compose into end-to-end success, an...