General Agent Evaluation

Elron Bandel, Asaf Yehudai, Lilach Eden, Yehoshua Sagron, Yotam Perlitz, Elad Venezian, Natalia Razinkov, Natan Ergas, Shlomit Shachor Ifergan, Segev Shlomov, Michal Jacovi, Leshem Choshen, Liat Ein-Dor, Yoav Katz, Michal Shmueli-Scheuer

Keywords: general-purpose agents, agent evaluation, evaluation harness, benchmark, leaderboard, failure modes, error analysis, behavioral taxonomy, LLM agents, agentic safety

TL;DR: First systematic study of general agents across 5 architectures × 5 LLMs × 6 benchmarks, with a behavioral failure taxonomy revealing architecture-distinctive error signatures.

Abstract: General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse unfamiliar environments. This is the first systematic study, comparing tool-calling, MCP, code-generation, and CLI agents on the same benchmarks with the same models. Two gaps blocked such a study: existing harnesses require per-benchmark wiring or fixed protocol classes (web for BrowserGym, CLI for Harbor), and benchmarks themselves expect human-authored prompts, context, and integration glue. To enable this study, we contribute (1) a unifying protocol that bridges existing benchmark and agent protocols; (2) an evaluation harness that surfaces any benchmark to any general-purpose agent and backbone model; and (3) the first Open General Agent Leaderboard of agent configurations, a full factorial over 5 agent architectures × 5 backbone LLMs (three closed-source, two open-weight) × 6 benchmarks spanning software engineering, customer service, deep research, and personal assistance. We find that (i) general agents adapt to every tested domain without per-domain customization; (ii) agent architecture choice swings results by up to 12pp within a single model, yet backbone model choice dominates overall performance; (iii) failure-mode analysis reveals architecture-distinctive error signatures invisible to aggregate scoring; (iv) open-weight models tested exhibit "generality sinks" absent from frontier closed-source models: they consistently collapse on specific agent architectures or benchmarks.

Track: Regular Paper (9 pages)

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 167