ComtradeBench: An OpenEnv Benchmark for Reliable LLM Tool-Use Under Adversarial Conditions#3378
Open
yonghongzhang-io wants to merge 1 commit intohuggingface:mainfrom
Open
Conversation
ComtradeBench is an OpenEnv-native benchmark that evaluates whether LLM agents can execute multi-step API workflows reliably under adversarial conditions: pagination, duplicates, rate limits, server errors, page drift, totals traps, and adaptive adversaries. Key contributions: - 10 procedurally-generated tasks (T1-T9 + adaptive variant) - 6-dimension scoring with anti-gaming governance gates - 5 LLM evaluations (Kimi K2.5, Claude Sonnet 4.6, GPT-5, Llama 3.3 70B, Qwen2.5-7B) - Full GRPO training pipeline with reproducible rollouts - Latent GRPO bug found and fixed (silent policy/actor desync) Submitted as part of AgentBeats Phase 2 OpenEnv Challenge.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds a new community blog post: ComtradeBench, an OpenEnv-native benchmark for evaluating reliable LLM tool-use under adversarial API conditions.
The post documents the design of a 10-task benchmark, results from 5 frontier and open-source LLMs, a full GRPO training pipeline, and a latent GRPO bug discovery (silent policy/actor desync).
Resources
Author
Member of blog-explorers.
Submitted as part of AgentBeats Phase 2 OpenEnv Challenge.