11 papers · 1 filter
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
Chong Zeng, Ziqian Zhong, Kexun Zhang +5
Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. Verifiers can be attacked into a…
AuraForge: Scaling Security Supervision for Training Coding Agents
Danqing Wang, Songwen Zhao, Harsh Sharma +4
Coding agents are now proficient enough to generate complex software applications from a single prompt. As their capabilities have grown, human oversight has increasingly shifted f…
What Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus
Edward Lue Chee Lip, Boden Moraski, Tim Knappe +4
Frontier benchmarks need tasks that current models cannot solve. But a task that no model solves is not automatically a hard task. The same zero pass rate can come from a real capa…
Hack-Verifiable Terminal Bench: Evaluating Reward Hacking in Terminal Tasks
Amit Roth, Ivan Bercovich, Yonathan Efroni
As agents grow more capable and autonomous, their tendency to reward hack, satisfying a task's checks while violating its intent, becomes an increasingly important failure mode. Me…
Good Benchmarks
Ivan Bercovich
Good tasks are correct, solvable, verifiable, well-specified, and hard for interesting reasons. The best tasks describe a real problem an experienced practitioner would recognize,…
Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty
Antonis Antoniades, Deepak Nathani, Ritam Saha +6
Autonomous AI Research promises to accelerate the scientific progress of machine learning. To realise this goal, current Large Language Model (LLM)-based agents need to go beyond j…
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
Ziqian Zhong, Ivgeni Segal, Ivan Bercovich +3
Agent benchmarks score submissions with outcome verifiers that are typically hand-written and brittle, leaving them open to reward hacking. We audit 1,968 tasks across five termina…
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
Rishi Desai, Jesse Hu, Joan Cabezas +23
AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent b…
What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design
Ivan Bercovich
Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation enviro…
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
Ivan Bercovich, Ivgeni Segal, Kexun Zhang +3
We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set inclu…
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…