Evaluating Agents Across Runtime Contracts: When Mismatch Costs Efficiency or Quality
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
The Flow has not summarised this story yet — read it at arXiv AI.
The paper introduces a coroutine-bridge harness that lets a language model emit a Python program to manage tool calls in the CAR-bench evaluation. By decoupling model invocations from tool round-trips, the approach reduces model calls to a median of two per task while maintaining seven agent turns, achieving a median latency of 1.8 s on a Cerebras gpt‑oss‑120b. The harness achieved 60.0 % Pass³ on the official hidden evaluation, outperforming the baseline by 4.5× and matching frontier-model agents on GPT‑5.5, all while keeping the prompt largely cached and minimizing input compute.
arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.
arXiv:2608.22510v1 Announce Type: new Abstract: Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: th...
The paper introduces NP‑Bench, a benchmark and a proactive scheduling planner that coordinates parallel large‑language‑model coding agents. By partitioning work scopes and ordering merges ahead of time, the planner improves clean‑integration rates from 1/9 to 9/9 and eliminates merge conflicts, outperforming both no‑coordination and reactive‑detection baselines. It also demonstrates that cross‑session memory can eliminate repeated mistakes and that routing facts to agents does not improve long‑context accuracy at scale.
The paper discusses the problem of benchmark maintenance debt in evaluating coding agents, where benchmarks become outdated as models improve and infrastructure changes. It introduces a continuous‑validation workflow that incorporates community feedback, automated checks, and human repairs, applied to Terminal‑Bench 2.0. The audit uncovered issues in about 30% of the benchmark, leading to a new version (Terminal‑Bench 2.1) that improved accuracy by over 10 percentage points and altered leaderboard positions, while also highlighting the importance of validating resource budgets alongside task artifacts.
InfraDev is a new benchmark comprising 36 tasks derived from real-world pull requests to Megatron‑LM, vLLM, and verl, designed to test coding agents on infrastructure development for training, inference, and reinforcement learning across many GPUs. Each task requires agents to reimplement multi‑file changes and run correctly, with grading that includes hidden probes and a prompt exposing only the interfaces used. The benchmark reveals that current frontier models resolve only about 39% of tasks, with probes rejecting a third of submissions that pass official tests, and that structural and state errors dominate failures.