arXiv subjects

Daniel Thi Graviet

Publications and source records attributed to Daniel Thi Graviet.

3 recordsLinked to original sources

arXiv2026

Returning to Development States: When Full Sandbox Snapshots Help Coding Agents

Coding agents often make useful progress before they fail, but retry-from-scratch discards the machine state created along the way. This makes failure recovery an interesting search problem: if intermediate environment states preserve meaningful progress, restoring and branching from them could outperform repeatedly restarting from the initial state. We implement Go-Explore-style search over full Daytona snapshots and find that higher and more efficient solve rates depend mainly on progress that sits outside the repository, such as databases, services, and other runtime state. Our results suggest that full-snapshot search is most effective when long-horizon coding work spans multiple services whose state cannot be reconstructed from a single diff.

cs.LG↗

arXiv2026

The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning

Coding-agent reinforcement learning treats execution infrastructure as a background implementation detail, despite relying on large numbers of interactive software rollouts. This is a missed opportunity: measuring infrastructure overhead can reveal practical efficiency gains for RL post-training, where small per-rollout savings compound at scale. We present a comparative study of four execution substrates: single containers, hosted sandboxes, Kubernetes-orchestrated containers, and cloud virtual machines. We find up to $110\times$ variation in cold-start latency and a $1.8\times$ spread in projected worker-hours for one million 150-step trajectories. Our results suggest that future coding-agent RL systems should optimize execution substrates as part of the training system itself, not merely as deployment plumbing.

cs.LG↗

arXiv2026

The Capability Frontier: Benchmarks Miss 82% of Model Performance

Existing benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particularly under heterogeneous data distributions: (i) different models get different questions correct according to their specializations, and (ii) given a budget, multiple generations can be sampled and selectively retained. To quantify this gap, we introduce the Capability Frontier: a Pareto frontier over a set of models that characterizes the best achievable performance at each cost level under optimal selection across models and generations (i.e., via an oracle). Our construction corrects for two opposing biases: underestimation from single-model evaluation and overestimation from taking maxima over noisy samples. We study 21 LLMs across 16 widely used benchmarks spanning coding, reasoning, medicine, factuality, instruction following, and agentic tasks, comparing Capability Frontier performance at matched cost to each benchmark's top-performing model. Correcting for single-model evaluation yields a 54% error rate reduction; additionally correcting for single runs yields an 82% improvement, with SOTA accuracy matched at 85% cost reduction. Complementing these empirical results, we use controlled probabilistic simulations to show that higher query topic entropy produces a near-monotonic increase in the performance gap between oracle routing and the best single model. Our findings suggest collective LLM capabilities are substantially underestimated, with implications for evaluation and deployment in data-heterogeneous, multi-domain settings.

cs.AI↗