The paper investigates the use of test‑time search, specifically Monte Carlo tree search (MCTS), to improve agent performance in terminal‑based computer‑use environments. It finds that conventional MCTS does not significantly boost task success due to limited critic information and poor intermediate state evaluation. The authors propose a new strategy called Probe‑and‑Resume, where a critic is invoked only when the agent believes it has finished, and it is given read, write, and execute access to a forked copy of the environment to probe hidden state. This approach raises success rates by 8.4 percentage points over standard MCTS and nearly matches a more expensive Codex CLI agent.
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obs...
arXiv:2610.20334v1 Announce Type: cross Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-pat...
arXiv:2610.14146v1 Announce Type: new Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its fi...
arXiv:2607. 08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks.
The paper introduces environment‑probing curation, a deployment‑compatible method that equips asynchronous curator agents with read‑only world tools to verify, scope, and refresh candidate memories without retraining models. In a GitHub Copilot‑based harness, this approach improves pass rates on CLBench from 39% to 73%, boosts reward metrics, and reduces both query counts and task‑agent costs. Across six APEX management‑consulting tasks, the method consistently outperforms baselines, yielding higher rewards and fewer tool calls while maintaining a compact task‑time interface.
Opera is a verbal critic framework designed for long‑horizon coding agents, treating each correction as a persistent note that is followed until the problem is resolved. It uses periodic and event‑driven triggers to diagnose issues, audits feedback against visible evidence, and tracks subsequent actions to distinguish compliance from true resolution. In tests, Opera improves the resolve rate of non‑critic agents by up to 12.4, 15.0, and 8.9 percentage points on three benchmarks and provides on‑policy training data that boosts a model’s performance without requiring a critic at inference time.
Mid‑Harness proposes a test‑time compute strategy that samples and verifies candidate actions before execution, keeping the underlying generator and harness unchanged. Experiments show that with a strong verifier, sampling more actions significantly boosts success rates—e.g., a GPT‑5.6 verifier raises Pass@1 from 50.00 % to 68.03 % on TerminalBench‑Lite using eight samples. The approach also improves performance across various models, benchmarks, and harnesses, demonstrating that action scaling is a promising target for enhancing terminal agent reliability.
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
arXiv:2606. 17929v1 Announce Type: new Abstract: Computer-using agents drive real software through the screen -- clicking and typing -- but they solve every task from scratch: asked to repeat a task, an agent re-reads the screen, re-reasons every tap, and pays the full cost again.
arXiv:2606. 11662v1 Announce Type: new Abstract: Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis.
The study compares an equal‑budget Monte Carlo Tree Search (MCTS) scheduler with a randomized‑restart list scheduler for directed‑acyclic‑graph (DAG) workflows, ensuring all methods receive the same number of candidate schedules. Across 768 validated schedules, MCTS performed 2.88% worse than the restarts at a budget of 2048 evaluations, with the deficit persisting even when the selection rule was changed to textbook UCT. The results, limited to synthetic domains with 8–32 tasks and up to 2048 evaluations, suggest that simpler restart strategies can outperform MCTS in certain workflow structures.
The paper introduces ReTRAIL, a framework that allows long‑horizon agents to rewind the environment to earlier states while preserving forward progress in knowledge. By training a shared policy with State‑Anchored GRPO and a branch‑advancement reward, ReTRAIL enables agents to recover from unproductive states and reuse insights from abandoned exploration. Experiments on MineSweeper, Sokoban, ALFWorld, and ScienceWorld show that this combined rewinding and experience‑reuse strategy outperforms simple rewind primitives and improves long‑horizon task solving.