Spine is a new interface and runtime that aligns a language model’s context with the nesting and completion of subtasks in long‑horizon coding problems. By letting agents declare explicit subtask boundaries through work scopes, Spine records interactions in a persistent SpineTree and compiles only the necessary unfinished subtask history into the model’s prompt, replacing completed subtasks with their results while reusing prefix‑cache. Integrated into Codex and Pi, SpineCodex and the reusable Pi package achieve significant performance gains—improving SWE‑Milestone and ProgramBench scores and reducing costs—without the overhead of recursive subagent delegation.
arXiv:2611.07461v1 Announce Type: cross Abstract: How can an agent handle a real-world task end to end? Frontier models with their own harnesses still fall short on real-world benchmarks: on Terminal...
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...
Terminal-Universe is a framework that transforms large collections of terminal‑based agent trajectories into reusable, executable environments. By replaying recorded file operations and completing missing files, it reconstructs the original workspace and task, then synthesizes new tasks and multi‑round interactions. The resulting 37.3k task‑sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑based benchmarks.
arXiv:2608. 15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps.
arXiv:2606. 30573v1 Announce Type: new Abstract: We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks.
arXiv:2603. 21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github.
Terminal-Universe is a framework that converts large collections of terminal-based agent trajectories into reusable, executable environments. By replaying recorded file operations and filling missing files with a completion agent, it reconstructs the original workspace and generates new tasks, scaling them in breadth (cross-workspace queries) and depth (multi-round interactions). The resulting 37.3k task-sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑centric benchmarks.
TaReD introduces a tool-aware recursive decomposition strategy for long‑horizon tasks, organizing tools into a hierarchy of capabilities and allowing agents to discover and use tools on demand. By aligning subtask decomposition with the required capabilities, the method reduces the unreliability of long execution chains and improves task success rates. Experiments on complex real‑world tasks demonstrate up to a 40‑percentage‑point improvement over baseline approaches.
arXiv:2608. 16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages.
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...
The paper introduces Harness Primitives—reusable agent harness mechanisms mined from failed task trajectories—and a framework called STITCH that selects and composes these primitives into task‑specific harnesses at test time. This approach avoids generating or debugging harness code for each task, achieving up to 12‑point gains in task success over fixed harness baselines and outperforming human‑designed harnesses like Codex CLI. STITCH also demonstrates minimal test‑time overhead (2.7%) and scales efficiently with the size of the primitive library.
arXiv:2608.27969v2 Announce Type: replace Abstract: Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and...