arXiv:2610.08452v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring...
The paper introduces Strategy Accumulation and Guided Execution (SAGE), a two-stage framework that makes automated fine-tuning of large language models cumulative. In the first stage, a multi-agent pipeline uses Monte Carlo Tree Search to explore training strategies while a Distillation Agent records task-specific insights and cross-task confidence scores into a structured repository. In the second stage, SAGE retrieves relevant experience from this repository to guide training on new tasks, achieving a 12.4‑percentage‑point improvement over a baseline pipeline without accumulated experience on nine unseen tasks.
arXiv:2607. 21324v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents.
arXiv:2610.16998v1 Announce Type: new Abstract: Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-sourc...
arXiv:2607. 26722v1 Announce Type: cross Abstract: Harness plays a critical role in large language model agent performance, and building a high-performing harness requires substantial expert effort.
arXiv:2602.16805v2 Announce Type: replace Abstract: Code evolution is a family of techniques that rely on large language models to search through possible computer programs by evolving existing code....
arXiv:2610.28568v1 Announce Type: new Abstract: Generative retrieval (GR) casts search and recommendation as autoregressive generation of discrete semantic identifiers (SIDs). SID design largely dete...
OpenResearcher is a fully open, reproducible pipeline for generating long‑horizon deep research trajectories that interleave search, evidence aggregation, and multi‑step reasoning. It decouples corpus bootstrapping from trajectory synthesis and runs the search‑and‑browse loop offline using three browser primitives over a 15M‑document corpus. Using GPT‑OSS‑120B as a teacher, the pipeline produced over 97K trajectories, enabling a 30B‑A3B model to achieve 54.8% accuracy on BrowseComp‑Plus and providing insights into pipeline design through controlled analysis.
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.
arXiv:2607. 12227v1 Announce Type: new Abstract: We revisit the evaluation of automatic harness evolution for LLM agents.
arXiv:2602. 12187v2 Announce Type: replace-cross Abstract: Search-Augmented Generative Engines (SAGE) have emerged as a new paradigm for information access, bridging web-scale retrieval with generative capabilities to deliver synthesized answers.
arXiv:2607. 06764v1 Announce Type: new Abstract: Recent progress on ARC-AGI-1 from disclosed architectures has come broadly from two regimes: heavy test-time compute over frontier models (evolutionary search, exhaustive sampling, extended chain-of-thought), or benchmark-specific training in which small models are fine-tuned on ARC data, often with task-specialized architectures.