News without the noise
Harnesses, orchestration, context engineering
61 articles · page 2 of 2
Ganz et al. tested coding agents that switched between lower-cost, lower-capability models and higher-cost, higher-capability models during long-running tasks. They find a “handoff tax”: giving a stronger model the weaker model’s full trajectory recovers less than half the quality gap between them while adding substantial cost.
27 Aug 2026The authors developed a search framework that iteratively modifies an agent’s surrounding harness using tasks selected according to baseline failure patterns. Across three enterprise benchmarks, evolved harnesses improved full-benchmark performance by 20–35 percentage points, with gains extending to held-out tasks and transferring across GPT and Qwen model families.
27 Aug 2026Chen et al. formulate the choice of reusable skill documents for LLM agents as a budget-constrained optimization problem rather than an independent relevance-ranking task. Their Best Prefix Selection algorithm achieved 0.73 task success on a contamination-controlled BigCodeBench variant, compared with 0.20–0.52 for existing selection methods, while using fewer tokens than the strongest released router.
23 Aug 2026Miyai, Aizawa and Yamasaki propose a method for improving the code and instructions surrounding an LLM agent without changing its model weights. Their approach adaptively evaluates candidate harnesses on tasks where past candidates disagreed, substantially reducing evaluation costs while preserving final performance in the reported experiments.
23 Aug 2026Fisch et al. model AI routing as a search problem in which inspecting each candidate model’s likely value is itself costly. Across multi-LLM routing, retrieval-augmented specialists, and variable reasoning budgets, their centralized policy reportedly preserves the routing quality of exhaustive estimation while invoking expensive estimators much less often.
23 Aug 2026The authors introduce NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework where any Python object can act as an AI agent: methods define available actions, fields store state, docstrings serve as prompts, and type annotations act as contracts. Methods whose body consists only of '...' are completed at runtime by an LLM-driven loop, while normal methods remain deterministic. The framework is demonstrated on SWE-bench Verified, Terminal-Bench 2.0, and ARC-AGI-3, showing that current models use this interface effectively.
23 July 2026Wang et al. revisit the evaluation of automatic harness evolution for LLM agents, comparing it with simple test-time scaling and discovery baselines under matched feedback and inference budgets. They find that harness evolution does not consistently outperform these baselines on Terminal-Bench 2.1 and shows limited generalization to held-out tasks, raising concerns about overfitting and the effectiveness of the approach.
14 July 2026The authors introduce SelfCompact, a scaffold that allows language model agents to dynamically decide when and how to compact their accumulated context. By combining a tool for summarization with a rubric that specifies when to invoke it, SelfCompact matches or exceeds fixed-interval baselines on math and agentic search benchmarks, using 30-70% fewer tokens.
23 June 2026The authors present Sol Video Inference Engine, a training-free framework that uses parallel agent modules to optimize cache, sparse attention, token pruning, quantization, and kernel fusion for a given model-hardware-configuration triplet. Across three models (64B Cosmos3-Super, 22B LTX-2.3, 2B SANA-Video), the full stack achieves over 2x end-to-end acceleration while maintaining near-lossless VBench quality, with minimal human effort.
22 June 2026The authors present Sakana Fugu, a family of orchestrator language models that generate dynamic, query-adaptive agentic scaffolds to harness the specialized capabilities of multiple LLMs. Fugu and Fugu-Ultra achieve state-of-the-art results on six challenging benchmarks, including SWE-Bench Pro, Terminal Bench, and GPQA-Diamond, surpassing any single publicly accessible model.
19 June 2026The authors test four context engineering strategies for GPT-5 agents using Model Context Protocol tools on a 50-task hotel expense benchmark. They find that pruning context to the last five tool call/response pairs and adding automated summarization yields the best results: 91.6% complete itemization, 99.64% amount itemized, with 63% fewer tokens and 60% less runtime than retaining full conversation history.
9 June 2026The authors introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes an AI agent's harness of skills, tools, and workflows using only past task trajectories. By selecting a diverse coreset of challenging tasks, re-solving them in parallel, and using self-validation to pick the best harness update, the method improves pass rate on SWE-Bench Pro from 59% to 78% in a single optimization round.
4 June 2026The authors critique the dominant on-the-fly paradigm for AI agents, which synthesizes plans and executes actions rapidly in response to prompts, arguing it bypasses established software engineering processes like testing and adversarial evaluation. They propose an AI Workflow Store of hardened, reusable workflows to amortize the cost of rigor across users, aiming to improve reliability and security for high-stakes applications.
12 May 2026