← All threads

Agent Harness Optimization

Techniques for optimizing the code, instructions, and training frameworks surrounding LLM agents to improve performance and reduce cost without changing model weights.

61 papers · 4 months

Where this stands

The written synthesis of this thread is for subscribers. Subscribe.

Results across this thread

1 reported result from the papers in this thread.

PaperBenchmarkMetricResultConditionsCode

The table is for subscribers. Subscribe to see every reported number side by side.

How this thread developed

  1. May 2026 · Columbia University, Google

    Proposing a workflow store to harden AI agents against failure

    Proposes a workflow store as an alternative to on-the-fly planning to harden agents against failure.

  2. June 2026 · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Tongyi Lab , Alibaba Group

    Evolutionary training harness co-evolves with LLM policies for RL

    Proposes co-evolution of training harness and LLM policies, treating the harness as an evolvable component.

  3. June 2026 · City University of Hong Kong, Microsoft Research Asia

    Self-supervised method improves agent harnesses using past trajectories

    Introduces a self-supervised method to optimize agent harnesses from past trajectories.

  4. June 2026 · Shanghai Innovation Institution, Huawei Technologies Ltd.

    Conversational image editing agent learns interpretable tool use

    Shows how an agent can be trained to use parameterized tools interpretably via a multitask pipeline.

  5. June 2026 · Stanford University

    Decentralized agents with shared context outperform centralized orchestration

    Decentralized multi-agent framework with shared context and task queue outperforms central orchestration.

  6. June 2026 · TokenRhythm Technologies, Infinigence AI

    New benchmark standardizes evaluation of coding agent harnesses

    Benchmark and adapter protocol for evaluating coding agent harnesses, revealing adapter design impact.

  7. June 2026

    Latent communication across different LLMs matches or beats text-based transfer at lower compute.

    Latent communication via KV-cache alignment reduces compute compared to text-based transfer between heterogeneous LLMs.

  8. June 2026 · Sakana AI

    Orchestrator models dynamically combine specialized LLMs into collective intelligence

    Orchestrator models generate dynamic, query-adaptive agentic scaffolds to combine specialized LLMs.

  9. June 2026 · NVIDIA Research

    Agent framework auto-tunes video diffusion for 2x speedup

    Training-free framework using parallel agent modules to auto-tune video diffusion (cache, sparse attention, quantization, etc.).

  10. July 2026 · University of Pennsylvania, Nvidia

    Skill evolution improves agent performance in image generation workflows

    Skill evolution via typed graph editing in an image generation harness.

  11. July 2026 · Allen Institute for AI, University of Washington

    Re-evaluation shows harness evolution for agents may not outperform simple test-time scaling

    Re-evaluation showing harness evolution may not outperform simple test-time scaling.

  12. 1 further paper

    July 2026 · NVIDIA

    Python objects become AI agents in new NVIDIA framework

    Introduces a model-agnostic Python framework where any Python object can act as an AI agent, simplifying harness construction.

  13. July 2026 · Columbia University, Dartmouth College

    New framework lets you train AI agents inside the same harness systems they use at inference

    Framework for training agents inside the same harness used at inference.

  14. Aug 2026 · Google DeepMind

    Cost-aware model routing matches exhaustive estimation with fewer expensive checks

    Models AI routing as search with inspection costs, achieving cost-aware routing across multiple LLM setups.

  15. Aug 2026 · The University of Tokyo

    Adaptive task selection cuts the cost of optimizing LLM agent harnesses

    Adaptive task selection for optimizing agent harnesses.

  16. 1 further paper

    Aug 2026 · ServiceNow, Mila

    Evolved agent harnesses lift enterprise performance without retraining models

    Presents an evolutionary search framework for improving agent harnesses, enhancing enterprise performance without model retraining.

  17. Aug 2026 · AWS

    Switching Models Mid-Task Imposes a Cost and Quality Penalty

    Quantifies the 'handoff tax' in mid-task model switching, informing harness design decisions about model selection.

  18. Aug 2026 · National University of Singapore, TCG CREST

    Bounded citation-graph search improves recall while cutting scholarly search costs

    Introduces a bounded citation-graph search method that reduces agent search costs while improving recall.

  19. Aug 2026 · KAIST

    Coding agents extend LLM serving simulators with greater fidelity and speed

    Simthesizer uses a coding agent to modify a shared simulator, improving harness efficiency for LLM serving workflows.

  20. Aug 2026

    Good tool plans can still fail under resource constraints

    Introduces PeakBench, a benchmark for evaluating tool plans under resource constraints, adding a new dimension to harness optimization.

    released code

  21. 30 further papers

    Sept 2026 · UMass Amherst, Zoom Video Communications

    Coding-agent harness choices should match model skill and context budget

    Shows that harness choices (planning, action space, context management) must match model skill and context budget, guiding harness optimization.

  22. 1 further paper

    Sept 2026 · The Chinese University of Hong Kong, University of Edinburgh

    Task-specific plans and terminal checks create different value for LLM agents

    Comparing task-specific plans against shuffled text reveals how meaningful planning signals add value, informing instruction design in agent harnesses.

  23. Sept 2026

    Voice-agent models diverge most beyond choosing the correct tool

    The benchmark isolates decision-making from speech components, allowing targeted analysis of voice-agent reasoning, which is relevant for optimizing harness components.

  24. Sept 2026 · University of Bristol, King Abdullah University of Science and Technology

    Formal logic solvers can audit and improve language-model reasoning chains

    Proposes a neuro-symbolic framework to audit and improve reasoning chains, enhancing reliability without changing model weights.

  25. Sept 2026 · Northeastern University, Seattle

    Serving stacks can distort local language-model tool-use evaluations

    Identifies and analyzes how serving-stack rejections can distort tool-use evaluations, offering insights for improving agent harness reliability.

  26. Sept 2026 · Nanyang Technological University

    Typed selective control cuts strong-model calls while preserving agent success

    Introduces a selective control architecture that preserves agent success while drastically reducing calls to strong models, optimizing harness efficiency.

  27. Sept 2026 · Tencent

    Wrappers keep LLM coaching aligned with live user state

    Introduces State-Grounded Conditioning wrappers that move state-dependent control from prompts to structured inputs, improving alignment in coaching.

  28. Sept 2026

    Closed-loop development improves mobile agents across planning and tool use

    Describes a closed-loop development pipeline that improves mobile agent performance on planning and tool use via human-gated iteration.

28 of 61 papers shown