LLM Agent Harnesses

LLM: Large Language Model

Ask about this topic

Overview

An LLM agent harness surrounds a language model with the mechanisms needed to act: tool interfaces, control loops, context and memory management, persistent state, and execution environments. Common approaches include ReAct-style loops, explicit workflow graphs, typed tool contracts, sandboxes, and verification or recovery steps; newer systems also adapt harnesses using execution traces, search, or reinforcement learning. Researchers evaluate these systems on coding, web, terminal, scientific, and interactive tasks, measuring not only success but also cost, reliability, and safety. A central tension is how much structure helps: added guidance can improve control and recovery, yet may constrain useful behavior, fail to transfer across models or tasks, or make comparisons hard to interpret without specifying the harness.

Latest papers

CardsList

389 papers118 papers in the last four weeks, up 103% on the four weeks before. 0.7% of all new papers.

Aug 20, 2026

Applying Anthropic Primitives at Large Enterprises: Harness Paradigm for Knowledge Work

Frontier models have collapsed the cost of writing custom code: a niche problem a specialist sees in their own domain now costs an afternoon. The cost of reviewing and maintaining that code hasn't collapsed. Each solution drifts from the next; understanding one means reading its codebase from scratch. Large enterprises build something centrally governed instead: at worst an off-the-shelf product, at best a graph-orchestration framework wired bespoke per use case, or a low-code platform used as the orchestrator. These are custom every time and limited in scope. Enterprises don't weigh a third option that escapes both constraints: the harness paradigm. Recent work treats the coding-agent harness as enterprise infrastructure rather than a coding tool, converging on three findings: harnesses suffice at the task level and outperform more elaborate architectures on enterprise work (arXiv:2604.00073, arXiv:2604.13107); harness choice accounts for most of the variance in agent benchmark results, more than model choice does (arXiv:2605.23950); and the gap between that finding and enterprise adoption is governance (arXiv:2605.10223, arXiv:2605.18747). We propose an architecture that closes that gap. One harness runs unmodified as the backbone; the code stays identical across every deployment, so reviewing what gets built collapses to reading its instructions file. Section 4 gives four mechanisms: credential-scoped tooling, where each backend gets one generic request tool and a scoped credential instead of a hand-built method; authorization logic outside the harness, so one artifact runs as a cron backbone, a chat-surface engine, and a terminal tool; registration is a side effect of pushing code, collapsing an audit a review of a text file. Built on microcc (https://pypi.org/project/micro-cc/), our reference harness.

George Juraj Salapa

G.S. s.r.o., PwC Austria

LLM Agent HarnessesLLM Agent OrchestrationAI Agent GovernanceBusiness Process AutomationTool Access Control for LLM Agents
AskPDF
Aug 20, 2026

Terminal Agents: A Survey of AI Agents in Command-Line Environments

Large language model agents increasingly act through terminals, yet existing surveys disperse terminal-mediated behavior across software engineering, tool use, and computer-use research. We regard terminal agents as systems whose dominant progress-bearing action--observation loop is mediated by terminal command execution, textual feedback, and stateful environment interaction. Using terminal-mediated execution as an organizing lens, this survey establishes workload-level boundaries and connects system architecture, competence acquisition, and evaluation through a seven-dimensional terminal competence profile. Our synthesis shows that realized behavior is jointly shaped by the model, interface, harness, runtime, and environment. Executable trajectories ground learning in action consequences, verification, and recovery, whereas prevailing evaluations emphasize final outcomes and expose process quality, recovery, and governance unevenly. Bounded fixed-condition diagnostics illustrate two implications: benchmark families expose different process signals, and matched system comparisons reveal benchmark-dependent performance and limits of component attribution. These findings motivate explicit reporting of system and runtime conditions, supported by replayable traces and process-level evidence. The framework provides a unified basis for studying terminal-mediated agency across software engineering and emerging application domains.

Yi Bin, Xiaoyang Yuan, Haoxi Zeng +9

Tongji University, Shanghai, China · Shanghai Innovation Institute, Shanghai, China · Shanghai Jiao Tong University, Shanghai, China +1

Terminal AgentsTool-Using AgentsLLM Agent EvaluationLLM Agent Harnesses
AskPDF
Aug 20, 2026

Bounded Loops: Pre-Run Spend Bounds, Proved Termination, and Verified Completion for Agent Harnesses

In mainstream agent frameworks, a step ends when the agent's own output says it has finished. Durable-execution platforms bound retries and time, but their checker conventionally lives in the same codebase as the work: a discipline the deployment is trusted to keep, not a property the harness enforces. We state what an agent harness must guarantee, prove it, and build the instrument that measures whether a harness delivers it. A bounded loop is a worker, an independent gate the worker cannot write to, and a declared budget; a bounded-loop graph composes them with a repair relation that lets a downstream failure re-run a finished upstream node. Three guarantees follow. It finishes: termination holds under repair, with the worst-case attempt total in closed form, if the repair budget is global not per node. It does not drift: no node reaches DONE without a gate verdict in an append-only hash-chained ledger, proved from control flow, since repair leaves no topological order to induct along. It does not overspend: the ceiling is enforced inside an attempt, not between attempts. Gates are measured against a two-tier held-out mutant corpus. We characterise two classes that let a sound-looking check pass anything: vacuity, satisfied by the absence of the thing checked, and self-attestation, where the subject supplies the value the check is applied to. On a 69-loop catalogue the instrument found 47 vacuous gates in shipped, reviewed code. Against the repaired gates it reports no false accepts over 209 destroying mutants (α≤1.8%α\le 1.8\%, Wilson 95%); that figure is saturation, not quality: freezing the gates and applying a fresh operator family recovers a 23.3% false-accept rate where the exhausted corpus reported none. A rate belongs to a specific gate; the apparatus, not our number, is the contribution. Engine, catalogue and corpus are Apache-2.0.

Varun Pratap Bhardwaj, Garima Singh, Arun Pratap Bhardwaj

Qualixar / Independent Researcher, India · Independent Researcher, India

LLM Agent HarnessesRuntime Enforcement for AI AgentsFormal Verification
AskPDF
Aug 20, 2026

EnvHarness: Awakening Static Worlds for Agent Learning

LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive or unreliable verifiers, and still produce static environments. To alleviate the engineering burden of rebuilding environments from scratch, we propose Environment Harness (EnvHarness), a programmable layer of plug-in components that wraps a static environment to reshape its behavior without modifying the underlying logic. Operating through standard interfaces, EnvHarness applies across diverse domains while ensuring every reshaped environment retains its original verifier. To automate this process, we introduce EnvRigger, which treats the target policy as a black box, observing its execution trajectories to synthesize EnvHarness components targeting diagnosed flaws, and validating them via fresh rollouts. Across five benchmarks in four domains, EnvHarness outperforms both original environments and domain-specific environment generation pipelines, achieving up to a 9.0-point improvement on held-out instances with 9.8% fewer execution steps. Furthermore, EnvHarness provides a superior optimization signal for reinforcement learning, enabling continuous, targeted co-evolution of the policy and its environment.

Chengsong Huang, Zifeng Wang, Rujun Han +14

Washington University in St. Louis · Google Cloud AI Research · University of North Carolina at Chapel Hill +1

LLM Agent HarnessesAgent Harness OptimizationProcedural Content GenerationRL for LLM Agents
AskPDF
Aug 18, 2026

StagedWorkspace: A Versioned Workspace for Knowledge-Work Agents

AI agents increasingly perform knowledge work (i.e., produce and modify persistent digital artifacts such as code repositories, documents, spreadsheets, slides, reports), yet the parsed views they search, the native files they edit, the changes they review, and the artifacts they submit can refer to different versions of the same work product. We formulate this as a workspace-state contract: every view should be explicitly tied to a version of the evolving workspace state. Coding agents partly address this need through repository contracts for search, diffs, and tests, whereas an analogous contract is less explicit for PDFs, spreadsheets, slides, notebooks, and mixed-format project folders. We propose StagedWorkspace, a versioned workspace for knowledge-work agents. The workspace binds parsed records and review diffs to content hashes of the native files as they change. In fixed-harness ablations on OfficeQA Pro and APEX-Agents, dual parsed/native access has the highest point estimate for every tested model; relative to the more limiting single view, it improves OfficeQA Pass@1 by 8.3-12.1 points and APEX mean rubric score by 4.7-9.2 points. SW-AGENT scores 63.9% with Gemini 3.1 Pro on OfficeQA and 42.1 with GPT-5.4 Nano on APEX, compared with published same-model scores of 29.3% and 25.5, respectively. A paired review-axis ablation on 57 file-editing tasks further finds higher observed scores when diffs are visible. These results identify workspace state as an experimental variable in knowledge-work agents and motivate benchmarks that score evidence, staged edits, and submitted artifacts as explicit state transitions.

Yining Hua, Hongbin Na, Yifan Zhou +3

Harvard University · Raycaster AI · University of Technology Sydney +2

LLM AgentsLLM Agent EvaluationLLM Agent Harnesses
AskPDF
Aug 18, 2026

HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external actions. Existing safety benchmarks mainly target individual attack mechanisms or a limited subset of operational settings, making it difficult to compare how safety failures emerge across different harness responsibilities. We present HarnessRisk, a lifecycle oriented benchmark that organizes agent harness safety into six operational phases including Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery. HarnessRisk contains 128 sandboxed cases, each pairing a benign user objective with an adversarial instruction embedded in an untrusted workflow artifact. We evaluate each trajectory using Utility, Attack Success Rate, Persistence, and Detection. Across three harnesses, six language models, and 14 model and harness configurations, attack success ranges from 12.6% to 80.9%, while Utility remains between 75.0% and 97.6%. Harness Configuration is the most vulnerable phase across all three harnesses, showing that attacks can succeed by altering security sensitive parameters within otherwise authorized workflows. We also find that explicit risk recognition does not reliably lead to safe action, as some configurations detect risks in more than 90% of runs while retaining substantial attack success. These results highlight the need to evaluate agent safety across multiple harness responsibilities and at the level of the deployed model and harness configuration.

Yajing Bai, Jinhao Duan, Jie Peng +4

University of North Carolina at Chapel Hill · University of Central Florida · Michigan State University

AI Agent Safety BenchmarksLLM Agent SafetyLLM Agent HarnessesPrompt Injection Attacks on AI AgentsEvaluation Awareness in Language Models
AskPDF
Aug 18, 2026

Agent Lightning v1.0: Towards Harnessed Agentic RL

Modern agents operate inside agent harnesses that manage tools, context, and control flow, making the harness a critical part of the agent system. Our original Agent Lightning introduced a disaggregated architecture that connects arbitrary agents to RL training through an LLM endpoint proxy, an approach later adopted by frameworks such as verl Uni-Agent, AReaL 2.0, slime, and Polar. We refer to this paradigm as harnessed agentic RL, where the deploy-time harness directly participates in model post-training. Harnessed agentic RL differs fundamentally from traditional agentic RL: the harness, rather than the training engine, owns the environment interaction loop, while the trainer observes only sequences of LLM request-response pairs. This introduces challenges in retokenization, sample merging, advantage calculation, loss normalization, and backend scheduling, which can substantially affect training stability and effectiveness. We present Agent Lightning v1.0, a lightweight framework for harnessed agentic RL implemented in approximately 3,500 lines of code. It supports arbitrary agent harnesses and serves as a practical testbed for studying these challenges. We evaluate it on instruction-following, search, and coding agents, and provide a complete reproducible pipeline for coding-agent RL. Using only 6K training examples and modest compute, RL improves Qwen3.5-9B on SWE-bench Verified from 41.8% to 56.4%, a 14.6-point absolute gain. We release the complete workflow and training scripts to facilitate reproducible research on harnessed agentic RL.

Zhiyuan He, Siwei Zhang, Zhiwen Zhou +7

Microsoft · Fudan University · Zhejiang University +1

Agentic RLLLM Agent TrainingLLM Agent Harnesses
AskPDF
Aug 18, 2026

Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations

LLM agents have been widely adopted to operate mission-critical infrastructure (MCI). These agents normally rely on a harness that determines what information they can access, which tools they can use, and what actions they can take. Existing systems often expose the same comprehensive harness to every task, which may not be necessary and cause resource wastes. In this paper, we focus on the identification of optimal harness configurations, and view it as a resource-matching problem between what each task requires and what the harness provides. To measure this match, we classify MCI tasks based on the mathematical representation of the underlying system and rank harness configurations by the amount and type of information they provide. We then construct task-to-harness mappings from two sources: mining research literature and measuring controlled agent execution. Leveraging the measured mapping, we propose a new harness provisioning algorithm: map-guided escalation. It begins with a task-specific harness and expands to full provision only after a failed self-check. We evaluate our method in two representative MCI tasks: in liquid cooling, it improves the agent accuracy from 0.652 under full provision to 0.715 and achieves accuracy comparable to Reflexion with 48% fewer tokens; In power grids, full provision remains accuracy-optimal, while map-based provisioning offers lower-cost alternatives. These findings show that harness provisioning follows a domain-dependent accuracy-cost Pareto frontier rather than a universal optimum.

Liangtao Lin, Qingang Zhang, Zhaomeng Zhu +2

Nanyang Technological University Singapore

Agent Harness OptimizationLLM Agent Harnesses
AskPDF
Aug 17, 2026

SkillEffect: Checked Lowering for Memory-Bounded Agent Tools

Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when models turn this guidance into code for existing tool interfaces, even a semantically correct program may load an entire input and exceed the memory available to one tool call. We present SkillEffect, a checked-lowering runtime for computations with a recoverable source relation, an audited bounded implementation, and a registered output postcondition. Before granting execution authority, an independent checker rebuilds each proposed lowering from the submitted program and immutable input. Every relation plugin supplies a source recognizer, input-fact extractor, bounded-IR constructor, arena-bound function, and postcondition; one common runtime provides checked selection, bounded-VM execution, atomic capacity leasing, and staged publication. Generality in SkillEffect is architectural rather than automatic: each supported computation requires an audited relation plugin, while the dispatch, resource-control, execution, and publication mechanisms are shared across plugins. Across six operator families, bounded access substantially reduces peak memory and improves completion under externally fixed caps. Six plugins instantiate the same contract across five execution patterns, from streaming reduction to bounded-heap Top-k. The XLSX onboarding study and Top-k extension show that a new relation and a new retained-state pattern reuse the same trust boundary, while the checker accepts all evaluated legal configurations and rejects all adversarial proposals. Together, these results show that one checked-lowering architecture can enforce heterogeneous registered memory relations at Agent tool dispatch.

Yinuo Wang, Yiyu Shi

Department of Computer Science & Engineering University of Notre Dame Notre Dame, IN, USA

Runtime Enforcement for AI AgentsTool-Using AgentsLLM Agent Harnesses
AskPDF
Aug 17, 2026

ClawGym II: Exploring Black-Box RL on Agent Harness

Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through complex harnesses remains largely unexplored, as scaling such training to long-horizon agent tasks introduces fundamental challenges. In this work, we present a unified black-box RL framework for stable and scalable optimization of general agents through complex harnesses. Concretely, we first build a sandbox-based execution infrastructure that isolates task environments and harnesses within temporary sandboxes for large-scale concurrent rollouts. We then decouple policy optimization from opaque harness execution and place a serving proxy at the model boundary to capture model calls. To reconstruct multi-turn trajectories and improve training efficiency, we organize the captured calls into prefix trees and further adapt both critic-based PPO and critic-free GRPO to optimize over the recovered tree structure. Meanwhile, we maintain training-inference consistency throughout the optimization process. Finally, we introduce mix-harness training, allowing a single model to be jointly optimized by heterogeneous harnesses. With Qwen3-30A3B, black-box RL improves Pass@1 on ClawGym-Bench by 9.98 and 14.81 points through OpenClaw and Claude Code, respectively, while remaining stable over 200-400 optimization steps. Moreover, the framework yields consistent gains on more challenging tasks such as JobBench and OfficeQA. Overall, our framework enables effective, stable, and scalable optimization of general agents through black-box harnesses, supporting unified training across heterogeneous execution systems.

Huatong Song, Fei Bai, Ming Yang +17

Gaoling School of Artificial Intelligence, Renmin University of China · IQuest Research

Reinforcement LearningRL for LLM AgentsAgent Harness OptimizationLLM Agent Harnesses
AskPDF
Aug 17, 2026

The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window. We model this as reconstructing a coupled-fact graph: at each edit, a required fact comes from recent context or parametric memory, and the facts covered by neither form coherence debt. We supply and withhold each channel and inject faults across seven models and five harnesses. As expected, no model completes a task on an unseen API with both channels empty, and putting the facts in the prompt restores success. When a rename defeats what models memorized about a real library, all seven fail in the same place, passing and missing the same tests. Availability decides the outcome and distance does not: withholding a fact costs exactly the work it supports, and a supplied fact works as well far from the edit as next to it. Harnesses pay unequal prices for it: configurations that all pass every test differ more than tenfold in tokens consumed because they rebuild the same content at different rates, and spending more recovers nothing when facts are withheld. A missing fact produces wrong work rather than absent work: an agent asked to act acts, fabricating the file or guessing the value, so instruments built on reads look for a hole already filled. How often it says it is blocked instead is a property of the model, from every trial to none. Availability does not settle every edit: where standard and code disagree, agents follow the standard even when it prescribes the worse code, so a stale convention file costs more than no file. Because parametric memory substitutes for reading, on SWE-bench, where models likely know the repositories, reads no longer predict success. Harnesses should keep the facts an edit depends on available when the agent writes, and check that availability against what the agent produces rather than what it reads.

Bardia Mohammadi, Lars Klein, Aman Chadha +2

Max Planck Institute for Software Systems · EPFL · Apple +1

Repository-Level Code GenerationLLM Agent MemoryAgent Memory ManagementLLM Agent HarnessesKnowledge Conflicts in Language Models
AskPDF
Aug 17, 2026

Mint-Agent: Introducing Finance-Native Agentic Foundation Models

Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining long-horizon research whose conclusions remain auditable. We present Mint-Agent, a family of finance-native agentic models designed around these two scales of financial intelligence. Mint-Agent is built upon three pillars: data, harness, and algorithm. Our data engine constructs clean, specialized tasks for atomic financial capabilities and long-horizon agentic execution from real-world financial sources. MintHarness enables stable interaction with open-ended environments and maintains auditable evidence trails across extended research trajectories. Our training recipe combines SFT, critical-step OPD, and RLVR to develop separate financial reasoning and agentic execution experts, which are then unified through model merging and multi-teacher on-policy distillation into compact, general-purpose financial agents. This pipeline yields two flagship models, Mint-Cu (9B) and Mint-Ag (27B). Across professional financial benchmarks, our models demonstrate two defining strengths: (1) Reliability: Mint-Ag achieves 98.33% on RFC-Bench, surpassing GPT-5.6-Sol and Claude-Opus-4.8 by 3.66 and 3.00 points; and (2) Executability: Mint-Cu reaches 69.86% on FinSearchComp T2, outperforming Agents-A1-35B and Nex-N2-mini by 22.83 and 12.78 points, while Mint-Ag achieves 76.00% and 60.49% on FinanceAgentBench v1.1 and v2, respectively. These results establish a path toward trustworthy financial intelligence in which domain expertise, long-horizon execution, and auditable evidence are jointly engineered as a unified foundation for frontier agentic models.

Mint-Agent Team, Kun Wang, Gavin Zhang +7

Mint Agent Team · Nanyang Technological University · Shanghai AI-Finance School, East China Normal University +1

LLM Agent TrainingAutonomous Research AgentsLLM Agent ReliabilityFinancial ServicesLLM Agent Harnesses
AskPDF
Aug 17, 2026

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

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. We introduce a unified execution model that maintains a work item's persistent identity and versioned authoritative state across calls. Each step receives input scoped to a specific state version and new material; a result advances state only after validation and recording. We implement selected paths of this model in AstronOS using Cases, Tasks, and Scenario Packs across central and local execution. We compare five complete strategies for carrying an established software-version update plan into a fresh model session: rereading original materials, replaying full history, deterministic text summary, deterministic JSON, and the AstronOS runtime-mediated handoff. Ten controlled tasks are run under all five strategies with three repetitions, yielding 150 included executions. On the single-stage reference family, strategies perform similarly. In the primary three-stage A-C batch, AstronOS passes the frozen scorer in 14 of 15 executions, compared with 0 of 15 for rereading and 2 of 15 for full-history replay; later non-interleaved summary and JSON batches each pass 0 of 15. AstronOS has lower attempt-accounted model-token cost per passing execution, while requiring more execution-window time per attempt. These results associate the complete AstronOS condition with higher end-to-end pass rates across fresh sessions in this benchmark, at a measurable time cost.

Zhenhang Nie, Gui Zheng, Xudong Sun +2

iFLYTEK Co., Ltd., Hefei, China · iFLYTEK Co., Ltd., Hefei, Anhui, China.

Long-Horizon Agent TasksLLM Agent HarnessesSoftware Engineering AgentsLLM Agent Evaluation
AskPDF
Aug 16, 2026

Deploying Frontier Agentic Technology in MOOSEnger, a Multiphysics-Capable AI Assistant

The Multiphysics Object-Oriented Simulation Environment (MOOSE) is an open-source finite-element framework for building multiphysics simulation applications. Using a multiphysics environment effectively demands specialized expertise, creating a barrier for many domain scientists and engineers. MOOSEnger, developed at Idaho National Laboratory (INL), is a domain-specific, tool-enabled AI agent built for the MOOSE Framework. This work extends MOOSEnger with a harness focused on locally-hosted models. The harness gives the agent a full pipeline: it retrieves contextual knowledge from the MOOSE repository, validates and diagnoses the resulting input through interaction with the simulation executable environment, and extracts and stores lessons in a persistent memory. The resulting framework is demonstrated on an engineering problem from the National Reactor Innovation Center Virtual Test Bed (VTB), illustrating its potential to support realistic multiphysics simulation workflows. Additionally, the agent performance is evaluated on different categories including diffusion, Navier--Stokes, phase field, plasticity, porous media flow, solid mechanics, transient heat transfer, and reactor mesh generation. Each category consists of 25 prompts/cases. We compare MOOSEnger-Gemma4 against MOOSEnger-GPT-5.2, alongside baseline Gemma4 and GPT-5.2 without agentic capabilities. MOOSEnger-GPT-5.2 shows a slight edge, achieving a 90% success rate versus 76.5% for MOOSEnger-Gemma4. The baseline models perform far worse, at just 5% (GPT-5.2) and 0% (Gemma4), underscoring the impact of the agentic harness.

Zaid Abulawi, Mengnan Li, Guillaume Giudicelli +2

Department of Nuclear Engineering, Texas A&M University (TAMU), TX, USA · Idaho National Laboratory (INL), ID, USA

Tool-Augmented Language Model AgentsLLM Agent HarnessesAI Agents for Scientific DiscoveryAgentic RAGMultiphysics SimulationMemory-Augmented Agents
AskPDF
Aug 16, 2026

Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report

AI-powered digital avatar streamers must answer product questions, engage viewers, and execute marketing strategies in real time, demanding low latency, frequent strategy updates, and accurate yet effective responses. Evolvable Harnesses, whose Skills, Hooks, prompts, and tools can be updated independently of model weights, enable rapid iteration but expose a trade-off: large models adapt zero-shot yet are too slow, whereas compact models meet latency targets but overfit to fixed Harness configurations. We propose Harness-Aware Training (HAT), which trains compact models to adapt to changing Harnesses. Its key component, Harness-State Augmentation (HSA), applies task-preserving transformations to Skill identifiers and content, tool schemas, prompt structures, and Hook functions. Training proceeds in three stages: HSA-SFT learns reasoning and tool use from strong-model trajectories across diverse environments; General On-Policy Distillation restores generalization lost during SFT; and HSA-RL improves robustness to changing Harnesses through reinforcement learning in augmented environments. Across four evaluation sets, HAT achieves 94.8 on Live-Stream QA (base: 80.3; strongest general LLM: 93.0) and 94.6 on Harness-Variant QA (base: 75.4). Unlike Fixed-Harness SFT, which lowers IFEval by 7.7 points from the base model, HAT avoids this regression and reaches 83.5. On one NVIDIA H20 GPU, the optimized system delivers P50 and P95 latencies of 3.4 s and 8.1 s. Deployed in Taobao Live's digital-avatar service, it also yields positive online A/B test results for item-page views.

TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin +7

TaoLive AIGC LLM Team

LLM Agent TrainingLLM Agent HarnessesRL for LLM Agents
AskPDF
Aug 16, 2026

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business rules and edge cases it must handle continue to evolve. Existing approaches address agent construction and one-time evaluation but provide no structured mechanism for continuous post-deployment behavioral correction without modifying the agent's source code. Most of the approaches offered in the market, require intense collection of logs and traces, and re-examining the agent design by the engineering team, a process which is heavy, long and negates the economical value of agentic transformation. We introduce Agent Gym, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop. The framework provides six composable capabilities --- Act, Evaluate, Investigate, Correct, Learn, and Observe --- organized across three architectural zones: a constitution layer that codifies domain knowledge in configuration artifacts, a runtime inference pipeline that chains acting, investigation, and adaptive correction, and a learning loop that enables subject matter experts to discover and validate new correction rules through natural language interaction. The key technical contributions include a hybrid deterministic-LLM correction engine with 21 condition operators and three-tier actions, a three-layer investigation architecture for ground-truth-free compliance validation, and a programmatic safety loop that guarantees rule correctness before human approval. We further introduce the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency. An open-source reference implementation for invoice processing demonstrates that the framework is fully operational and ready for adoption.

Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge +2

Google Cloud

LLM Agent EvaluationLLM Agent Self-ImprovementHuman-in-the-Loop EvaluationLLM Agent HarnessesContinual Learning for LLM Agents
AskPDF
Aug 16, 2026

Kozuchi Agent: A Language-Agnostic Open-Weight Agent for Software Repair

Industrial software-engineering teams increasingly need LLM agents that turn bug reports into correct patches, yet benchmark-scale operation adds long horizons, tool-use discipline, context persistence, heterogeneous clusters, and evaluation reuse. We present Kozuchi Agent, a language-agnostic open-weight repair agent and CI-operated evaluation pipeline. Explicit phases, persistent state, deterministic tools, a model-independent action interface, and cross-agent test-time selection make runs auditable and repeatable. With locally hosted Qwen3.5-27B, no fine-tuning, and TTS@8, Kozuchi resolves 374/500 SWE-bench Verified instances on the official evaluator. Unchanged on Multi-SWE-bench Java, the same 27-billion-parameter agent resolves 41/128 instances (32.03%), ranking first among strict open-weight submissions and fourth of 42 overall; on Python it ranks 12th of 135 and first among open-weight systems. Per-phase behavior remains within +/-5 percentage points across languages. Remaining failures mainly reflect semantic correctness, Java-specific harness issues, and selection errors. Across both tracks, results compare favorably with open/local peers by parameter count. Analysis of candidate diversity, selector regret, and patch reliability shows that the remaining gap is primarily semantic correctness and selection rather than edit formatting or proprietary-model access. Operationally, reusable CI stages reduce operator touch-points from five to one across heterogeneous internal clusters.

Mehdi Bahrami, Kosaku Kimura, Satoshi Munakata +24

Fujitsu Research of America Santa Clara, CA, USA · Fujitsu Research Kawasaki, Japan · Fujitsu Research of Europe Slough, UK +1

Software Engineering AgentsAutomated Program RepairLLM Agent HarnessesLLM Agent Evaluation
AskPDF
Aug 15, 2026

StateM: Reaching 95.3% Raw Accuracy, or a $15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate lessons from earlier executions, skip known procedures, or stop prematurely. We bet on harness scaling to improve the execution system around an agent without changing its model weights. We introduce StateM, an agent-native runtime that organizes execution around durable states, phase-local context, checked transitions, recoverable runbooks, and versioned procedural practices that agents and users can inspect together. On Terminal-Bench 2.1, StateM raises GPT-5.5 xhigh to 92.1%, versus 83.1% reference and GPT-5.6 Sol Ultra at 91.9%. The runbook transfers unchanged to GPT-5.6. With GPT-5.6 Sol xhigh, StateM reaches 95.3% raw accuracy across 445 trials and succeeds on all 89 tasks at least once. The frozen profile raises GPT-5.6 Luna from 76.7 to 85.4%, above the 84.9% Sol xhigh reference. Using the same runtime, runbook structure, and golden rules, less than $38 of adaptation raises DeepSeek-V4 Flash from 82.7 to 88.1% under standard timeouts and to 89.1% on an 88-task common core. Extending only the remaining latency-sensitive task matches the reported 88.8% GPT-5.6 Sol max result. Final-score API usage is about $15 versus $574.68 for the GPT reference; total DeepSeek expenditure is $52.22. On BusinessBench, family-specific runbooks built on development sets yield held-out gains of 0.55 macro and 1.34 micro points; two mechanism-matched families improve by 10.04 points. Concrete rules generalize when tasks share execution structure, while the control methodology applies broadly. StateM turns selected postmortem findings into persistent, executable preconditions and practices, making learned controls explicit and enforceable through stateful controls. Code at github.com/henryqin1997/statem.

Ziheng Qin, Yaxin Lu, Zhangyang Atlas Wang +1

Somewhere on the Earth

LLM Agent HarnessesLong-Horizon LLM AgentsLLM Agent ReliabilityRuntime Enforcement for AI Agents
AskPDF
Aug 15, 2026

Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents

Learning from experience is critical for developing capable, self-improving large language model (LLM) agents. Existing methods typically extract knowledge from accumulated trajectories via reflection, memory, rules, or skills. However, agents in realistic environments continuously encounter novel tasks, often offering only a one-shot opportunity to improve. These executions yield rich but highly noisy contexts, entangling broadly useful lessons with task-specific artifacts. Critically, prior works rarely validate their effectiveness on complex real-world tasks or isolate the underlying drivers of improvement. To address these gaps, we formulate online harness learning, where a frozen agent improves by continually updating a structured harness across sequential tasks. This formulation enables a systematic study of key self-improvement factors through our proposed Evo-Harness. At its core, context-to-harness skill compilation distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation. To demonstrate the efficacy of one-shot skill compilation, we evaluate across five realistic benchmarks (TerminalBench2, SWE-bench, CL-Bench, -bench, WebArena-Infinity). Our extensive analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly. Our code is available at https://github.com/A-EVO-Lab/a-evolve/tree/release/evo-harness.

Tianxin Wei, Zhan Shi, Minhua Lin +14

University of Illinois Urbana-Champaign · Amazon · The Pennsylvania State University +3

Continual Learning for LLM AgentsLLM Agent Skill LearningOnline LearningLLM Agent HarnessesSelf-Evolving Agents
AskPDF
Aug 14, 2026

MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning

Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time. Existing approaches handle this poorly: a one-shot vision-language model (VLM) compresses the whole procedure to fit its context window and loses the detail a "before" or "after" question depends on, while video agents that train the model where to look are data-hungry and transfer poorly to out-of-domain surgery. We build an agent harness that separates reasoning from perception and improves by evolving context rather than optimizing weights. A text-only orchestrator plans which evidence to gather and issues an auditable sequence of tool calls, while frozen vision-language sub-agents execute each call over the pixels, viewing, cropping, inspecting frames, and retrieving external knowledge. We further propose a gradient-free, reward-gated Heuristic Skill Distillation loop that mines the agent's own low-scoring traces and keeps a candidate skill only when it raises a validation reward, yielding reusable retrieval skills, notably directed re-look. Growing an external skill library rather than tuning weights, the loop adapts from only about 100 labeled examples, far fewer than supervised or reinforcement fine-tuning requires. To evaluate this agent, we introduce MedClawBench, a de-leaked, doctor-grounded benchmark of 1,123 questions over self-built long neurosurgery recordings and a held-out public lecture-video test split. Across both datasets and all four evaluation dimensions, our agent consistently outperforms one-shot VLMs and general video-agent frameworks, with the largest gains on the long, out-of-domain neurosurgery videos. Project page: https://fyycs.github.io/medclaw/.

Yingying Fan, Penghui Du, Leyan Zhu +10

School of Automation and Intelligence, Beijing Jiaotong University, Beijing 100044, China · Department of Electrical and Computer Engineering, University of Maryland, College Park, MD 20742, USA · University of British Columbia +2

Surgical Video UnderstandingLLM Agent HarnessesLLM Agent Skill LearningLong-Horizon Agent Evaluation
AskPDF
Aug 14, 2026

HELIX: Model-Harness Co-evolution for Recursive Self-Improvement

Scaling agent capability has largely focused on improving the model, yet an interactive agent acts through a runtime harness that mediates context, tools, control flow, and stopping. The harness shapes both what a model can accomplish and the trajectories from which it learns. This coupling motivates model-harness co-evolution for recursive self-improvement: build harnesses for a fixed model, update the model from verified sibling trajectories, and rebuild the harnesses as model capabilities change. Realizing this loop requires a controlled way to evolve harnesses while preserving intervention identity and effect. We present HELIX, a source-traceable substrate for harness evolution. HELIX decomposes agent systems into typed ports, reusable atoms, recipes, product shells, and runtime policies. It makes interventions explicit and auditable while retaining trajectories, test outcomes, and provenance. Harness evolution thus serves two linked roles: improving fixed-model execution and producing matched successes, regressions, near misses, and alternative solutions as data for subsequent model improvement. We evaluate HELIX in one evolution round on code repair. A 65-candidate portfolio discovers a fixed harness that improves task coverage by 4.0% over Pi, while the full portfolio exposes up to 58.0% more verified coverage through complementary sibling behavior. Selected candidates are assessed with repeated runs and the SWE-bench evaluator. A 200-slot sibling slice yields 438 verified SFT, critic, filter, and preference records. These results show how harness, model, and data form a feedback system: harness evolution expands current capability and creates learning signal for the next model; model updates motivate the next round of harness evolution. HELIX provides an auditable interface for studying this recursive process. Code is available at https://github.com/HKUDS/HELIX.

Tianyu Fan, Chao Huang

In3 Lab, The University of Hong Kong

LLM Agent HarnessesAgent Harness OptimizationLLM Agent Self-Improvement
AskPDF
Aug 13, 2026

Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test

Agent harnesses combine retrieval, routing, state, provenance, and verification, but locally successful components may disagree on shared state. We model this failure with a finite capability sheaf: stalks encode typed behavior signatures, restriction maps retain shared fields, and accepted runs are useful global sections. An exact finite constraint-satisfaction problem (CSP) defines acceptance, while a linearized relative cohomology class provides a diagnostic and search feature. A controlled experiment over 20 task clusters introduces hidden interior mediators whose raw states are nuisance variables. Quotienting their coboundaries reduces the candidate budget from 2,000 to 1,000 per cluster; aligning the hidden state removes the gap. Exact CSP matches the quotient, so the result demonstrates invariance to stale representatives, not superiority over exact reasoning. We then test the method on a discovery split from the SWE-bench Multilingual pool of PatchFuseBench: 160 issues from 20 repositories, 875 real candidate patches, 2,579 source-aware edit atoms, and 153 newly executed patches. A first pool-level construction is constant because [b−Dx]=[b][b-Dx]=[b] in coker⁡D\operatorname{coker}D and therefore cannot rank configurations. A candidate-indexed repair is nontrivial on 848/875 candidates and varies within 120/160 issues. It resolves 118 issues versus 116 for a matched noncohomological selector, but the difference is not supported across repositories (exact sign-flip p=0.75p=0.75). A leave-one-repository-out abstention gate reaches 127/160, tying the strong anchor and exceeding its matched gate by one issue (p=1.0p=1.0). The discovery gate therefore fails and the confirmatory split remains sealed. The study supports the controlled invariance mechanism and an identifiability correction, but not a real-world cohomological advantage.

Saveliy Batruin

Independent researcher

Automated Program RepairSheaf TheoryLLM Agent Harnesses
AskPDF
Aug 13, 2026

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first develop a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective. Building on this formulation, we propose HARD (Harness-based Autonomous Runtime Defense Evolution), a self-evolving runtime defense framework that automatically identifies appropriate intervention strategies and iteratively improves defense artifacts based on observed failure traces. HARD transforms runtime defense development from manual engineering into an autonomous evolution process, and extensive experiments demonstrate that it improves security performance over existing handcrafted defenses while preserving benign task utility. Our findings highlight autonomous defense evolution as a promising new paradigm for securing deployed LLM agents, enabling agents to identify defense weaknesses and continuously improve their protection mechanisms.

Jiajun Ruan, Peiyang Li, Yukun Chen +2

University of Minnesota · Ant Group · Tsinghua University +1

LLM Agent SecurityLLM Agent SafetyLLM Agent HarnessesSelf-Evolving Agents
AskPDF
Aug 12, 2026

@skills: Attention is all you have

There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains in the system prompt, competing for fewer than 100 reliable trigger slots. This leaves the long tail with no practical path to use and forces teams' own playbooks to compete for the same scarce space. We observe that installation bundles three separable functions: content, persistence, and automatic triggering. Only the last requires prompt residency. We therefore propose @skills, an open protocol that separates them. A path addresses any skill, subtree, or collection, and reading a skill is sufficient to use it, so nothing is installed or made resident. The operation vendors a copy at the same path into a project's Git-tracked tree for adaptation and ownership. The operation adds one .gitignore-style line, the only element that costs prompt residency. A directory is a menu, making bundles ordinary directories rather than all-or-nothing units. The protocol requires no manifest, lockfile, or registration, and SKILL.md remains unchanged. @skills is additive, ships as an installable package, and turns any agent that can read files and run commands into a client through a single instruction file. Its open specification is at https://github.com/SylphAI-Inc/atskills and it is implemented in the AdaL CLI at https://adalagent.ai . Because paths address skills well but cannot find them, the protocol is paired with a free hub at https://atskills.one for corpus-wide search and ranking, repository-free hosting, private and team collections, and one-screen authoring. The hub is optional: gh: and local paths resolve without it, and indexed GitHub skills retain their gh: identities. Install less, use more.

Li Yin, Zhi Li, Zhan Shi +4

Atlas · The University of Texas at Austin

LLM Agent Skill RetrievalLLM Agent Harnesses
AskPDF
Aug 10, 2026

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime control. Existing safety mechanisms often treat the harness as a fixed deployment artifact, limiting their ability to evolve with emerging risks. Moreover, coupled functions across harness components obscure safety responsibility attribution, making localized evolution difficult. We propose Safety Harness Evolution (SHE), a framework that learns evolving safe boundaries from rollout trajectories. SHE decomposes the harness into four artifacts with explicit safety responsibilities, including the System Prompt, Rule Bank, Safety Memory, and Tool Policy, defining clear functional boundaries for localized evolution. Based on this decomposition, SHE introduces an attribution-guided evolution loop that converts trajectory failures into structured diagnoses, learns artifact-specific boundary refinements, and selects evolved harnesses through safety-utility validation. Experiments on Agent-SafetyBench demonstrate that SHE effectively enhances safety through harness evolution, achieving a 3.1x ASR reduction compared with static SafeHarness, while also improving benign utility. The evolved harness further generalizes to unseen risks on the held-out AgentHarm benchmark and transfers across agent models without additional evolution.

Wanying Qu, Qinghua Mao, Yu Li +12

Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Fudan University +1

Agent Harness OptimizationLLM Agent SafetyLLM Agent Harnesses
AskPDF
Aug 10, 2026

STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework

Incident response planning is critical for restoring compromised software systems. Existing AIOps methods automate fault diagnosis and remediation and adapt response using feedback, but lack a unified decision basis across planning and execution. This limits their ability to maintain incident state and align actions with evolving recovery objectives during long-horizon, multi-stage security incident response. We present STAIR, an end-to-end agentic response framework that organizes planning and execution around a shared incident state. STAIR maintains incident evidence, response actions, and execution feedback in Graph-as-State (GAS), using the latest state to determine the response stage and recovery objectives for stage-specialized planning. The framework retrieves effect-validated historical experience based on the current state and stage to guide action selection. An Execution Harness executes actions, returns feedback to update GAS, and validates action effects for future experience reuse. We construct STAIR-Bench, an executable incident response benchmark comprising 44 Docker-based cyber-range cases. On its held-out test cases, STAIR achieves an overall defense score of 0.95, improving over the strongest baseline by approximately 10.47%. In the independent CAGE4 environment with ongoing attacks and benign activity, STAIR reduces cumulative penalties by approximately 28.8% relative to the strongest baseline.

Hanlin Jiang, Jionghao Huang, Shaofei Li +6

Key Laboratory of High Confidence Software Technologies, Peking University, Ministry of Education · Southeast University · Huawei Technologies Co., Ltd.

Autonomous Cyber DefenseLLM Agent OrchestrationCybersecurityLLM Agent HarnessesLLM Agent Planning
AskPDF
Aug 10, 2026

From Prompt to Harness: Coderlet from Scratch

A model alone does not determine how a programming agent acts. What the model sees, how actions enter the environment, how feedback returns, and how one run affects the next all depend on how the harness is organized. Minimal examples usually show only the basic interaction between a model and tools, while production systems spread these relationships across complex components and dependencies. This paper studies a compact harness design by following a single request through context formation, model decision, environmental action, observation return, and state continuation. Three boundaries---model, execution, and state---connect the model service, tool environment, and persistent state, while the request lifecycle determines the order in which these transitions occur. Together, they show the harness's core role: turning model generations into environmental actions, carrying runtime feedback into later decisions, and allowing state to continue across requests. On top of this runtime structure, a harness can also be gradually refined across runs through continued bootstrapping. The design is realized in the executable artifact https://github.com/lilinxi/Coderlet.

Mengfan Li

Coding AgentsAgent Harness OptimizationLLM Agent Harnesses
AskPDF
Aug 9, 2026

Evidence-Calibrated Runtime Reconstruction for Agent Skills Across Heterogeneous Coding Agents

Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly represented by session-, model-, or tool-centric traces: a Skill can be discovered but not activated, activated without instructions, or appear successful without an independently verified outcome. We present Skill Runtime Intelligence, a passive runtime-intelligence system that reconstructs supported Skill-lifecycle stages across heterogeneous harnesses while preserving unsupported stages as unknown. Its Run Panorama separates immutable events, deterministic relations, inferred diagnoses, and controlled outcomes with four evidence grades; optional trace import and OTLP/HTTP export support existing observability deployments. Across six frozen repository profiles, three coding agents, and seven clean or fault-injected conditions, all 126 executions preserve source worktrees and each correlates to exactly one source session. Yet adapters expose three distinct semantics: no Skill runs; complete runs but no failure-like events; or failure-like events in every operational-failure and clean session. In a seven-template diagnostic study, semantic aliases and Panorama localize the same six non-clean boundaries but differ in exact/status behavior; both Raw views emit a failure status on all 18 clean cases, while Panorama emits none. A known-rule graph conforms to 126/126 frozen contracts, whereas a second model completes only 228/378 calls. These observations motivate executable adapter qualification and show that event presence is not boundary fidelity, composite exact scores mask distinct errors, and model explanations must not overwrite deterministic facts.

Xueping Gao

Alibaba Cloud, Hangzhou, China

AI Coding AgentsAI Agent MonitoringLLM Agent Harnesses
AskPDF
Aug 9, 2026

The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task

How much an AI coding agent costs to run can depend more on the agent scaffolding that drives it than on the interface through which it reaches its tools. We set out to measure the cost of tool use over the Model Context Protocol (MCP) against tool use over an ordinary command-line interface (CLI), a difference on which published estimates disagree by more than an order of magnitude while resting on practitioner reports that cannot be reproduced. We ran one fixed software task -- six operations against a private online git repository -- across seven agent scaffoldings and five language models, and we verified completion by inspecting the repository state rather than trusting the agent's self-report. The dominant effect was the scaffolding. Two of the seven ship no MCP support at all; they completed every run using only the CLI, which shows that MCP is unnecessary for this class of work, and they were 5.0x to 28x cheaper than the five scaffoldings that do support MCP, comparing CLI runs alone with no MCP server attached anywhere. The effect was largest for a small 27-billion-parameter model running locally, whose cost varied 139x across scaffoldings while it completed the task under all of them. The comparison we set out to make proved unstable: thirteen strictly paired MCP-to-CLI ratios span 0.43x to 29x, with outliers on both sides. The two interfaces separate on the cost of failure, where 12.9 per cent of the money spent on MCP runs bought no completed work against 2.2 per cent on CLI runs, but not on its frequency: failures were equally common in both, in the original runs and in their repetitions alike. Agents frequently ignored the interface they were assigned, so comparisons that do not verify actual behaviour measure an unknown mixture. The harness, the task, the verification and the complete dataset are released as open source.

Marc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo +1

Universitat Politècnica de Catalunya (UPC), Barcelona, Spain · Universidad de Salamanca (USAL), Salamanca, Spain · Universidad del País Vasco / Euskal Herriko Unibertsitatea (UPV/EHU), Donostia-San Sebastián, Spain

AI Coding AgentsLLM Agent EvaluationTool-Using AgentsModel Context ProtocolLLM AgentsLLM Agent Efficiency+1
AskPDF
Aug 7, 2026

A2EA^2E : An End-to-End Agent Auditing Engine

With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce A2EA^2E (Agent Auditing Engine), an end-to-end evaluation engine designed for agent harnesses. A2EA^2E leverages our newly proposed Agent Task Protocol (ATP) to enable the rapid integration of evaluation tasks with different harnesses. Through an automatically instrumented Monitor, it captures and generates standardized execution traces during experiments. In the Evaluation stage, A2EA^2E systematically assesses harness capabilities using a suite of multidimensional metrics. Compared with correctness alone, these metrics provide a more fine-grained characterization of differences among harnesses in execution efficiency, tool use, task planning, and error recovery. Experiments conducted with A2EA^2E further reveal that model-harness combinations exhibit substantial performance variation across different types of tasks, and that no single combination consistently outperforms all others across every task. These findings not only demonstrate the necessity of systematic evaluation but also provide useful guidance for the co-evolving of models and harnesses. Our code is available at https://github.com/datamllab/A2E.

Haoning Wang, Mingxun Zhang, Chenyue Yu +4

Shanghai Artificial Intelligence Laboratory

Tool-Use EvaluationAI Agent AuditingLLM AuditingLLM Agent EvaluationLLM Agent HarnessesAutomated Agent Evaluation
AskPDF