LLM Agent Harnesses

LLM: Large Language Model

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

428 papers67 papers in the last four weeks, down 46% on the four weeks before. 0.5% of all new papers.

Mar 3, 2026

REGAL: A Registry-Driven Architecture for Deterministic Grounding of Agentic AI in Enterprise Telemetry

Enterprise engineering organizations produce high-volume, heterogeneous telemetry from version control systems, CI/CD pipelines, issue trackers, and observability platforms. Large Language Models (LLMs) enable new forms of agentic automation, but grounding such agents on private telemetry raises three practical challenges: limited model context, locally defined semantic concepts, and evolving metric interfaces. We present REGAL, a registry-driven architecture for deterministic grounding of agentic AI systems in enterprise telemetry. REGAL adopts an explicitly architectural approach: deterministic telemetry computation is treated as a first-class primitive, and LLMs operate over a bounded, version-controlled action space rather than raw event streams. The architecture combines (1) a Medallion ELT pipeline that produces replayable, semantically compressed Gold artifacts, and (2) a registry-driven compilation layer that synthesizes Model Context Protocol (MCP) tools from declarative metric definitions. The registry functions as an "interface-as-code" layer, ensuring alignment between tool specification and execution, mitigating tool drift, and embedding governance policies directly at the semantic boundary. A prototype implementation and case study validate the feasibility of deterministic grounding and illustrate its implications for latency, token efficiency, and operational governance. This work systematizes an architectural pattern for enterprise LLM grounding; it does not propose new learning algorithms, but rather elevates deterministic computation and semantic compilation to first-class design primitives for agentic systems.
Mar 1, 2026

Tracking Capabilities for Safer Agents

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these challenges, we propose to put the agent in a programming-language-based "safety harness": instead of calling tools directly, agents express their intentions as code in a capability-safe language: Scala 3 with capture checking. Capabilities are program variables that regulate access to effects and resources of interest. Scala's type system tracks capabilities statically, providing fine-grained control over what an agent can do. In particular, it enables local purity, the ability to enforce that sub-computations are side-effect-free, preventing information leakage when agents process classified data. We demonstrate that extensible agent safety harnesses can be built by leveraging a strong type system with tracked capabilities. Our experiments show that agents can generate capability-safe code with no significant loss in task performance, while the type system reliably prevents unsafe behaviors such as information leakage and malicious side effects.
Feb 26, 2026

General Agent Evaluation

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse unfamiliar environments. This is the first systematic study, comparing tool-calling, MCP, code-generation, and CLI agents on the same benchmarks with the same models. Two gaps blocked such a study: existing harnesses require per-benchmark wiring or fixed protocol classes (web for BrowserGym, CLI for Harbor), and benchmarks themselves expect human-authored prompts, context, and integration glue. To enable this study, we contribute (1) a unifying protocol that bridges existing benchmark and agent protocols; (2) an evaluation harness that surfaces any benchmark to any general-purpose agent and backbone model; and (3) the first Open General Agent Leaderboard of agent configurations, a full factorial over 5 agent architectures x 5 backbone LLMs (three closed-source, two open-weight) x 6 benchmarks spanning software engineering, customer service, deep research, and personal assistance. We find that (i) general agents adapt to every tested domain without per-domain customization; (ii) agent architecture choice swings results by up to 12pp within a single model, yet backbone model choice dominates overall performance; (iii) on 4 of 6 tested benchmarks, top general agents are indistinguishable from the leading heavily-customized domain-specific agents; (iv) open-weight models tested exhibit "generality sinks" absent from frontier closed-source models: they consistently collapse on specific agent architectures or benchmarks; (v) a behavioral failure analysis reveals architecture-distinctive error signatures that aggregate scoring cannot discriminate. Code, harness, leaderboard, and traces are at https://www.exgentic.ai.
Feb 25, 2026

VeRO: A Harness for Agents to Optimize Agents

An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Harness optimization differs from conventional software engineering: agent harnesses interleave deterministic code with stochastic LLM completions, requiring structured capture of both intermediate execution traces and downstream outcomes. To address these challenges, we introduce (1) VeRO (Versioning, Rewards, and Observations), an outer harness that provides versioned snapshots, budget-controlled evaluation, and structured execution traces of target harnesses, and (2) VeRO-Bench, a benchmark suite of target agents and tasks with reference evaluation procedures. Using VeRO, we conduct an empirical study comparing optimizers across tasks and analyzing which modifications reliably improve target agent harnesses. We release VeRO to support research on agent optimization as a core capability for coding agents. Code is available at https://github.com/scaleapi/vero.
Feb 23, 2026

Implicit Intelligence -- Evaluating Agents on What Users Don't Say

Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit instruction-following but fail to evaluate whether agents can reason about implicit requirements spanning accessibility needs, privacy boundaries, catastrophic risks, and contextual constraints. We present Implicit Intelligence, an evaluation framework testing whether AI agents can move beyond prompt-following to become genuine goal-fulfillers, paired with Agent-as-a-World (AaW), a harness where interactive worlds are defined in human-readable YAML files and simulated by language models. Our scenarios feature apparent simplicity in user requests, hidden complexity in correct solutions, and discoverability of constraints through environmental exploration. Evaluating 16 frontier and open-weight models across 205 scenarios, we find that even the best-performing model achieves only 48.3% scenario pass rate, revealing substantial room for improvement in bridging the gap between literal instruction-following and human-like contextual reasoning.
Feb 23, 2026

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results. This exposes them to prompt injection: data meant only to be read is obeyed as an instruction. The most principled defences replace content inspection with provenance: classifying data by source and keeping trusted and untrusted apart through a separation of duty (the dual-LLM pattern) and information-flow control. Yet the leading systems are hard to fully trust: flow tracking is easy to get wrong, deliberate relaxations are hard to audit, and the dual-LLM pattern is hard-wired into the architecture. We present LLMbda, an untyped call-by-value lambda calculus that makes provenance-based defence both expressible and provably sound, without committing to an architecture. It adds the operational core of agentic systems as first-class constructs: prompt-response conversations that can be forked and cleared, code generation, and dynamic information-flow control in which every value carries a label that every reduction propagates. Isolation becomes a policy a program expresses, and reclassification an explicit, auditable construct. Our central result is a termination-insensitive probabilistic noninterference theorem over the whole calculus, including code-generating agents, with an insulated variant that holds even when the attacker chooses all untrusted inputs. The verified interpreter is itself the harness that calls the model, to our knowledge the first LLM agent harness whose executable is the subject of machine-checked security theorems, so every agent inherits the guarantee. On the AgentDojo banking benchmark, an agent built within LLMbda, enforcement always on, matches the utility of CaMeL, a leading dual-LLM defence, run without its policy checks (which halve its utility), and resists all but two of 1296 attacked runs. Our harness and all proofs are in Lean.
Feb 16, 2026

EmbeWebAgent: Embedding Web Agents into Custom Enterprise UIs

Most web agents operate at the human interface level, observing screenshots or raw DOM trees without application-level access, which limits robustness and action expressiveness. In enterprise settings, however, explicit control of both the frontend and backend is available. We present EmbeWebAgent, a framework for embedding agents directly into existing UIs using lightweight frontend hooks (curated ARIA and URL-based observations, and a per-page function registry exposed via a WebSocket) and a reusable backend workflow that performs reasoning and takes actions. EmbeWebAgent is stack-agnostic (e.g., React or Angular), supports mixed-granularity actions ranging from GUI primitives to higher-level composites, and orchestrates navigation, manipulation, and domain-specific analytics via MCP tools. Our demo shows minimal retrofitting effort and multi-step behaviors grounded in a live UI setting. Demo Video: https://youtu.be/Cy06Ljee1JQ
Jul 20, 2025

AgentFly: Scaling Agentic Reinforcement Learning with Unified Resource System

Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL). However, agentic RL remains bottlenecked by its surrounding systems: agents must interact with heterogeneous environments, such as sandboxes, model services, and external APIs. Their allocation, reuse, and lifecycle dominate rollout cost and cap the scale at which training becomes practical. In this work, we present AgentFly, an agentic RL framework built with a unified resource layer that treats each of these environments as a distinct, typed resource scheduled through one engine, with per-tool acquisition for multi-turn reuse, asynchronous backpressure, and rollout versus global-scoped lifecycles. AgentFly adopts a four-layer design: (I) agent layer that abstracts the agent, tool, and reward concepts, decomposing agentic RL into defining agents, tools, and reward functions; (II) rollout layer that composes these into agent loops and computes rewards; (III) context layer that organizes rollouts, injects contextual information, and arranges resources; and (IV) a low-level resource layer that performs resource management. We provide a suite of prebuilt tools and environments, demonstrate successful agent training across multiple tasks and models, and report the first controlled cross-framework throughput comparison against agentic RL frameworks.