Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.24007

Federation over Harness

Dixi Yao·Tahseen Rabbani·Tian Li
View original source ↗Read source document ↗Export metadata ↓

Abstract

Modern LLM-powered agents increasingly improve through experience sharing, where distributed agents distill local reasoning experience into reusable knowledge, such as a shared insight library. Existing approaches, however, still heavily rely on manually designed prompts and workflows that determine both how local agents extract useful reasoning traces and how a central/global agent aggregates them to obtain common patterns and insights. We propose Federation over Harness (FoH), a framework that automatically evolves the harness for both local and global components in this distributed multi-agent reasoning pipeline. A server agent evolves the client harness for task solving and self-reflection while, at the same time, evolving its own harness for aggregating distributed reflections, maintaining shared knowledge, and updating subsequent client harnesses. Importantly, FoH requires no extra validation signals, such as ground-truth labels or validation data, during evolution; it learns solely from self-generated reflections produced by distributed agents. Experiments on multiple benchmarks show that FoH consistently improves over single-agent baselines with a fixed harness and with harness self-evolution by 53.57% and 29.76%.

Explore related subjects

cs.MA

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Dixi Yao, Tahseen Rabbani, Tian Li. 2026-10-15. Federation over Harness. https://arxiv.org/abs/2610.24007

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

OpenAgenet / OAN White Paper: Open Infrastructure for Trusted Agent Interconnection

OpenAgenet, abbreviated as OAN, is an open infrastructure project for trusted Agent interconnection. It addresses a problem that becomes visible when Agents move from isolated applications into open, multi-operator networks: before an Agent can safely discover, select, and invoke another Agent, it needs a way to verify identity provenance, governance state, discovery authorization, freshness, and pre-connection trust evidence. OAN is designed as a protocol-neutral trust layer. It does not replace Agent interaction protocols, tool protocols, model orchestration frameworks, or application-level workflows. Instead, it provides routing-aware did:oan-based resource identity, local OAN Identity material for signing and authentication, governance-backed admission, Registrar-assisted onboarding, Root-verified package publication, authorization-aware Discovery, Root-issued infrastructure authorization VCs, controller-aware authorization, and profile-defined signed trusted invocation. The architectural center of OAN is the combination of federated governance, resource identity, trusted Discovery, and the Root Node's three hub responsibilities. Root acts as a trust authorization hub for accepted identity state and evidence, a data-distribution hub for Root-verified packages, and a semantic-governance hub for the tag tree shared by registration and Discovery. This white paper explains the motivation, architecture, roles, governance model, relationship with MCP, A2A, and ANP, deployment patterns, cooperation model, on-chain governance layer, prototype status, public pilot network, standardization surfaces, performance profile, and roadmap of OAN.

cs.MA↗
arXiv2026

OpenAgenet / OAN Yellow Paper: Technical Architecture for Trust-Governed Resource Identity and Discovery

This yellow paper describes the technical architecture of OpenAgenet / OAN. OAN is a protocol-neutral trust layer for open Agent interconnection and discoverable AI resource products. It specifies the role architecture, did:oan identity objects, registration workflow, governance-backed Root lifecycle enforcement, Root-verified package model, authorization-aware Discovery, Root-issued infrastructure authorization VCs, signed trusted invocation, Root's trust, data-distribution, and semantic-governance hub responsibilities, verification requirements, state transitions, security properties, implementation boundaries, and deployment considerations. The design is intended to support heterogeneous Agent frameworks and interaction protocols, including MCP, A2A, ANP-like systems, domain-specific Agent protocols, Skills, MCP Servers, and Tool/API resources. OAN does not define the entire business conversation among Agents or the native protocol of every resource; it defines how resource identities become admissible, discoverable, verifiable, and safe to approach before protocol-specific interaction begins, and how defined profiles carry that identity into protected protocol interaction.

cs.MA↗
arXiv2026

ECHO: Learning Epistemically Adaptive Language Agents with Turn-Level Credit

Effective multi-turn agents must decide what information to seek, how to use new evidence, and when they are certain enough to act. We introduce Epistemic Decision Processes (EDPs), a belief-state formulation of multi-turn information seeking in which actions produce external observations that update the agent's posterior over a latent task variable. EDPs make epistemic adaptivity explicit: good policies choose actions that are useful under the current belief, not merely those that correlate with eventual success. We then introduce ECHO (Epistemic Credit for History-Conditioned Optimization), a practical clipped policy-gradient objective that assigns turn-level credit using posterior-sensitive rewards. In the Clue Selector Game, a novel controlled evidence-seeking benchmark, and in CRAFT, a challenging multiagent coordination game, we show that ECHO substantially improves resolution, information gain, and efficiency over trajectory-level GRPO, and matches or exceeds frontier baselines on epistemic metrics such as grounding, recovery, and calibration.

cs.MA↗