RSIHub: A Composable Framework for Agent-Evolution Methods

Zimu Wang; Xiaobo Wang; Siyu Ye; Jiaqi Li; Silin Chen; Yuling Shi; Ruobing Wang; Jingjing Zhang

cs.AIOct 23, 2026

RSIHub: A Composable Framework for Agent-Evolution Methods

Authors: Zimu Wang, Xiaobo Wang, Siyu Ye, Jiaqi Li, Silin Chen, Yuling Shi, Ruobing Wang, Jingjing Zhang,

Organizations: University of California, Berkeley · Shanghai Jiao Tong University · University of Science and Technology of China · Beijing Institute for General Artificial Intelligence ·

Abstract

Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an open-source framework for building, comparing, and extending these methods on shared infrastructure. Recipes compose reusable operators and declare mutable resources; RSIHub supplies execution, evaluation, recovery, and lineage. Researchers can focus on evolution policy while evaluation stays outside the mutable surface and results remain tied to candidates and evaluation conditions. We instantiate AHE, Hyperagents, A-Evolve, and GEPA without modifying the framework core, keeping method-specific logic in recipes and operators. We evaluate them with MiniSWE and Codex on Terminal Bench 2 and $τ^3$ Banking under fixed model and evaluator configurations. The largest observed overall pass@1 gain is 13.5 percentage points, while method rankings vary across settings and optimization gains do not always transfer to held-out tasks. RSIHub provides a common protocol for comparing evolution policies, inspectable candidate histories, and reusable components for developing new methods.

Figures & tables

Figure 1: RSIHub separates method policy from framework-managed execution. In a recipe-driven run, a researcher-authored recipe remains fixed across iterations. In an agent-driven run, an outer agent uses permitted feedback from each completed iteration to revise the recipe’s operator bindings and policy settings for the next. At each iteration boundary, RSIHub validates and snapshots the active recipe before running the same guarded lifecycle. The target definition, evaluator, runtime, data splits, and mutable surface remain fixed; surface enforcement, protected evaluation, and verified archive writes stay under framework control.

Benchmark	Agent	Method	Train split	Gate split	Sealed split	Overall
Terminal Bench 2	MiniSWE	Seed	32.6	12.4	11.2	56.2
		AHE	37.1 ( $+4.5$ %)	12.4 ( $+0.0$ %)	15.7 ( $+4.5$ %)	65.2 ( $+9.0$ %)
		Hyperagents	36.0 ( $+3.4$ %)	16.9 ( $+4.5$ %)	16.9 ( $+5.6$ %)	69.7 ( $+13.5$ %)
		A-Evolve	40.5 ( $+7.9$ %)	12.4 ( $+0.0$ %)	16.9 ( $+5.6$ %)	69.7 ( $+13.5$ %)
		GEPA	36.0 ( $+3.4$ %)	12.4 ( $+0.0$ %)	15.7 ( $+4.5$ %)	64.0 ( $+7.8$ %)
	Codex	Seed	39.3	15.7	14.6	69.7

Table 1: Pass@1 before and after evolution on Terminal Bench 2 and

\tau^{3}

Banking. All entries are percentages; split columns report their contribution to full-benchmark pass@1. Parenthesized values are absolute changes from the corresponding seed baseline, measured in percentage points. Among evolved variants, the best results per agent are in bold and the second best are underlined .

Benchmark	Agent	Avg@3			Agreement		Excess disagreement
Benchmark	Agent	Direct	RSIHub	$\Delta$	D–D	D–R	Excess disagreement
Terminal Bench 2	MiniSWE	59.6	56.9	$-2.6$	83.5	84.6	$-1.1$
Terminal Bench 2	Codex	64.0	61.4	$-2.6$	88.0	82.0	$+6.0$
$\tau^{3}$ Banking	MiniSWE	24.6	22.0	$-2.6$	81.1	80.9	$+0.2$
$\tau^{3}$ Banking	Codex	29.6	33.0	$+3.4$	82.1	80.1	$+2.1$

Table 2: Capability preservation across three repetitions. Avg@3 is mean pass@1; D–D is Direct-A–Direct-B agreement, and D–R averages Direct-A–RSIHub and Direct-B–RSIHub agreement.

Class	Scenario	Required invariant	Correct	Median (s)	Correct	Median (s)
			Terminal Bench 2		$\tau^{3}$ Banking
Recovery	Terminate during mutation	Resume from a certified parent; admit no partial child	30	4.72	30	5.15
Recovery	Terminate during evaluation	Preserve the old attempt and certify one terminal retry	30	3.61	30	4.94
Recovery	Terminate after stamp/receipt	Reconcile receipts without a duplicate event	30	3.27	30	4.81
Boundary	Modify evaluator files	Reject evaluator mutation before certified evaluation	30	4.72	30	2.35
Boundary	Write outside the mutable surface	Exclude all out-of-surface edits from the candidate	30	3.27	30	2.37

Table 3: Fault-injection and boundary-enforcement results in two benchmark campaigns. Each correct-outcome entry is out of 30 trials; no trial admitted corrupted state. Latencies are reported separately rather than averaged across machines.

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Benchmark	Agent	Direct-A–RSIHub	Direct-B–RSIHub	Mean D–R
Terminal Bench 2	MiniSWE	84.3	85.0	84.6
Terminal Bench 2	Codex	82.4	81.6	82.0
$\tau^{3}$ Banking	MiniSWE	82.1	79.7	80.9
$\tau^{3}$ Banking	Codex	79.4	80.8	80.1

Appendix

Table 4: Pairwise cross-mode task agreement over three repetitions. The mean D–R agreement is the arithmetic mean of the two pairwise agreements and is the value reported in Table 2 . All entries are percentages.

Framework operation	Median (ms)	P95 (ms)	Median (ms)	P95 (ms)
	Terminal Bench 2		$\tau^{3}$ Banking
Workspace initialization and configuration freeze	155.5	368.8	1229.3	1320.4
Candidate worktree and snapshot creation	756.2	2952.3	19.2	21.6
Mutable-surface validation	27.1	43.2	13.5	16.0
Evaluation stamp and archive update	32.4	69.8	10.8	14.9
State verification and champion recomputation	652.5	1482.2	108.4	113.8

Appendix

Table 5: Framework overhead by benchmark campaign. Operation latencies are in milliseconds. On Terminal Bench 2, the framework’s exclusive spans account for a median of 0.02% and a P95 of 0.06% of end-to-end generation time; on

\tau^{3}

Banking, they account for 0.019%.

Method	Recipe LOC	New operator LOC	Reused operators	Framework files changed	Integration tests
AHE	47	1087	2	0	47
Hyperagents	48	216	2	0	15
A-Evolve	57	684	2	0	14
GEPA	61	745	2	0	16

Appendix

Table 6: Method-integration effort under the shared recipe and operator interfaces.

Figure 2: Inspecting one RSIHub execution. The read-only viewer identifies the accepted Generation 8 candidate as champion, shows its lifecycle status and run-specific primary-split and sealed scores, places it in the generation lineage, and summarizes its cumulative target-tree changes. The displayed values describe this execution; aggregate performance is reported in Section 4 .

Stage	Mode	Primary input	Validated result and framework handling
Select	Req.	Archive view and execution context	Non-empty parent-generation list; the framework verifies eligibility and forks the recorded commit.
Rollout	Req.	Candidate checkout and context	Structured summary and artifact paths retained as mutation evidence.
Analyze	Opt.	Candidate checkout and context	Analysis summary and artifact paths bundled before mutation.
Mutate	Req.	Checkout, observation text, and context	Changed paths, notes, and usage metadata; the framework checks the actual tree diff against the declared surface.
Validate	Opt.	Mutated checkout and context	Acceptance flag, reason, and artifacts; rejection stops before protected evaluation.
Novelty	Opt.	Uncommitted checkout and context	Finite novelty score and acceptance flag; rejection stops before commit.

Appendix

Table 7: Lifecycle operator contracts. “Req.” denotes a registry-required operator and “Opt.” an operator enabled per recipe.

Layer	Recorded identity	Role
Candidate	Candidate commit and tree, generation, and optional dependency digest	Binds evidence to the evaluated source and relevant candidate dependencies.
Evaluator	Frozen evaluator tree, semantic configuration digest, and framework version	Makes evaluator changes visible in per-attempt provenance.
Data and trials	Dataset-content and task-set digests, ordered task members, split, repetitions, seed namespace, and trial identities	Makes task membership and multiplicity explicit.
Runtime and model	Runtime digest, agent and model names, endpoint digest, concurrency, and retry policy	Records execution conditions that can affect evidence collection.
Fixed comparison identity	Evaluator-tree fingerprint, task-set hash, and runtime fingerprint	Defines the cross-generation projection that a selectable parent must match.
Integrity receipt	Framework marker and hash receipt for the serialized evaluation event	Flags an event when its framework’s receipt is absent or no longer matches.

Appendix

Table 8: Evaluation identity and the parent-selection predicate.

Observed state	Recovery action	Preserved property
Active child worktree at run start	Stop and require the operator to preserve edits or invoke repair.	The in-progress candidate remains untouched.
Stale managed worktree	Repair removes only clean worktrees; dirty and externally managed worktrees are preserved and reported.	Cleanup is conservative with uncommitted work.
Generation tag without a certified evaluation	Evaluate the existing tagged commit instead of repeating selection and mutation.	Resumption retains the created candidate’s identity.
Complete evaluation pending Gate	Resume Gate from the tagged candidate, then attempt terminal Record; keep the row ineligible until the Gate decision.	Parent selection waits for Gate finalization.
Interrupted or terminally failed evaluation	Append available attempt evidence; require an explicit retry to create a new certified attempt.	Failed attempts remain auditable and retries are operator-controlled.
Terminal Record already attempted	Skip a duplicate Record invocation on recovery.	Each terminal Record is invoked at most once.

Appendix

Table 9: Checkpoint and recovery behavior.

Self-Evolving Agents

Self-evolving agents improve their skills, memory, tools, policies, or environments by learning from interaction and evaluation feedback.

See all 427 papers

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Jun 12, 2026Tingyang Chen, Shuo Lu, Kang Zhao +11LLM Agent Orchestration Agent Harness Optimization
Darwin Agent Team
PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins
Sep 26, 2026Yaorui Shi, Yuchun Miao, Yuxin Chen +5Agent Harness Optimization LLM Agent Harnesses
University of Science and Technology of China · Meituan · Wuhan University +1
ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
Sep 14, 2026Siwei Wu, Jincheng Ren, Yizhi Li +12Coding Agents Agent Harness Optimization
University of Manchester · IQuest Research · M-A-P +3

Jun 12, 2026J/K move · Enter open · S save

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Tingyang Chen, Shuo Lu, Kang Zhao, Weicheng Meng+10

Darwin Agent Team

LLM Agent Orchestration Agent Harness Optimization LLM Agent Workflow Optimization LLM Agent Self-Improvement LLM Agent Harnesses Self-Evolving Agents

Open paper AskPDF arXiv

AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

Abstract

Self-Evolving Agents

Explore similar work

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement