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, Chaofan Wang, Kai Wu, Mengnan Qi, Kai Cai, Xiaodong Gu, Zilong Zheng
Organizations: University of California, Berkeley · Shanghai Jiao Tong University · University of Science and Technology of China · Beijing Institute for General Artificial Intelligence · Douyin Group · Simple Agent Lab · Tongji University
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 τ3 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 τ3 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
Direct
RSIHub
Δ
D–D
D–R
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
τ3 Banking
MiniSWE
24.6
22.0
−2.6
81.1
80.9
+0.2
τ3 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.
Terminal Bench 2
τ3 Banking
Class
Scenario
Required invariant
Correct
Median (s)
Correct
Median (s)
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
τ3 Banking
MiniSWE
82.1
79.7
80.9
τ3 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.
Terminal Bench 2
τ3 Banking
Framework operation
Median (ms)
P95 (ms)
Median (ms)
P95 (ms)
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 τ3 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.
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.
The harness surrounding a language model is a central determinant of agent performance. Recent methods optimize harnesses by searching over complete programs, where individual mechanisms are difficult to isolate and reuse. We introduce PluginRSI, which represents a harness as a composition of atomized plugins and organizes harness evolution around these plugins. Individual plugins are improved independently and accumulated in a shared library, then recombined into new harnesses at each iteration. PluginRSI improves over existing harness optimization methods across software engineering, command-line interaction, and question-answering tasks. The resulting harnesses retain their advantage when transferred to other solver models without further optimization. The evolved plugin library accelerates subsequent optimization from the initial harness, which helps faster and higher convergence on unseen tasks. These results show that accumulating reusable mechanisms provides an effective basis for continued harness improvement.
Yaorui Shi, Yuchun Miao, Yuxin Chen +5
University of Science and Technology of China · Meituan · Wuhan University +1
Recent work extends recursive self-improvement (RSI) to agent harnesses for long-horizon coding and terminal tasks, enabling agents to improve execution mechanisms from experience. However, generalizable harness RSI remains challenging. First, evolving harnesses on evaluation benchmarks or their subsets makes it difficult to distinguish reusable improvements from benchmark-specific adaptation. Second, single-trajectory updates can conflate systematic harness deficiencies with instance-specific reasoning and solution details, producing modifications that transfer poorly to unseen tasks. Third, localizing recurring behavioral deficiencies within monolithic harnesses is difficult, while whole-harness optimization can entangle unrelated mechanisms and complicate attribution and validation. We propose ModularRSI, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution. ModularRSI contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies. It decomposes the evolvable harness into five functional modules: Agent Loop, Tool Use, Observation Management, Context Management, and Task Completion Detection. Each module evolves independently within a restricted modification scope, followed by an integration stage that combines the evolved modules into a unified harness and resolves potential conflicts. To support benchmark-disjoint evolution, we curate 2,000 executable evolution tasks from external sources that are disjoint from downstream evaluation benchmarks. Experiments on TB2.0 and SWE-Bench Verified show consistent improvements on unseen in-domain and cross-domain tasks, with the evolved harness also transferring across different foundation models.
Siwei Wu, Jincheng Ren, Yizhi Li +12
University of Manchester · IQuest Research · M-A-P +3