Humans often learn fastest not by repeating success, but by remembering which failures not to repeat. Open-ended self-improving agents can share experience across lineages, as in GEA, or edit their own improvement mechanisms, as in DGM-Hyperagents, yet failed improvement attempts are rarely retained as reusable cross-branch knowledge, and search can collapse onto redundant strategies. We introduce MetaShare, a failure-aware framework that records successful and unsuccessful agent modifications together with signed performance deltas. Before each generation, MetaShare retrieves diverse high-performing strategies alongside high-confidence failures from other lineages, letting agents reuse effective mechanisms while avoiding known dead ends. A task-blind auditor periodically injects absent or underrepresented mechanism categories, while embedding-based de-ranking limits redundancy during retrieval. Multiple meta-agents propose modifications in parallel at heterogeneous temperatures behind a deterministic selector that gates applicability, scope, compilability, and size. Experiments across paper review, coding, math grading, robotics reward design, and financial audit-risk assessment show that MetaShare's median matches or exceeds DGM-Hyperagents' final performance and reaches its own best-performing agent in 1.7--2.9× fewer evolution iterations.
Figures & tables
Figure 1: MetaShare converts evaluated outcomes into signed, reusable lessons. A measured scaffold change becomes a positive (helped, reuse) or negative (hurt, avoid) lesson, passed to generation t+1 to exploit gains and skip known failures.
Figure 2: MetaShare architecture. Top : one generation—select parent ap , build the signed-guidance context Cg (adopt/avoid/must-try), let K meta-agents propose patches, admit one through a deterministic gate, then apply and score it to yield ac . Bottom : each evaluated modification becomes a signed record in a bounded cross-lineage pool; failure-aware diverse retrieval rebuilds Cg , and a task-blind auditor injects Must-Try classes from a scrubbed digest.
Figure 3: MetaShare vs. DGM-H across all evaluation domains. Left : final score ( ↑ ); right : generation of the selected best ( ↓ ), with per-domain speed-up. Error bars are 95% bootstrap CIs where available. DGM-H values for paper review, robotics, and IMO (scores, intervals, and generations) are as reported by Zhang et al. (2026) , not rerun; the Polyglot and audit-risk DGM-H bars are our five-run reimplementation. Dashed lines mark the static, no-self-improvement baseline ( Zhang et al., 2026 ; Luong et al., 2025 ) (none for Polyglot or audit risk). NMAE ( ↓ ) is 0.175 vs. 0.157 (IMO-full) and 0.357 vs. 0.312 (audit risk). For Polyglot both arms hold the task-agent on o3-mini here, with the DGM-H baseline rerun on a Sonnet-4.5 meta-agent (Sonnet-3.5 deprecated); Sec. 5.2 analyzes model-routing separately.
Domain (budget)
DGM-H
Ours
Ratio
Paper Review (100)
83M
52M
0.6×
Polyglot (100) †
135M
163M
1.2×
IMO-grading (200)
88M
213M
2.4×
Table 1: Estimated total token count (millions, input + output), MetaShare (Ours) vs. the DGM-H baseline, following DGM-H’s protocol ( Zhang et al., 2026 ) . Baseline self-modification is DGM-H’s reported estimate ( ∼ 33M tokens per 100 iterations, scaled to each budget); totals are medians over five runs to the selected checkpoint; Ratio is Ours / baseline. † Polyglot baseline re-measured on the matching model (Claude 4.5) for parity.
Configuration
Train
Val
Gens ↓
Success only
0.68 [.68,.69]
0.69 [.69,.72]
63
+ failure ( k=1 )
0.70 [.69,.70]
0.73 [.72,.74]
60
+ parallel ( k=3 )
0.77 [.76,.79]
0.78 [.76,.83]
48
+ auditor (full)
0.81 [.79,.83]
0.83 [.80,.88]
36
Pool disabled, k=3
0.70[.70,.71]
0.72 [.72,.73]
55
Table 2: Component ablation on paper review: best-so-far accuracy (median over five paired runs; 95% bootstrap CI) on train and validation—also the checkpoint-selection split—and generations-to-best on validation (Gens ↓ ). The first four rows add one component at a time; the last is the compute-matched reference, with the pool disabled at the full system’s proposal count ( k=3 ).
Configuration
Accuracy
Gens ↓
w/o auditor
0.30 [.30,.31]
80
Shuffled failures
0.38 [.37,.39]
65
Full ( k=3 , hetero temps)
0.45 [.44,.46]
42
Pool disabled, k=3
0.28 [.28,.30]
100 †
Table 3: Single-component removals from full MetaShare on the 225-task Polyglot benchmark (median over five runs, 95% bootstrap CI; Gens ↓ = generations to best). The last row is the compute-matched reference—pool disabled at k=3 —which lands on the k=1 DGM-H baseline. All arms start from GPT o3-mini. † Best reached at the end of the 100-generation budget, so a lower bound.
Appendix figures & tables14 assets
Supplementary material from the paper’s appendix.
Appendix
Parameter
Value
Role
C
10 generations
cadence of the task-blind audit; an audit also requires at least five records in the pool
Pool bound
100 records
capacity of the strategy pool; on overflow the records with the largest ∣δi∣ are retained, so the strongest positive strategies and the most informative failures both survive eviction
Ks
5
positive retrieval budget
Kf
5
failure retrieval budget
Token budget
20k
approximate size of the retrieved context
Embedding model
text-embedding-ada-002
embeds each record for the de-ranking step
Appendix
Table 4: Memory and retrieval settings that take the same value in every domain
Domain
γ
τ
K
θ
Paper review
0.0
0.92
3
[0.0,0.35,0.7]
Polyglot coding
0.4
0.92
3
[0.0,0.45,0.75]
IMO grading
0.0
0.85
3
[0.0,0.35,0.75]
Robotics reward
0.0
0.85
3
[0.0,0.35,0.75]
Audit risk
0.0
0.85
3
[0.0,0.3,0.7]
Appendix
Table 5: Per-domain settings: the staged-evaluation threshold γ , the de-ranking threshold τ , the number of parallel meta-agents K and their decoding temperatures θ , as recorded in the run metadata
Setting
Value
Audit model
Claude Sonnet-4.5
Temperature
0.0
Max output tokens
8000
Pool entries per audit
up to 56; a per-call cap on the size of the digest, below the pool bound of Table 4
Diff truncation
2500 characters per entry, added lines only
Requested output
numbered list of 6–10 mechanism categories
Appendix
Table 6: Auditor configuration.
Label
Definition
prompt_engineering
Changes to system prompts, instructions, or personas
tool_creation
Adding new tools or capabilities
memory_system
Adding performance tracking, history, or knowledge bases
evaluation_logic
Changes to how the meta agent evaluates performance
self_modification
Meta agent changing its own improvement logic
structural_refactor
Reorganizing code without functional change
Appendix
Table 7: The fixed mechanism-type vocabulary. Every record carries exactly one of these six labels.
Function
Returns
Passes when
scope_ok(diff)
{0,1}
the diff modifies at least one allowed file
applies(diff, repo)
{0,1}
git apply --check succeeds against the parent repository, i.e. the patch is applicable without altering the working tree
compiles_after(diff, repo)
{0,1}
the allowed files, copied into a scratch repository with the diff applied, all pass python -m py_compile
size_band(diff)
{0,1}
added plus removed lines fall within [MIN_LINES_CHANGED,MAX_LINES_CHANGED]
Appendix
Table 8: The four axes of the admissibility gate.
Component
Specification
CPU nodes
5× Azure Standard D8as v5: 8 vCPU, 32 GiB memory, 2 threads per core
GPU nodes
5× Azure Standard NC8as T4 v3: 8 vCPU, 56 GiB memory, 1 thread per core, NVIDIA T4
Operating system
Linux, Ubuntu 24.04 LTS
Python
3.12.3
Container runtime
Docker; each of the K parallel proposals runs in its own container and repository copy, and each domain evaluation runs in its own container
Table 9: Computing infrastructure used for the reported experiments.
#
Inherent Risk Factor
Definition
1
Account nature
Whether the account is routine and recurring, or unusual and non-recurring.
2
Misstatement history
Whether the account has a history of proposed or booked audit adjustments.
3
Fraud indicators
Whether fraud risk factors, or prior instances of fraud, are present in the account.
4
Control deficiency history
Whether significant deficiencies or material weaknesses have historically related to the account, as opposed to lesser or no identified deficiencies.
5
Transaction volume and value
The number of transactions processed through the account and their monetary magnitude.
6
Transaction complexity
How complex the transactions processed through the account are.
Appendix
Table 10: Definitions of the 15 Inherent Risk Factors (IRFs).
Split
Clients
High
Medium
None
Total
Train
8
457
420
2344
3221
Validation
2
132
127
506
765
Test
5
130
105
675
910
Total
15
719
652
3525
4896
Appendix
Table 11: Class balance of the audit-risk labels by split. Each count is one labelled assessment of a single account group against a single factor.
DGM-H
MetaShare
Run
Gens
Accuracy
NMAE
Gens
Accuracy
NMAE
1
46
0.448
0.309
30
0.512
0.342
2
42
0.445
0.366
24
0.544
0.305
3
44
0.450
0.370
26
0.550
0.309
4
45
0.452
0.371
27
0.553
0.302
5
43
0.456
0.369
25
0.560
0.302
Appendix
Table 12: Audit-risk results per run on the held-out test split. Accuracy is aggregated as the median over runs and NMAE as the mean, as described above; lower NMAE is better.
Risk factor
DGM-H
MetaShare
Δ
Account nature
0.10
0.06
−0.04
Misstatement history
1.00
1.00
+0.00
Fraud indicators
0.04
0.57
+0.53
Control deficiency history
1.00
1.00
+0.00
Transaction volume and value
0.30
0.05
−0.25
Transaction complexity
0.01
0.15
+0.14
Appendix
Table 13: Accuracy per risk factor on the held-out test split, as the median over five runs. Δ is MetaShare minus DGM-H.
Run
Best accuracy
Generations to best
1
0.902
8
2
0.907
9
3
0.912
10
4
0.917
10
5
0.922
10
Median
0.912
10
Appendix
Table 14: Per-run Polyglot results on the small+medium set (60 tasks), with Claude Sonnet-4.5 as both task- and meta-agent, matching the GEA configuration. “Generations to best” is the iteration at which the reported score first appears.
Figure 4: Best score so far against evolution iteration on the 60-task small+medium Polyglot subset. The MetaShare curve is the best of our five runs, ending at 0.922 ; the median over the five is 0.912 (Table 14 ). The DGM and GEA curves are digitised from the published figure in Weng et al. (2026) : plateau levels and the iterations at which they begin were read off the plot, so they are approximate and indicate shape rather than exact values. Dashed line: reported open-source state of the art. Note that the initialisations differ—both baselines begin from an agent already scoring ≈0.38 , whereas MetaShare begins from an agent that solves nothing.
Run
DGM-H
MetaShare
Δ
1
21
27
+6
2
22
26
+4
3
21
27
+6
4
22
27
+5
5
21
24
+3
Median
21
27
+6
Appendix
Table 15: Cumulative unique Polyglot tasks solved per run, out of the 60-task small+medium subset, over a matched 100-generation budget.
Mechanism type
Gen. 1–19 (pre-audit)
Gen. 20–24 (post-audit)
evaluation_logic
12
1
prompt_engineering
7
0
tool_creation
0
1
structural_refactor
0
1
memory_system
0
0
self_modification
0
0
Appendix
Table 16: Mechanism types in the pool of one Polyglot run that begins on GPT o3-mini, before and after the generation-20 audit fired. Types are assigned by the post-hoc classifier of Sec. B.6 ; the six available types are listed in Table 7 .
Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavior. Yet agents increasingly operate alongside peers whose strategies and outcomes are publicly visible. This raises an under-studied question: when does shared experience produce improvements that self-improvement alone cannot achieve? We introduce SAGE (Social Agent Group Evolution),an evaluation framework that compares two compute-matched conditions: SocialEvo, where agents from five distinct model families co-evolve with access to all peers' histories; and SelfEvo, where each agent receives the same number of task attempts but sees only its own past, which is conventional in self-improving agent studies. We instantiate SAGE in three arenas: open-ended ML research, long-horizon economic planning, and strategic multiplayer play, evaluated across multiple evolutionary rounds. We find that group history is not a universal amplifier: the strongest agent does not exceed its self-evolution ceiling. However, agents that plateau under self-improvement can achieve significant breakthroughs when peer experience is available. In competitive settings, counterfactual controls reveal that agents improve generally rather than developing opponent-specific strategies. Across different forms of shared history, filtered peer traces and reflective summaries often outperform raw logs, indicating that social gains depend on abstraction rather than exposure volume. These findings reveal that peer-history gains are agent-specific, arena-dependent, and contingent on the capacity to abstract transferable knowledge from public traces.
Self-evolving agents improve their performance on long-horizon tasks by learning from their own interactions with an environment. A common approach uses the resulting failed trajectories as negatives for preference training. However, collecting an agent's own failures does not ensure that they provide informative supervision for further improvement. Obvious failures may be easy to reject without learning to identify errors in more plausible attempts. These plausible but incorrect trajectories can serve as hard negatives, helping agents learn to distinguish successful behavior from failures with less obvious errors. To enable agents to generate and learn from such informative negatives, we propose a co-evolving framework that couples a target agent's self-improvement with a failure agent trained to generate hard negatives. The failure agent learns exclusively from both agents' failed trajectories to generate higher-reward failures, which the target agent uses as negatives for preference training. As the target policy improves, its failures provide new training data for the failure agent. The updated failure agent, in turn, provides new negatives for target training, allowing negative generation to adapt alongside the target policy. Across online shopping, scientific reasoning, and interactive SQL querying, our framework improves average task reward by 5.7 over the baseline. These results demonstrate the value of learning to generate and use informative failures for agent self-improvement. We will make our code publicly available.
Yeonsung Jung, Trilok Padhi, Sina Shaham +4
KAIST · Georgia State University · Independent Researcher +2
As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills directly act on task execution, whereas Meta-Skills govern how agents discover and improve future Skills; their value therefore emerges through the subsequent search processes they induce. Existing approaches improve Meta-Skills from observed raw Skill-search trajectories and branch outcomes. However, branch performance entangles the effects of the initial discovery state and the Meta-Skill revision that generated the search process, making it difficult to characterize what a particular revision actually changed, and pushing updates toward revisions that benefit from favorable states rather than those that improve the process. We introduce HMED (Hindsight Meta-Experience Distillation), a mechanism for constructing Meta-Experience for self-improving agents. HMED revisits the completed event from which a revision originates and re-executes the incumbent and revised Meta-Skills from the same restored discovery state, so that the changes associated with the revision can be observed under a shared condition. Each comparison is distilled into a Meta-Experience, a structured record that can be reused by future updates, so that even revisions that are not ultimately retained still contribute a learning signal. Across three interactive agent benchmarks and both open-source and closed-source models, HMED consistently improves Skill discovery performance over strong baselines, shifting Meta-Skill learning beyond branch outcomes toward the consequences of changing the improvement process.
Qianhan Feng, Zhongzhen Huang, Yakun Zhu +2
The Chinese University of Hong Kong · Shanghai Jiao Tong University · Shanghai Innovation Institue