paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 2mo ago
Self-rewarding agents that retrace failures
Agents that attribute their own errors and retrace to repair multi-step reasoning.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownretrace-agents →
- LinkedLinked via unknownAgentTrace →
- FuzzySimilar title/name (fuzzy) · 87%Retrace-1.5B →
“Fuzzy title match (0.94): “Self-rewarding agents that retrace failures” ≈ “Retrace-1.5B””
- PossiblePossibly related (embedding) · 28%julep-ai/julep →
“Possibly related via embedding similarity 0.56 (not asserted). Timestamp check: artifact after paper (+16d).”
- LinkedLinked via unknownProduction-grade AI agents for financial compliance: Lessons from Stripe →
- LinkedLinked via unknownI made a superhuman Generals.io agent with self-play RL [P] →
- LinkedLinked via unknownAI coding agents taught robots how to install GPUs and cut zip ties →
- LinkedLinked via unknownHow agents are transforming work →
Implements
Related to
Has model
Covers (incoming)
Related to (incoming)
Implements (incoming)
Related across the graph
repotomasz-tomczyk/critrepoEigenwise/atomic-agentscompanyNorthwind AInewsAI coding agents taught robots how to install GPUs and cut zip tiesrepobug-ops/zephrepoAgentToolkit/altk-evolvereposnomiao/agent-yesrepoTauricResearch/TradingAgentsnewsHow agents are transforming workrepojulep-ai/juleprepojnMetaCode/agency-agents-zhrepodatawhalechina/hello-agentsmodelRetrace-1.5BnewsI made a superhuman Generals.io agent with self-play RL [P]reporetrace-agentsrepoOpen-Curiosity/gini-agentrepoUnity-Technologies/ml-agentsrepoNirDiamant/GenAI_AgentsarticleRetrieval is underratednewsProduction-grade AI agents for financial compliance: Lessons from StripetoolAgentTrace