REVIEW 10 cited by
A Self-Improving Coding Agent
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent advancements in Large Language Models (LLMs) have spurred interest in deploying LLM agents to undertake tasks in the world. LLMs are often deployed in agent systems: code that orchestrates LLM calls and provides them with tools. We demonstrate that an agent system, equipped with basic coding tools, can autonomously edit itself, and thereby improve its performance on benchmark tasks. We find performance gains from 17% to 53% on a random subset of SWE Bench Verified, with additional performance gains on LiveCodeBench, as well as synthetically generated agent benchmarks. Our work represents an advancement in the automated and open-ended design of agentic systems, and demonstrates a data-efficient, non gradient-based learning mechanism driven by LLM reflection and code updates.
Forward citations
Cited by 10 Pith papers
-
VeRO: A Harness for Agents to Optimize Agents
VeRO supplies a versioned harness, benchmark suite, and empirical comparison of optimizer configurations for coding agents that improve other agents.
-
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
A new benchmark, HarnessOpt-Bench, measures how well frontier LLMs can improve the prompts, tools, and control flow of target agents under a fixed evaluation budget with a held-out test set.
-
Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents
When agents co-edit policies and self-tests, self-scores stay high while deployment fails; a sealed exogenous non-regression audit (SEAL) reliably reduces those regressions.
-
Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark Coevolution
A verifier-grounded self-evolving Lean proof agent with a champion-driven, self-hardening benchmark reached 45.1% held-out miniF2F solve rate versus 32.0% for a fixed-benchmark baseline.
-
LOGOS: A Living Logic for AI Agent Teams That Evolve With Humans
LOGOS makes multi-agent self-evolution governable by compiling inputs into versioned Agent Packs and promoting only candidates that pass held-out evidence, root policy, and human authorization.
-
HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
HarnessX composes typed harness components, evolves them from execution traces via a four-stage meta-agent pipeline, and jointly fine-tunes the agent model, reporting +14.5% average peak gains on five benchmarks (vali...
-
A global log for medical AI
MedLog defines a nine-field, syslog-style event log for clinical AI, intended to support real-world surveillance and auditing; the four-deployment validation claimed in the abstract is absent from the body.
-
Exploring the Challenges and Opportunities of AI-assisted Codebase Generation
Developers prompting codebase-level AI assistants are often dissatisfied with generated code, citing missing functionality, poor code quality, and communication gaps, despite varied prompting strategies.
-
Code Is the Body: Agent-Owned Software Bodies for Recursive Evolution and Descent
OurArk makes a personal agent's code, prompts, and policies into a versioned body under user control, enabling governed self-evolution and recursive descent into new agent instances.
-
Prompts Blend Requirements and Solutions: From Intent to Implementation
Prompts in AI-assisted development can be decomposed into functionality/quality, general solutions, and specific solutions — the 'Prompt Triangle' framework.
Discussion (0). Sign in to comment.