GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge

• URL: http://arxiv.org/abs/2606.14470v1
• Date: Fri, 12 Jun 2026 14:02:37 GMT
• Title: GitOfThoughts: Version-Controlled Reasoning and Agent Memory You Can Replay, Diff, and Merge
• Abstract summary: We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository.<n>Every scored thought is a commit, scores are notes, outcomes are tags, and retrieval is "git log" over the agent's own history.<n>This makes reasoning replayable, auditable, and mergeable across agents at near-zero engineering cost.
• Score: 0.02066679446411895
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) reasoning is ephemeral: chains of thought vanish with the context window, pruned search branches leave no record, and memory buffers cannot be diffed, merged, or audited. Every other complex software process (code, infrastructure, data, experiments) is version-controlled; reasoning is not. We introduce GitOfThoughts, which stores an agent's reasoning tree as a git repository: every scored thought is a commit, scores are notes, outcomes are tags, and retrieval is "git log" over the agent's own history. This makes reasoning replayable, auditable, and mergeable across agents at near-zero engineering cost. We then ask the harder question: does memory, in any substrate, actually improve accuracy? Across five substrates (none, markdown, vector, graph, git), two benchmarks, two model scales, and pre-registered replications, the answer for novel problems is no. No memory format reliably helps, and a promising early result collapsed under its own pre-registered replication. Memory pays only above what we call the copyability threshold: when the retrieved case is a near-duplicate of the current problem (similarity >~ 0.8), accuracy jumps sharply; below it, nothing. The gain is answer retrieval, not method transfer: a 4.5x larger model doubles the near-duplicate payoff yet still cannot extract a transferable method from a worked example. The only general lever we find is test-time sampling. The case for git-as-substrate is therefore auditability, provenance, and mergeability at accuracy parity. We document a retracted result and a refuted hypothesis to model the evaluation standard we hold ourselves to.

Related papers

• Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization [31.31831511580543]
  We introduce Belief-Calibrated Optimization (BCO), a method that writes that belief down as a persistent in-context document.<n>A fresh predictor given the accumulated document forecasts how the environment will respond more accurately than given either no document or a same-form copy whose content has been falsified.
  arXiv  Detail & Related papers  (2026-09-01T20:47:04Z)
• Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework [49.16055123488827]
  coding agents powered by large language models can now generate code patches directly from bug reports.<n>No mechanism independently verifies whether it truly resolves the reported problem.<n>We propose RETRACE, a training-free post-generation verification framework.
  arXiv  Detail & Related papers  (2026-08-09T22:59:13Z)
• CrossAudit: A Git-Native, Cross-Vendor Audit Loop for Agentic Science [5.610929955077264]
  CrossAudit is a protocol for supervising autonomous research pipelines.<n>Each increment of work is audited by an agent from a different vendor against a rulebook a human wrote and versioned.<n>Reports, verdicts, disputes and rulings are git commits, so the supervision history can be re-read and cited.
  arXiv  Detail & Related papers  (2026-08-05T12:35:59Z)
• Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability [49.415740364852105]
  Deployed agents increasingly keep their long-term memory as a directory tree of markdown files that the agent itself reads, writes, and reorganizes through generic file tools.<n>Prior systems design bespoke memory representations and study retrieval over them, leaving the default's two working assumptions untested.<n>We present the first systematic exploration of chunk-based memory for LLM agents.
  arXiv  Detail & Related papers  (2026-07-29T08:59:43Z)
• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
  Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
  arXiv  Detail & Related papers  (2026-07-23T04:34:06Z)
• Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data [4.191965713559235]
  Coding agents can now be left alone to improve software against a score.<n>In this pattern, the agent receives a dataset, an evaluation script, and one editable file, and iterates without supervision.<n>We ran this loop on a real production task: deciding which Quranic verses appear in a noisy speech-recognition transcript.
  arXiv  Detail & Related papers  (2026-07-20T15:32:09Z)
• Why Git Is the Memory Solution for the Agentic Development Lifecycle [0.0]
  We argue memory should be git-bound, built into the repository's version control.<n>On this ledger we solve two problems separately, then combine them.<n>A router dispatches breadth to a git-anchored structural map, pointed lookups to confidence-gated episodes, and rationale to decision synthesis.
  arXiv  Detail & Related papers  (2026-07-15T22:06:59Z)
• Can Code Specify a System Precisely Enough to Formally Verify It? [0.0]
  This paper evaluates both on production software: the payment workflow of an operational restaurant point-of-sale system.<n>The core protocol is correct relative to a hand-built, line-cited model under a precisely stated failure model.<n>A single probe of the production payment sandbox exposed a response-shape divergence that makes an entire recovery ladder unreachable.
  arXiv  Detail & Related papers  (2026-07-06T13:39:00Z)
• Echo-Memory: A Controlled Study of Memory in Action World Models [58.77172260403133]
  We present a controlled study of memory mechanisms in action-conditioned world models.<n>Existing memory designs are hard to compare because gains are entangled with backbone, training, retrieval, and evaluation differences.<n>We use Echo-Memory to fix the action-to-video interface and varies only how history is stored and read by the generator.
  arXiv  Detail & Related papers  (2026-06-08T17:54:10Z)
• CommitDistill: A Lightweight Knowledge-Centric Memory Layer for Software Repositories [0.5872014229110213]
  Software accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads.<n>Recent work on typed-memory architectures for agents (MemGPT, generative agents, and the PlugMem module of Yang et al.) argues that agent memory should be distilled, typed knowledge rather than raw interaction text.<n>We adapt that stance to a software repository's own git history under a constrained regime: deterministic, dependency-free, local-only, no embeddings.
  arXiv  Detail & Related papers  (2026-05-18T12:14:28Z)
• Fine-grained Multi-Document Extraction and Generation of Code Change Rationale [9.038241584076468]
  We study how rationale components (e.g., a change's goal, need, and alternative) are distributed across artifacts.<n>We introduce ARGUS, an LLM-based approach that identifies sentences expressing goal, need, and alternative across a commit's artifacts.
  arXiv  Detail & Related papers  (2026-04-11T20:49:36Z)
• Lore: Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding Agents [0.0]
  This paper proposes Lore, a lightweight protocol that restructures commit messages into self-contained decision records.<n>Lore requires no infrastructure beyond git, is queryable via a standalone CLI tool, and is discoverable by any agent capable of running shell commands.
  arXiv  Detail & Related papers  (2026-03-16T17:27:30Z)
• From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents [26.35084166166742]
  TierMem casts retrieval as an inference-time evidence allocation problem.<n>On LoCoMo, TierMem achieves 0.851 accuracy while reducing input tokens by 54.1% and latency by 60.7%.
  arXiv  Detail & Related papers  (2026-02-20T00:21:37Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Learning Refined Document Representations for Dense Retrieval via Deliberate Thinking [58.69615583599489]
  Deliberate Thinking based Retriever (Debater) is a novel approach that enhances document representations by incorporating a step-by-step thinking process.<n>Debater significantly outperforms existing methods across several retrieval benchmarks.
  arXiv  Detail & Related papers  (2025-02-18T15:56:34Z)
• Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls [83.89771461061903]
  Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>Recent advancements in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs)<n>We identify two key challenges contributing to this inefficiency: $textitover-exploration$ due to redundant states with semantically equivalent content, and $textitunder-exploration$ caused by high variance in verifier scoring.<n>We propose FETCH, a flexible, plug-and-play system compatible with various tree search algorithms.
  arXiv  Detail & Related papers  (2025-02-16T16:12:01Z)
• Fact Checking Beyond Training Set [64.88575826304024]
  We show that the retriever-reader suffers from performance deterioration when it is trained on labeled data from one domain and used in another domain. We propose an adversarial algorithm to make the retriever component robust against distribution shift. We then construct eight fact checking scenarios from these datasets, and compare our model to a set of strong baseline models.
  arXiv  Detail & Related papers  (2024-03-27T15:15:14Z)
• Delving into Commit-Issue Correlation to Enhance Commit Message Generation Models [13.605167159285374]
  Commit message generation is a challenging task in automated software engineering. tool is a novel paradigm that can introduce the correlation between commits and issues into the training phase of models. The results show that compared with the original models, the performance of tool-enhanced models is significantly improved.
  arXiv  Detail & Related papers  (2023-07-31T20:35:00Z)
• ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation [106.04777600352743]
  Differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. The single-path DARTS comes in, which only chooses a single-path submodel at each step. While being memory-friendly, it also comes with low computational costs. We propose a new algorithm called RObustifying Memory-Efficient NAS (ROME) to give a cure.
  arXiv  Detail & Related papers  (2020-11-23T06:34:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.