Beancount.io LogoBeancount.io

33 tagged with "Plain-Text Accounting"

Research grounded in plain-text accounting formats and workflows

View all tags

MemGPT: Virtual Context Management for LLM Agents
·mike

MemGPT: Virtual Context Management for LLM Agents

MemGPT applies OS-style virtual memory paging to LLMs, using three-tier storage — working memory, recall, and archival — to give agents persistent recall across sessions; on multi-session chat benchmarks, MemGPT with GPT-4 achieves 92.5% accuracy versus a 32.1% fixed-context baseline.

ai
llm
machine-learning
automation
+4
SWE-agent: How Interface Design Unlocks Automated Software Engineering
·mike

SWE-agent: How Interface Design Unlocks Automated Software Engineering

SWE-agent (NeurIPS 2024) introduces Agent-Computer Interfaces (ACIs) — purpose-built layers between LLMs and software environments — showing a 10.7-percentage-point improvement over raw shell access and 12.47% resolution on SWE-bench with GPT-4 Turbo. Interface design, not model capability, is the primary bottleneck for autonomous coding agents.

ai
llm
automation
machine-learning
+4
SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
·mike

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

SWE-bench evaluates language models on 2,294 real GitHub issues across 12 Python repositories using execution-based tests; at publication, Claude 2 resolved only 1.96% of issues with realistic retrieval, establishing the de facto benchmark for coding agents and revealing retrieval and patch-length failure modes directly relevant to Beancount write-back agents.

ai
llm
machine-learning
beancount
+3
CodeAct: Why Executable Python Code Makes LLM Agents 20% More Accurate
·mike

CodeAct: Why Executable Python Code Makes LLM Agents 20% More Accurate

CodeAct (ICML 2024) replaces JSON tool-calling with executable Python code, improving GPT-4 agent success rates by ~20 percentage points on multi-tool tasks and reducing interaction turns by 30% — with direct implications for building reliable Beancount reconciliation agents.

ai
llm
automation
machine-learning
+3
Tree of Thoughts: Deliberate Problem Solving with LLM Search
·mike

Tree of Thoughts: Deliberate Problem Solving with LLM Search

Tree of Thoughts (ToT) achieves 74% on Game of 24 vs 4% for standard GPT-4 CoT by organizing LLM reasoning into a branching search tree with pruning and backtracking — with direct implications for multi-step financial classification and tax optimization in Beancount workflows.

ai
llm
machine-learning
automation
+2
Reflexion: Language Agents That Learn from Mistakes Without Retraining
·mike

Reflexion: Language Agents That Learn from Mistakes Without Retraining

Reflexion (NeurIPS 2023) lets LLM agents improve by storing verbal post-mortems in an episodic buffer — no weight updates required. It reaches 91% on HumanEval with GPT-4 but fails on WebShop, revealing a structural constraint: verbal reinforcement only works when the evaluator produces a crisp, actionable signal. Here is what that means for building a self-correcting Beancount ledger agent.

ai
llm
machine-learning
automation
+2
Can LLMs Reason Over Tabular Data? What Four Benchmarks Tell Us About Finance AI
·mike

Can LLMs Reason Over Tabular Data? What Four Benchmarks Tell Us About Finance AI

Four 2024–2025 benchmarks show GPT-4 scoring 42% on real-world table QA versus 86% for humans, with complex aggregations collapsing to 19.6%—and Beancount's native syntax sits at the worst-performing end of the serialization hierarchy for LLM input.

ai
llm
beancount
data-science
+3
ReAct: Synergizing Reasoning and Acting in Language Models
·mike

ReAct: Synergizing Reasoning and Acting in Language Models

ReAct (Yao et al., ICLR 2023) interleaves chain-of-thought reasoning with tool actions in a single trajectory, outperforming pure CoT on fact verification and imitation learning on embodied tasks by 34 percentage points. This analysis covers the paper's failure modes — search-induced distraction and compounding errors — and what they mean for autonomous agents writing back to Beancount ledgers.

ai
llm
machine-learning
automation
+3
Toolformer: Self-Supervised Tool Use and Its Limits for Finance AI
·tian

Toolformer: Self-Supervised Tool Use and Its Limits for Finance AI

A close reading of Toolformer (Meta AI, NeurIPS 2023): how perplexity-filtered self-supervised training teaches a 6.7B-parameter model to call external APIs, where it outperforms GPT-3 175B on arithmetic benchmarks, and why its single-step architecture cannot support the chained tool calls required for structured ledger operations.

ai
llm
machine-learning
automation
+4
Showing 25–33 of 33 posts
Prev3 / 3