Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes

• URL: http://arxiv.org/abs/2607.13071v1
• Date: Sat, 11 Jul 2026 07:45:13 GMT
• Title: Compaction as Epistemic Failure: How Agentic LLM Tools Fabricate Confirmed Results from Killed Processes
• Abstract summary: This paper documents a failure mode in Claude Code where partial standard output from timed-out commands (exit code 143) is recorded in compaction summaries as confirmed results.<n>The underlying mechanism is a conflation of observation and persistence, where information that appeared in the terminal is treated as equivalent to information written to durable storage.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Agentic LLM coding tools compress long session histories into compaction summaries that subsequent sessions inherit as ground truth. This paper documents a failure mode in Claude Code where partial standard output from timed-out commands (exit code 143) is recorded in compaction summaries as confirmed results, propagating false positives across sessions and model versions without re-verification. The underlying mechanism is a conflation of observation and persistence, where information that appeared in the terminal is treated as equivalent to information written to durable storage. This finding extends the analysis of LLM self-evaluation failures reported in prior work on non-determinism in LLM-as-judge grading by showing that agentic tools exhibit analogous reliability deficits when reporting on their own operational outcomes. The failure has direct implications for any workflow that relies on agentic session continuity for data processing, scientific computation, or multi-step automation.

Related papers

• Automata from Agent Traces: Failure and Next-Step Prediction [1.16693435589939]
  We collapse an entire trace corpus into a single, compact finite-state machine (FSM) that serves as a structural substrate for the behavior of LLM agents.<n>For failure prediction, per-state behavioral features reach held-out AUROC up to 0.94, and an online monitor ranks failing runs above passing ones.
  arXiv  Detail & Related papers  (2026-08-24T17:58:01Z)
• From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents [75.69180947909148]
  We propose a trajectory-level UQ framework for large language model (LLM) agents.<n>RuPA represents an execution history as a directed trajectory graph in which reasoning states, tool interactions, and environment feedback are nodes connected by temporal and semantic dependency edges.<n>We evaluate RUPA on representative agent benchmarks, including $$-2, Terminal-Bench-2, and GAIA, using 6 open-source LLMs spanning multiple model families.
  arXiv  Detail & Related papers  (2026-08-17T01:40:14Z)
• A Mechanistic Lens on Semantic Conflicts: Using Activation Patching to Understand LLM Behavior [7.506391522879222]
  We present the first controlled, mechanistic study of large language models (LLMs) behavior under semantic conflicts.<n>We evaluate four open-weight LLMs on two tasks (output prediction and unit-test generation) using behavioral performance measures.<n>Our results show that semantic conflicts significantly reduce execution-grounded correctness in both tasks.
  arXiv  Detail & Related papers  (2026-07-06T19:35:04Z)
• Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints [37.92327096151557]
  This paper reports reproducible phenomenon observed in a production Agent system.<n>Multiple open-weight models cease invoking tools despite maintaining high schema compliance.<n>We propose Transparent Two-Execution, an inference-time strategy that decouples tool execution from schema-constrained response generation.
  arXiv  Detail & Related papers  (2026-06-24T09:14:18Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis [0.8193467416247519]
  Review and meta-analyses rely on converting narrative articles into structured, numerically grounded study records.<n>Despite rapid advances in large language models (LLMs), it remains unclear whether they can meet the structural requirements of this process.<n>We propose a structural, diagnostic framework that evaluates LLM-based evidence extraction as a progression of schema-constrained queries.
  arXiv  Detail & Related papers  (2026-02-11T14:09:43Z)
• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check [54.08619694620588]
  We present a comprehensive evaluation of dLLMs across two distinct agentic paradigms: Embodied Agents and Tool-Calling Agents.<n>Our results on Agentboard and BFCL reveal a "bitter lesson": current dLLMs fail to serve as reliable agentic backbones.
  arXiv  Detail & Related papers  (2026-01-19T11:45:39Z)
• TS-Agent: A Time Series Reasoning Agent with Iterative Statistical Insight Gathering [16.95452463476229]
  We propose TS-Agent, a time series reasoning agent for large language models (LLMs)<n>Instead of mapping time series into text tokens, images, or embeddings, our agent interacts with raw numeric sequences through atomic operators.<n>Our experiments show that TS-Agent achieves performance comparable to state-of-the-art LLMs on understanding benchmarks.
  arXiv  Detail & Related papers  (2025-10-08T18:31:53Z)
• When the Code Autopilot Breaks: Why LLMs Falter in Embedded Machine Learning [0.8880611506199766]
  We show how prompt format, model behavior, and structural assumptions influence both success rates and failure characteristics.<n>Our analysis reveals a diverse set of error-prone behaviors, including format-induced misinterpretations and runtime-disruptive code that compiles but breaks downstream.
  arXiv  Detail & Related papers  (2025-09-13T19:00:04Z)
• IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
  IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
  arXiv  Detail & Related papers  (2025-05-23T09:37:52Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)

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.