The paper introduces representational commitment, a metric that quantifies hidden‑state similarity across repeated runs of a tool‑using LLM agent at the same step. Experiments on Llama‑3.1‑70B with ReAct on HotpotQA and other models show that higher step‑4 similarity correlates with lower overall trajectory variability, indicating when agent behavior stabilizes. The study also demonstrates that this metric captures stability rather than correctness, and explores monitoring and intervention techniques that can predict and reduce trajectory variability, though they do not significantly improve accuracy.
arXiv:2610.19679v1 Announce Type: cross Abstract: Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in completing complex tasks through multi-step reasoning and tool i...
The study evaluates how large language model agents maintain consistency over extended interactions by simulating a 20‑step delayed‑gratification task. Researchers ran 84,540 trajectories across eight model families, using survival analysis to track when agents first claim a reward and discrete‑time hazard regression to assess how factors like social visibility, persona stressors, and deliberation policy affect failure risk. They also developed a seven‑category taxonomy from 13,780 deliberation traces, revealing that early failures are impulse‑driven, later ones are fatigue‑ or cost‑benefit‑framed, and public settings elicit norm‑oriented justifications; longer deliberation correlates with higher intra‑rationale contradictions, challenging assumptions about reasoning depth and consistency.
The paper introduces ontological trust, a task‑conditioned property of trajectory prefixes, and presents RGE, an online monitor that decomposes trust into Role, Goal, and Evidence. RGE uses LLMs only for structured task and step representations, while trust updates and interventions are deterministic, producing a replayable and auditable trust trajectory. Evaluated on a cross‑domain corpus, RGE outperforms rule‑, judge‑, and shield‑style baselines, achieving over 93% Drift F1 and maintaining high benign coverage.
arXiv:2608. 04066v1 Announce Type: new Abstract: How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust?
arXiv:2605. 28850v2 Announce Type: replace Abstract: We study behavioral alignment and representation dynamics of large language model (LLM) agents in financial decision environments.
arXiv:2601.15322v3 Announce Type: replace-cross Abstract: Tool-using agents can repeat a final decision while changing their recorded execution. We introduce the Determinism-Faithfulness Assurance Ha...
The paper introduces CauTrace, a white‑box diagnostic framework that analyzes why large language models (LLMs) fail by examining internal states, representation propagation, and temporal coordination during reasoning. It defines seven functional states to capture support and constraint processing, tracks how these states evolve across Transformer blocks, and studies the timing of commitment and verification steps. Experiments on Qwen and LLaMA-family models show distinct failure signatures, and repair/steering tests confirm that the framework’s signals align with expected changes in the inference process.
Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable. We show that failure is predictable early from the agent's internal representations: lightweight per-round probes on hidden activations anticipate eventual episode failure as early as the first interaction round, where scorers reading only the agent's observable behavior are barely better than chance.
arXiv:2606. 15579v1 Announce Type: new Abstract: We propose Base Sequence Analysis, a framework that encodes the runtime behavior of LLM-powered autonomous agents into compact symbolic sequences using a four-letter alphabet: X (Explore), E (Execute), P (Plan), and V (Verify).
arXiv:2602. 11619v2 Announce Type: replace Abstract: Running the same LLM agent on identical inputs yields 2.
arXiv:2607. 10526v1 Announce Type: new Abstract: Stateful personal agents increasingly maintain long-term user profiles, episodic memories, and reusable skills.
arXiv:2607. 06503v1 Announce Type: new Abstract: Large language model (LLM) agents solving multi-step tasks frequently commit to trajectories that are doomed to fail, yet continue to consume substantial inference compute before the failure becomes observable.