Pith. sign in

REVIEW 6 cited by

Can We Rely on LLM Agents to Draft Long-Horizon Plans? Let's Take TravelPlanner as an Example

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

arxiv 2408.06318 v1 pith:DNU2AE2S submitted 2024-08-12 cs.AI cs.LG

classification cs.AIcs.LG
keywords agentsplansfeedbackfine-tuningllmslongplanningaccurate
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLMs) have brought autonomous agents closer to artificial general intelligence (AGI) due to their promising generalization and emergent capabilities. There is, however, a lack of studies on how LLM-based agents behave, why they could potentially fail, and how to improve them, particularly in demanding real-world planning tasks. In this paper, as an effort to fill the gap, we present our study using a realistic benchmark, TravelPlanner, where an agent must meet multiple constraints to generate accurate plans. We leverage this benchmark to address four key research questions: (1) are LLM agents robust enough to lengthy and noisy contexts when it comes to reasoning and planning? (2) can few-shot prompting adversely impact the performance of LLM agents in scenarios with long context? (3) can we rely on refinement to improve plans, and (4) can fine-tuning LLMs with both positive and negative feedback lead to further improvement? Our comprehensive experiments indicate that, firstly, LLMs often fail to attend to crucial parts of a long context, despite their ability to handle extensive reference information and few-shot examples; secondly, they still struggle with analyzing the long plans and cannot provide accurate feedback for refinement; thirdly, we propose Feedback-Aware Fine-Tuning (FAFT), which leverages both positive and negative feedback, resulting in substantial gains over Supervised Fine-Tuning (SFT). Our findings offer in-depth insights to the community on various aspects related to real-world planning applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evolution and The Knightian Blindspot of Machine Learning

    cs.AI 2025-01 conditional novelty 6.0 of 10

    ML's formalisms, particularly RL's, exclude Knightian uncertainty, and evolution's diversify-and-filter mechanisms point toward a direct remedy.

  2. LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback

    cs.RO 2025-09 conditional novelty 5.0 of 10

    LAD-VF iteratively rewrites LLM prompts using formal verification failure rates as a loss, lifting safety-spec compliance from about 60% to over 90% without model fine-tuning.

  3. LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models

    cs.MM 2025-02 conditional novelty 5.0 of 10

    LLMER uses LLM-generated JSON data instead of code to create interactive XR worlds, cutting token use and task completion time in a small user study.

  4. Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference

    cs.CL 2025-01 conditional novelty 5.0 of 10

    EHPC uses a handful of attention heads, selected via a synthetic needle-in-a-haystack test, to compress long prompts and speed up LLM inference while retaining task performance.

  5. Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study

    cs.RO 2025-07 conditional novelty 4.0 of 10

    Reasoning-optimized LLMs reach at most 63.4% success across the five PDDL benchmarks, versus 97.9% for Fast Downward, and frequently produce plans that fail during execution.

  6. A Survey on Multi-Turn Interaction Capabilities of Large Language Models

    cs.CL 2025-01 conditional novelty 2.0 of 10

    A comprehensive review of how large language models are evaluated, trained, and improved for multi-turn interaction, organized into evaluation practices, core capabilities, and general algorithms.

Pith tools