Automatic Prompt Optimization with "Gradient Descent" and Beam Search | Paper Citation Record

Observation c21e125a-3242-4b21-a107-19862b44f6e0 · inbound

Reflexion: Language Agents with Verbal Reinforcement Learning cites this paper.

Reflexion: Language Agents with Verbal Reinforcement Learning Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T13:51:41.963062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 248d197e-5664-46a0-b283-9a17060d7292 · inbound

Large Language Models as Optimizers cites this paper.

Large Language Models as Optimizers Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:04:31.319892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation becd4a9f-14a8-495a-99a4-ab0364ab9764 · inbound

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers cites this paper.

EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 124

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:11:49.632758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 213284a3-377b-4f83-b988-8249236fa8cc · inbound

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution cites this paper.

Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-16T08:12:35.372889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 48a488a9-4799-4f18-b2c6-34b41ca9b20b · inbound

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines cites this paper.

DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:57:46.984559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5ac2f298-efaf-462f-9ad2-c7d11eb7e95e · inbound

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting cites this paper.

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-17T01:59:51.390802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 42853ad6-8802-4dd5-a3bb-1204e374f4e0 · inbound

Keeping Experts in the Loop: Expert-Guided Optimization for Clinical Data Classification using Large Language Models cites this paper.

Keeping Experts in the Loop: Expert-Guided Optimization for Clinical Data Classification using Large Language Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T23:49:47.777789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0f7aca-7e9a-48b8-b17f-c48348e5c2f2 · inbound

REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization cites this paper.

REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T22:52:15.153246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58ee331e-028c-4880-b473-3a0245e8a01d · inbound

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers cites this paper.

GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T16:52:28.858246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a976c4-3c5f-4b22-944a-7a56d05c7142 · inbound

Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models cites this paper.

Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T12:08:03.446562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ec70e26-31ac-470f-af77-f1c385d5afd8 · inbound

Memory-Augmented Agent Training for Business Document Understanding cites this paper.

Memory-Augmented Agent Training for Business Document Understanding Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T13:27:32.007712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 370d08af-cab4-4270-8fc0-00d151c0797d · inbound

Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework cites this paper.

Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T00:08:16.262491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a67637-65b7-4a28-8045-d49684bf27b2 · inbound

An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts cites this paper.

An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T17:14:06.503198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72977d4d-6982-49b8-b0ef-fe6e6f1df630 · inbound

LLM-AutoDiff: Auto-Differentiate Any LLM Workflow cites this paper.

LLM-AutoDiff: Auto-Differentiate Any LLM Workflow Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T11:33:24.646115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed5725ed-d274-40e8-89c1-761ee62b7939 · inbound

Generating Symbolic World Models via Test-time Scaling of Large Language Models cites this paper.

Generating Symbolic World Models via Test-time Scaling of Large Language Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T21:45:45.383025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0035b54-31fd-4826-8f7f-8f36abe1e12e · inbound

SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches cites this paper.

SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T12:22:43.278203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cb9fe6e-734b-47b7-ae38-2066156d5ec2 · inbound

MODP: Multi Objective Directional Prompting cites this paper.

MODP: Multi Objective Directional Prompting Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T10:14:32.340920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc4b4eb-1059-4a06-adf4-331c566e6781 · inbound

Local Prompt Optimization cites this paper.

Local Prompt Optimization Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:35:33.343962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbae75c1-ee3e-4eb9-b514-2d082e80b1c6 · inbound

TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution cites this paper.

TrajEvo: Designing Trajectory Prediction Heuristics via LLM-driven Evolution Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-15T23:32:07.515621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06b76652-7bd8-4a69-9cb7-6fb1955cdbc1 · inbound

Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow cites this paper.

Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T22:00:35.734403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 866b4b9a-3db6-4e01-aa06-335aa0eef24b · inbound

Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control cites this paper.

Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T21:45:35.101965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c6f579-4b73-4c96-a89c-7fa29cd3b437 · inbound

Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization cites this paper.

Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimization Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:08:46.207594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed60016a-60bb-4880-970b-71b09668513e · inbound

Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands cites this paper.

Cog-TiPRO: Iterative Prompt Refinement with LLMs to Detect Cognitive Decline via Longitudinal Voice Assistant Commands Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:08:25.999511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67ae6db2-43e4-42a9-a8a1-91266ea4ffdc · inbound

Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test cites this paper.

Visual Large Language Models Exhibit Human-Level Cognitive Flexibility in the Wisconsin Card Sorting Test Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T13:19:32.679972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03b6f9bb-dec4-4d97-89a5-6a47e344f3db · inbound

Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings cites this paper.

Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:15:39.830669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dde4865-f67f-48c4-b329-bb5f47e9ba75 · inbound

Predicting Empirical AI Research Outcomes with Language Models cites this paper.

Predicting Empirical AI Research Outcomes with Language Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:05:56.352320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80a63cd2-c49e-4284-80c9-33203b0a57ce · inbound

Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimization cites this paper.

Research on Driving Scenario Technology Based on Multimodal Large Lauguage Model Optimization Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:24:34.774410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1c5b9b8-fa9c-4d5b-8bfe-23dae174d260 · inbound

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs cites this paper.

Direct Behavior Optimization: Unlocking the Potential of Lightweight LLMs Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:19:34.725290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9817da71-1d6d-4c95-bca6-6f241c3dd680 · inbound

Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search cites this paper.

Enhancing Reasoning Capabilities of Small Language Models with Blueprints and Prompt Template Search Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:10:39.559056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f9b93ab-2e34-4361-8f83-873ae3112df1 · inbound

The Evolution of Natural Language Processing: How Prompt Optimization and Language Models are Shaping the Future cites this paper.

The Evolution of Natural Language Processing: How Prompt Optimization and Language Models are Shaping the Future Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T19:07:06.877853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c60c9bbc-260c-499f-97d2-5f75df7fd49e · inbound

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models cites this paper.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.373110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447b35a4-65a8-4979-8e55-6cbd5ae0b8db · inbound

Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing cites this paper.

Audit, Alignment, and Optimization of LM-Powered Subroutines with Application to Public Comment Processing Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:33:05.012547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aadb03a5-8aad-4467-8735-bfb4c5b7b56f · inbound

Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation cites this paper.

Stabilizing Black-Box Prompt Optimization with Textual Regularization and Signal Aggregation Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T17:51:03.278384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720098eb-df62-4700-8594-77f97dce52e5 · inbound

BuildEvo: Designing Building Energy Consumption Forecasting Heuristics via LLM-driven Evolution cites this paper.

BuildEvo: Designing Building Energy Consumption Forecasting Heuristics via LLM-driven Evolution Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:56:11.700817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78ea5e32-c17c-4513-a199-c79c0c6fdb00 · inbound

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities cites this paper.

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:25.139637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 840c83b5-d7dc-45b5-9c2a-6569e62b754a · inbound

Prompt Smart, Pay Less: Cost-Aware APO for Real-World Applications cites this paper.

Prompt Smart, Pay Less: Cost-Aware APO for Real-World Applications Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T16:11:25.974242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e7ddcc-6812-40fe-ac18-ea223bc4bb2e · inbound

TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards cites this paper.

TRPrompt: Bootstrapping Query-Aware Prompt Optimization from Textual Rewards Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T14:35:46.580669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cddf09b-d4f8-4c9d-85b3-669bbd6404fa · inbound

Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity cites this paper.

Prompt Engineering and the Effectiveness of Large Language Models in Enhancing Human Productivity Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T22:37:38.443498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bdbb183-1cea-4b1c-b069-9490ddf2573b · inbound

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:23:15.590683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 515253c4-bd57-4470-8ce0-bd2e682d4bae · inbound

ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients" cites this paper.

ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients" Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T00:55:38.065300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e59c8d2-79bf-484e-8123-a79756763244 · inbound

CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series cites this paper.

CaPulse: Detecting Anomalies by Tuning in to the Causal Rhythms of Time Series Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T23:55:53.056029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 579e80bc-d222-41cb-9496-958a6861aefe · inbound

WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning cites this paper.

WST: Weak-to-Strong Knowledge Transfer via Reinforcement Learning Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:15:24.202120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae57cb2-65ff-4ed8-9203-d33b666837aa · inbound

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

LAD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T15:47:12.941106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b3e3c15-937a-493b-9528-1144b1466b80 · inbound

Knowing How to Edit: Reliable Evaluation Signals for Diagnosing and Optimizing Prompts at Query Level cites this paper.

Knowing How to Edit: Reliable Evaluation Signals for Diagnosing and Optimizing Prompts at Query Level Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T20:29:15.134142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45e0833-4283-4a0e-b4ad-0791c01aac9d · inbound

PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data cites this paper.

PIAST: Rapid Prompting with In-context Augmentation for Scarce Training data Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-16T23:18:40.073746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 51d39e98-5c40-4162-a6b7-aa2b89d2e52d · inbound

Visual Persuasion: What Influences Decisions of Vision-Language Models? cites this paper.

Visual Persuasion: What Influences Decisions of Vision-Language Models? Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T23:00:27.011059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e988b4d7-58fc-499f-8bea-7ad2a6f5b85c · inbound

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search cites this paper.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.234658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 34d12499-f33d-4f66-9b19-971739a86db7 · inbound

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks cites this paper.

MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T19:22:25.401817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7429ff8e-41b7-4603-b049-3e45aec47877 · inbound

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training cites this paper.

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:45:26.392459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fc9790a2-fa30-4e26-82b8-d49efe1a8f46 · inbound

Meta-Harness: End-to-End Optimization of Model Harnesses cites this paper.

Meta-Harness: End-to-End Optimization of Model Harnesses Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 40

Resolution: verified exact; arxiv_id, observed 2026-05-13T16:15:58.020671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7054d502-1b0e-4239-9319-1c9aacb3f196 · inbound

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering cites this paper.

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 120

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:20:59.723082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 654bae84-0984-423c-84b7-af515b9411f0 · inbound

Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems cites this paper.

Prompt Optimization Is a Coin Flip: Diagnosing When It Helps in Compound AI Systems Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:10.383973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 90dd37db-fc11-464d-91bb-08891c753f77 · inbound

Embedding-perturbed Exploration Preference Optimization for Flow Models cites this paper.

Embedding-perturbed Exploration Preference Optimization for Flow Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-20T18:38:53.027822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4c9b3fa0-77a0-4645-8abb-f281dd2f23ce · inbound

A Reproducibility Analysis of PO4ISR: Diagnosing and Mitigating Semantic Drift in LLM-Based Session Recommendation cites this paper.

A Reproducibility Analysis of PO4ISR: Diagnosing and Mitigating Semantic Drift in LLM-Based Session Recommendation Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:49:19.533621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f7bd9f60-3431-46c1-8a9c-a26c023ae623 · inbound

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework cites this paper.

Building Customer Support AI Agents at 100M-User Scale: An Evaluation-Driven Framework Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-02T23:17:29.499369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a39b3b0b-5d08-4fb1-84a1-411370f9e410 · inbound

TAHOE: Text-to-SQL with Automated Hint Optimization from Experience cites this paper.

TAHOE: Text-to-SQL with Automated Hint Optimization from Experience Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:48:21.407189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f4f18d23-9a3e-489c-bb8d-7cc519028ba9 · inbound

BCL: Bayesian In-Context Learning Framework for Information Extraction cites this paper.

BCL: Bayesian In-Context Learning Framework for Information Extraction Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:29:15.908307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation adb0eadf-fa52-4a37-a0e6-c8ed9cb663c6 · inbound

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution cites this paper.

Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T03:39:30.821536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 061943ce-084a-435a-bdf3-68774a070a4f · inbound

MetaPS: Adaptive Programmatic Strategy Selection for Market Agents cites this paper.

MetaPS: Adaptive Programmatic Strategy Selection for Market Agents Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:39:42.748336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4fdfb860-2707-41d9-90b3-dcd53d517e61 · inbound

Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems cites this paper.

Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-04T12:09:48.813322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 63fd08e3-f085-46b9-920e-49040285988e · inbound

LLM4MTLs: Automated Generation and Empirical Evaluation of Model Transformation Languages cites this paper.

LLM4MTLs: Automated Generation and Empirical Evaluation of Model Transformation Languages Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-07-04T18:40:03.104242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d26e4894-fb73-4ea1-afc8-99341156c044 · inbound

BT-APE: A Computationally Light Backtracking Approach to Automatic Prompt Engineering for Requirements Classification cites this paper.

BT-APE: A Computationally Light Backtracking Approach to Automatic Prompt Engineering for Requirements Classification Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-02T09:16:48.666443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation faa636a4-b382-437e-bdca-723a4f9ea488 · inbound

Heuristic Learning for Active Flow Control Using Coding Agents cites this paper.

Heuristic Learning for Active Flow Control Using Coding Agents Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-14T04:44:42.371749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a966f4a-b337-4348-b2d5-2704c541d164 · inbound

MemoHarness: Agent Harnesses That Learn from Experience cites this paper.

MemoHarness: Agent Harnesses That Learn from Experience Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T05:43:00.443189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cffb090-0a89-462c-be0c-f4ea62d39747 · inbound

Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulation in Complex Task Resolution cites this paper.

Asking Questions the Right Way: A Multi-Agent Conversational System for Prompt Formulation in Complex Task Resolution Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T00:20:37.207547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb3fabb6-421b-4749-a9a1-4ba47e3aa620 · inbound

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories cites this paper.

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T10:10:32.578208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe5e747e-cfbe-4cb1-86b1-f8cb6e2dcb3f · inbound

FLARE: Few-shot Learning-based Adaptive Reflective Engine cites this paper.

FLARE: Few-shot Learning-based Adaptive Reflective Engine Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-15T14:58:05.734796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc143e12-766b-43b8-8e60-a00c8a8b140c · inbound

Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation cites this paper.

Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T14:00:07.898848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71c17b2b-a50e-4d4a-9cdd-a44fb3bd3a75 · inbound

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance cites this paper.

The Wording Effect: Quantifying Two-Way Drift in LLM Benchmark Performance Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-16T00:39:52.369060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers