Long-context LLMs Struggle with Long In-context Learning | Paper Citation Record

Observation 86620063-7b2c-43f3-88b9-107dba444e64 · inbound

Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement cites this paper.

Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement Long-context LLMs Struggle with Long In-context Learning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-23T21:03:26.410772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c63bafa3-c91a-4311-8e76-27f01500a565 · inbound

Retrieval-Augmented Generation with Graphs (GraphRAG) cites this paper.

Retrieval-Augmented Generation with Graphs (GraphRAG) Long-context LLMs Struggle with Long In-context Learning

Reference 236

Resolution: verified exact; arxiv_id, observed 2026-05-18T04:33:39.591469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1d922b90-4734-4fd0-af0b-6852874d5f1e · inbound

Context-Aware Hierarchical Merging for Long Document Summarization cites this paper.

Context-Aware Hierarchical Merging for Long Document Summarization Long-context LLMs Struggle with Long In-context Learning

Reference 9474

Resolution: unresolved; no resolver link, observed 2026-08-09T17:07:30.662673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a45e0e0f-87e4-4066-a2a9-84c261d249dc · inbound

Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation cites this paper.

Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation Long-context LLMs Struggle with Long In-context Learning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T11:13:39.932258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34078b2e-310f-495a-ad88-44534e5003e2 · inbound

SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions cites this paper.

SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions Long-context LLMs Struggle with Long In-context Learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T10:50:59.375239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5682e00f-6242-4384-a697-3aa452dd53ab · inbound

Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models cites this paper.

Scalable In-Context Learning on Tabular Data via Retrieval-Augmented Large Language Models Long-context LLMs Struggle with Long In-context Learning

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T05:48:07.652670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa2fe151-5fba-4f95-b4eb-f1b9fd9d455f · inbound

MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters cites this paper.

MeDiSumQA: Patient-Oriented Question-Answer Generation from Discharge Letters Long-context LLMs Struggle with Long In-context Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T05:15:41.580608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1769055d-ccbe-4e67-a929-82562c067985 · inbound

GistVis: Automatic Generation of Word-scale Visualizations from Data-rich Documents cites this paper.

GistVis: Automatic Generation of Word-scale Visualizations from Data-rich Documents Long-context LLMs Struggle with Long In-context Learning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T00:48:08.702615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36827dbe-3559-405c-aadd-9efa3cb8e055 · inbound

ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification cites this paper.

ARISE: Iterative Rule Induction and Synthetic Data Generation for Text Classification Long-context LLMs Struggle with Long In-context Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-08T17:27:59.646167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f368372-216b-45ec-9fc6-c629eb6c1806 · inbound

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs cites this paper.

LCIRC: A Recurrent Compression Approach for Efficient Long-form Context and Query Dependent Modeling in LLMs Long-context LLMs Struggle with Long In-context Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T16:40:27.093627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c75a524-0c86-42a8-be21-4a6cfc0403a3 · inbound

Jailbreaking to Jailbreak cites this paper.

Jailbreaking to Jailbreak Long-context LLMs Struggle with Long In-context Learning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T17:02:47.335381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65777269-ef84-45f5-ba98-b3d6232b67ca · inbound

Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy cites this paper.

Multi-Stage Retrieval for Operational Technology Cybersecurity Compliance Using Large Language Models: A Railway Casestudy Long-context LLMs Struggle with Long In-context Learning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-22T18:31:55.892145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e160ea35-a85a-4b41-aa55-253084685939 · inbound

KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification cites this paper.

KG-HTC: Integrating Knowledge Graphs into LLMs for Effective Zero-shot Hierarchical Text Classification Long-context LLMs Struggle with Long In-context Learning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:36:44.905844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 039ff61f-f777-47d3-9cd0-f03786cc47dd · inbound

SafeTrans: LLM-assisted Transpilation from C to Rust cites this paper.

SafeTrans: LLM-assisted Transpilation from C to Rust Long-context LLMs Struggle with Long In-context Learning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T14:14:55.685609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a8ea5c78-5ed7-4a47-9c18-03385a0090de · inbound

Automated Profile Inference with Language Model Agents cites this paper.

Automated Profile Inference with Language Model Agents Long-context LLMs Struggle with Long In-context Learning

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T14:31:40.712667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 73ad850e-624c-4ae7-9c86-67b414a48740 · inbound

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning cites this paper.

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning Long-context LLMs Struggle with Long In-context Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:09:43.774129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49645e82-b652-4441-9933-cf3cd5d6f730 · inbound

LIFEBench: Evaluating Length Instruction Following in Large Language Models cites this paper.

LIFEBench: Evaluating Length Instruction Following in Large Language Models Long-context LLMs Struggle with Long In-context Learning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T15:08:05.259340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc804305-0ee1-475c-9af0-593a7fe6707e · inbound

Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models? cites this paper.

Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models? Long-context LLMs Struggle with Long In-context Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T13:49:22.576492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a25759-e103-4159-9809-9ffbe1bc9358 · inbound

Can Large Language Models Match the Conclusions of Systematic Reviews? cites this paper.

Can Large Language Models Match the Conclusions of Systematic Reviews? Long-context LLMs Struggle with Long In-context Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:05:45.055957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b062dc1-b16a-422c-bda6-97032990cd28 · inbound

Evaluating the Sensitivity of LLMs to Prior Context cites this paper.

Evaluating the Sensitivity of LLMs to Prior Context Long-context LLMs Struggle with Long In-context Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:45:46.890412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee8ef9b7-c48d-404d-8c54-9e52813fd1d9 · inbound

Adaptive Task Vectors for Large Language Models cites this paper.

Adaptive Task Vectors for Large Language Models Long-context LLMs Struggle with Long In-context Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:12:59.410752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92168c9d-c211-4fed-940c-36e2da21e3bb · inbound

ECoRAG: Evidentiality-guided Compression for Long Context RAG cites this paper.

ECoRAG: Evidentiality-guided Compression for Long Context RAG Long-context LLMs Struggle with Long In-context Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:30:33.160856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff86f8ee-34c5-4dbb-a114-47e96cef8416 · inbound

Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation cites this paper.

Respecting Temporal-Causal Consistency: Entity-Event Knowledge Graphs for Retrieval-Augmented Generation Long-context LLMs Struggle with Long In-context Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:17:25.318781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0473c9c2-a41b-4010-bf25-5fd125a256b7 · inbound

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs cites this paper.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Long-context LLMs Struggle with Long In-context Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.464454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef2157f-4b37-44a9-a632-4a9a0d311bf4 · inbound

Code Researcher: Deep Research Agent for Large Systems Code and Commit History cites this paper.

Code Researcher: Deep Research Agent for Large Systems Code and Commit History Long-context LLMs Struggle with Long In-context Learning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-22T02:20:56.134151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5b0b2d2a-3666-4e71-a7ea-d384c72101a5 · inbound

Long-Short Alignment for Effective Long-Context Modeling in LLMs cites this paper.

Long-Short Alignment for Effective Long-Context Modeling in LLMs Long-context LLMs Struggle with Long In-context Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:10:20.209082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae77716-eacf-49ce-9dab-ea2f4fccce3e · inbound

LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions cites this paper.

LIFELONG SOTOPIA: Evaluating Social Intelligence of Language Agents Over Lifelong Social Interactions Long-context LLMs Struggle with Long In-context Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:49:26.420709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa0033a-f9b9-48e1-b771-49d7b24b3522 · inbound

From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation cites this paper.

From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation Long-context LLMs Struggle with Long In-context Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:49:45.617067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b86a78-b459-40bb-ae34-1b76186d72e9 · inbound

SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments cites this paper.

SetupBench: Assessing Software Engineering Agents' Ability to Bootstrap Development Environments Long-context LLMs Struggle with Long In-context Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:08:48.218778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b087177-8611-4c47-883f-a3e8bdd52e52 · inbound

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models cites this paper.

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models Long-context LLMs Struggle with Long In-context Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T15:03:57.180820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3234a85f-b5c8-493c-96b9-98b49a9c935c · inbound

QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting cites this paper.

QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting Long-context LLMs Struggle with Long In-context Learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-05T17:39:23.292009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986e0cc3-f4da-43cf-90dd-b80c84213a5a · inbound

ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings cites this paper.

ThumbnailTruth: A Multi-Modal LLM Approach for Detecting Misleading YouTube Thumbnails Across Diverse Cultural Settings Long-context LLMs Struggle with Long In-context Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T06:00:51.063095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82bdb0c9-8baf-4baf-a895-7bfd9ded53c8 · inbound

LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering cites this paper.

LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering Long-context LLMs Struggle with Long In-context Learning

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-04T18:49:58.304178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5aaefce-db02-46c2-a4f2-f01226b8edd9 · inbound

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference cites this paper.

POPI: Personalizing LLMs via Optimized Natural Language Preference Inference Long-context LLMs Struggle with Long In-context Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-18T05:42:24.382956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1e0ae090-7a3c-47a1-9972-e04a83bd1191 · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Long-context LLMs Struggle with Long In-context Learning

Reference 250

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:22.427536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ac9ee6a4-f454-4165-85f7-81ed3d779208 · inbound

LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data cites this paper.

LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data Long-context LLMs Struggle with Long In-context Learning

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-03T10:43:50.298778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6c52c7e-9276-46e6-bf4f-c3c6d67945fd · inbound

Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method cites this paper.

Knowledge-Embedded and Hypernetwork-Guided Few-Shot Substation Meter Defect Image Generation Method Long-context LLMs Struggle with Long In-context Learning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T10:43:42.301267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3036ea04-0192-46b7-9790-df5fde4432fd · inbound

Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories cites this paper.

Vital Trace: Protocol-Constrained Patient-State Reasoning for Longitudinal Clinical Trajectories Long-context LLMs Struggle with Long In-context Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T23:44:43.039263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90ec86a6-9ab4-49f3-b054-3f8bf7b8fc85 · inbound

Learning to Adapt: In-Context Learning Beyond Stationarity cites this paper.

Learning to Adapt: In-Context Learning Beyond Stationarity Long-context LLMs Struggle with Long In-context Learning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:45:59.452590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 94234118-4423-4bbe-badc-927c07aad1d2 · inbound

Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies cites this paper.

Evaluating Multi-Hop Reasoning in RAG Systems: A Comparison of LLM-Based Retriever Evaluation Strategies Long-context LLMs Struggle with Long In-context Learning

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T04:04:47.614524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fbc2da4b-add3-4c99-8d73-b391c06652d7 · inbound

GR-Evolve: Design-Adaptive Global Routing via LLM-Driven Algorithm Evolution cites this paper.

GR-Evolve: Design-Adaptive Global Routing via LLM-Driven Algorithm Evolution Long-context LLMs Struggle with Long In-context Learning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:16:10.630377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 53d39b89-9bf5-4b93-b5d0-e41e35540cd8 · inbound

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation cites this paper.

Automation-Exploit: A Multi-Agent LLM Framework for Adaptive Offensive Security with Digital Twin-Based Risk-Mitigated Exploitation Long-context LLMs Struggle with Long In-context Learning

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:31:09.481105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0cef2088-9512-44df-af79-2d145b9e6402 · inbound

Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects cites this paper.

Generative AI-Based Virtual Assistant using Retrieval-Augmented Generation: An evaluation study for bachelor projects Long-context LLMs Struggle with Long In-context Learning

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:48:23.071537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bcd77922-cffc-40a0-bdbe-d4b632738933 · inbound

LLMs with in-context learning for Algorithmic Theoretical Physics cites this paper.

LLMs with in-context learning for Algorithmic Theoretical Physics Long-context LLMs Struggle with Long In-context Learning

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T08:31:25.694030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9d2b9f35-9e88-48ed-bcb7-abeb8bdc09fa · inbound

MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence cites this paper.

MMCL-Bench: Multimodal Context Learning from Visual Rules, Procedures, and Evidence Long-context LLMs Struggle with Long In-context Learning

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:59:27.471087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b0b41212-72e5-4014-beac-24ca2d6a76ab · inbound

ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract) cites this paper.

ERFSL: An Efficient Reward Function Searcher via Language Models for Custom-Environment Multi-Objective Optimization (Student Abstract) Long-context LLMs Struggle with Long In-context Learning

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T05:08:05.251593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 599a877f-0a73-4536-afcc-765ea693098a · inbound

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents cites this paper.

Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents Long-context LLMs Struggle with Long In-context Learning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-22T09:21:21.743874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 643a73a5-e4e9-4282-8b37-9b6a3d9f9eb3 · inbound

Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization cites this paper.

Step-TP: A Grounded, Step-Level Dataset with Chain-of-Thought Reasoning for LLM-Guided Tensor Program Optimization Long-context LLMs Struggle with Long In-context Learning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-06-29T23:24:01.897423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f3c76877-8faa-457a-8ef3-eb81c0f25206 · inbound

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor cites this paper.

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor Long-context LLMs Struggle with Long In-context Learning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-29T12:13:26.708638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f86840d6-93a8-45a3-a22d-a1f02c194019 · inbound

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs cites this paper.

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs Long-context LLMs Struggle with Long In-context Learning

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:23:13.213462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1b497549-0644-4ef8-82d7-1c7877c12359 · inbound

Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison cites this paper.

Ten Headache Specialists versus Artificial Intelligence for Clinical Literature Summarization: A Critical Evaluation and Comparison Long-context LLMs Struggle with Long In-context Learning

Reference 133

Resolution: verified exact; arxiv_id, observed 2026-07-02T08:26:48.062206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6e672629-a3ff-444d-a79b-734f3a932eea · inbound

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering cites this paper.

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering Long-context LLMs Struggle with Long In-context Learning

Reference 62

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T17:17:15.085456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f61857a1-a566-47fe-91b7-489b085bcfa7 · inbound

DD-GEPA: Prompt Optimization for Dialogue Disentanglement Focusing on Task Instruction and Utterance Representation cites this paper.

DD-GEPA: Prompt Optimization for Dialogue Disentanglement Focusing on Task Instruction and Utterance Representation Long-context LLMs Struggle with Long In-context Learning

Reference 127

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:07:22.123919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64c0ab5b-30db-43f8-bf41-03a5bbba6d91 · inbound

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling cites this paper.

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling Long-context LLMs Struggle with Long In-context Learning

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T19:03:51.847875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 74d4752e-61b7-43e0-9367-e1b3c2a216c1 · inbound

MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition cites this paper.

MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice Decomposition Long-context LLMs Struggle with Long In-context Learning

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-06-30T13:44:41.803407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 05aeba3b-0582-44f7-9d3c-69f7309d4e74 · inbound

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers cites this paper.

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers Long-context LLMs Struggle with Long In-context Learning

Reference 95

Resolution: verified exact; arxiv_id, observed 2026-06-30T06:14:17.965737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cab16a1b-cb9c-4eb1-b28d-db25b91d52f1 · inbound

UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp cites this paper.

UNIBROWSE: A Data-to-Agent Framework for Multimodal BrowseComp Long-context LLMs Struggle with Long In-context Learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-14T10:51:16.019022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51b9ae17-d878-46ab-a870-14d81b1d5d69 · inbound

State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation cites this paper.

State Compression in Two-Agent LLM Relays: A Closed-World Study of Constraint Preservation Long-context LLMs Struggle with Long In-context Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T13:36:49.852907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10a72db7-b872-4ede-8e78-c591443af755 · inbound

X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment cites this paper.

X$^3$-OPD: Distilling Reasoning into Large Audio-Language Models via On-Policy Alignment Long-context LLMs Struggle with Long In-context Learning

Reference 125

Resolution: unresolved; no resolver link, observed 2026-08-01T07:12:17.628789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a67faf4e-332e-4931-a36b-593d66ef0fc1 · inbound

Lost in Context: Addressing Context Anxiety in Large Language Models cites this paper.

Lost in Context: Addressing Context Anxiety in Large Language Models Long-context LLMs Struggle with Long In-context Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T12:47:57.566012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47cae494-6a96-47a4-a6c8-c94a54562870 · inbound

RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings cites this paper.

RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings Long-context LLMs Struggle with Long In-context Learning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T00:24:45.625119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers