Pith. sign in

REVIEW 5 cited by

Chain of Agents: Large Language Models Collaborating on Long-Context Tasks

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 2406.02818 v1 pith:ZGAITOWL submitted 2024-06-04 cs.CL

Chain of Agents: Large Language Models Collaborating on Long-Context Tasks

classification cs.CL
keywords contextllmsinformationinputlanguagelong-contexttasksagent
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Addressing the challenge of effectively processing long contexts has become a critical issue for Large Language Models (LLMs). Two common strategies have emerged: 1) reducing the input length, such as retrieving relevant chunks by Retrieval-Augmented Generation (RAG), and 2) expanding the context window limit of LLMs. However, both strategies have drawbacks: input reduction has no guarantee of covering the part with needed information, while window extension struggles with focusing on the pertinent information for solving the task. To mitigate these limitations, we propose Chain-of-Agents (CoA), a novel framework that harnesses multi-agent collaboration through natural language to enable information aggregation and context reasoning across various LLMs over long-context tasks. CoA consists of multiple worker agents who sequentially communicate to handle different segmented portions of the text, followed by a manager agent who synthesizes these contributions into a coherent final output. CoA processes the entire input by interleaving reading and reasoning, and it mitigates long context focus issues by assigning each agent a short context. We perform comprehensive evaluation of CoA on a wide range of long-context tasks in question answering, summarization, and code completion, demonstrating significant improvements by up to 10% over strong baselines of RAG, Full-Context, and multi-agent LLMs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

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

  1. Is Progressive Disclosure All You Need for Long-Context Agents?

    cs.AI 2026-07 conditional novelty 7.0

    Progressive disclosure is redundant for a strong agent reading one book, but decisive when an agent must navigate a 20-book library; one flat routing level beats deeper hierarchies.

  2. Traj-Evolve: A Self-Evolving Multi-Agent System for Patient Trajectory Modeling in Lung Cancer Early Detection

    cs.AI 2026-06 unverdicted novelty 6.0

    Traj-Evolve combines non-parametric experience retrieval and multi-agent RL with a leave-one-out unification strategy to outperform baselines on lung cancer prediction from up to five years of multimodal EHRs, includi...

  3. VeriCache: Turning Lossy KV Cache into Lossless LLM Inference

    cs.AR 2026-05 unverdicted novelty 6.0

    VeriCache turns lossy KV cache compression into lossless LLM inference by drafting with compressed cache and verifying drafts with full cache, achieving up to 4x throughput with identical outputs.

  4. Context-Mediated Domain Adaptation in Multi-Agent Sensemaking Systems

    cs.HC 2026-03 unverdicted novelty 5.0

    Context-mediated domain adaptation treats user modifications to AI artifacts as implicit domain specifications that reshape LLM-powered multi-agent reasoning, demonstrated via the Seedentia system which extracted 46 d...

  5. MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL

    cs.CL 2025-11 unverdicted novelty 5.0

    MARS-SQL trains a multi-agent RL system with ReAct-style interaction and generative validation to produce SQL queries, reaching 77.84% execution accuracy on BIRD dev and 89.75% on Spider test.