SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.01469 · NeurIPS · 2024

AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback

Wei Wu, Minlie Huang, Peng Xu, Hongning Wang, Zujie Wen, Jian Guan

arXiv · PDF · Open in the Atlas

Code that ran

19 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 10 failures of our instrument; 5 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.01469.json · badge: /api/ran/2402.01469.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
JianGuanTHU/AMOR canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
jianguanthu/amor alias (classifier label)
classifier basis: classifier_2025
12 ran · 5 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
repeat_kv Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JianGuanTHU/AMOR/code/modeling_llama.py
pointer only (licence: NONE) · get_code("30d7eec482ebf6b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JianGuanTHU/AMOR when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Generator Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("3dbe593f2d6f3b4e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LlamaAttention Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("6bfe6fa28a5de901")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LlamaDynamicNTKScalingRotaryEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("572dde6105d00036")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LlamaLinearScalingRotaryEmbedding Ran
ran on a synthesized input
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("06c2cf625cad2b53")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LlamaMLP Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("8e8d8d9e109e9f1e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LlamaRMSNorm Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("50ff7976d78544ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LlamaRotaryEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("88c615c48b7dd37b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

State Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("5fc26624516c1588")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JianGuanTHU/AMOR/code/modeling_llama.py
pointer only (licence: NONE) · get_code("f725bc2d76076485")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JianGuanTHU/AMOR when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from time-series-foundation-models/lag-llama
pointer only · get_code("9a65a30d006fc96e")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

encode_with_prompt_completion_format Ran
ran; our contract draft was wrong, not the code
JianGuanTHU/AMOR/code/finetune.py
pointer only (licence: NONE) · get_code("99e4a58eb23854c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JianGuanTHU/AMOR when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_decompose_prompt Ran
ran; our contract draft was wrong, not the code
JianGuanTHU/AMOR/code/prompts.py
pointer only (licence: NONE); the stored copy get_code serves, from jianguanthu/amor, is pointer only (licence: NONE) · get_code("bd4037a865476156")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JianGuanTHU/AMOR when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_finish_prompt Ran
ran; our contract draft was wrong, not the code
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("229b36214feed61d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_history_str Ran
ran; our contract draft was wrong, not the code
JianGuanTHU/AMOR/code/get_reward.py
pointer only (licence: NONE) · get_code("fe65d70569706d67")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JianGuanTHU/AMOR when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_relevance_prompt Ran
ran; our contract draft was wrong, not the code
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("5b8b14beaf8deb74")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_solve_prompt Ran
ran; our contract draft was wrong, not the code
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("76fe6fab3919e7d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rotate_half Ran
ran; our contract draft was wrong, not the code
JianGuanTHU/AMOR/code/modeling_llama.py
pointer only (licence: NONE) · get_code("b99eea6376d1e212")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JianGuanTHU/AMOR when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

text_toolkits Ran
ran on a synthesized input · constructed an object; no result was computed
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("8fd91ae45180bf3e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

LLama Not yet run
unverified (harvested, no recorded run)
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("3df7b70913f4ced7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LlamaDecoderLayer Not yet run
unverified (harvested, no recorded run)
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("358cf499b8ba9ff5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LlamaModel Not yet run
unverified (harvested, no recorded run)
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("04e5aaed2ab55a45")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

LlamaMoeSparseMoeBlock Not yet run
unverified (harvested, no recorded run)
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("e1590868abc435b3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Manager Not yet run
unverified (harvested, no recorded run)
jianguanthu/amor/code/manager.py
pointer only (licence: NONE) · get_code("0b69caf4cf9368d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jianguanthu/amor when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 8 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 4 the same month, 8 later) and 15 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
rotate_half
brick of this paper's assembly: helper
360 other papers
68 dated earlier, 25 the same month, 258 later, 6 same year, order not determinable, 3 undated · 30 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2302.13971 (2023-02)
LLaMA: Open and Efficient Foundation Language Models
and 357 more not named here
repeat_kv
brick of this paper's assembly: helper
243 other papers
33 dated earlier, 19 the same month, 187 later, 2 same year, order not determinable, 2 undated · 22 only as an assembly brick
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2203.08913 (2022-03)
Memorizing Transformers
2305.17888 (2023-05)
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
and 240 more not named here
apply_rotary_pos_emb
brick of this paper's assembly: helper
83 other papers
19 dated earlier, 11 the same month, 51 later, 2 same year, order not determinable · 6 only as an assembly brick
2306.15595 (2023-06)
Extending Context Window of Large Language Models via Positional Interpolation
2307.05695 (2023-07)
ReLoRA: High-Rank Training Through Low-Rank Updates
2307.06945 (2023-07)
In-context Autoencoder for Context Compression in a Large Language Model
and 80 more not named here
LlamaRMSNorm
brick of this paper's assembly: helper
6 other papers
2 dated earlier, 1 the same month, 3 later · 5 only as an assembly brick
2203.08913 (2022-03)
Memorizing Transformers
2401.07159 (2024-01)
Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
2402.14905 (2024-02)
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
and 3 more not named here
LlamaLinearScalingRotaryEmbedding
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later · 3 only as an assembly brick
2203.08913 (2022-03)
Memorizing Transformers
2401.07159 (2024-01)
Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
2406.12335 (2024-06)
Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters
and 2 more not named here
LlamaDynamicNTKScalingRotaryEmbedding
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2503.13108 (2025-03)
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
LlamaRotaryEmbedding
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2503.13108 (2025-03)
Lifting the Veil on Visual Information Flow in MLLMs: Unlocking Pathways to Faster Inference
get_decompose_prompt
brick of this paper's assembly: helper
1 other paper
1 later
2406.19934 (2024-06)
From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

The notable success of large language models (LLMs) has sparked an upsurge in building language agents to complete various complex tasks. We present AMOR, an agent framework based on open-source LLMs, which reasons with external knowledge bases and adapts to specific domains through human supervision to the reasoning process. AMOR builds reasoning logic over a finite state machine (FSM) that solves problems through autonomous executions and transitions over disentangled modules. This allows humans to provide direct feedback to the individual modules, and thus naturally forms process supervision. Based on this reasoning and feedback framework, we develop AMOR through two-stage fine-tuning: warm-up and adaptation. The former fine-tunes the LLM with examples automatically constructed from various public datasets, enabling AMOR to generalize across different knowledge environments, while the latter tailors AMOR to specific domains using process feedback. Extensive experiments across multiple domains demonstrate the advantage of AMOR to strong baselines, thanks to its FSM-based reasoning and process feedback mechanism. The code and data are publicly available at https://github.com/JianGuanTHU/AMOR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.01469")
get_code_for_paper("2402.01469")
have("2402.01469")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.01469.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.01469.svg)](https://syntology.ai/paper/2402.01469)

Connect an agent — have() is free.