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

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

2 Feb 2024arXiv:2402.01469archive 2025-07-28

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

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.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 24 code samples: 23 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 24: 19 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 23 samples from 1 repository, 18 ran (10 with no instrument failure; 8 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 19 samples that ran have no recorded date.

jianguanthu/amor officialmentioned in papermentioned on GitHubpytorchSyntology: 23 samples, 18 ran (8 instrument-failed) · 5 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

24 samples harvested: 19 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran · our draft was wrong
3ran; the contract check could not run
10ran
5unverified

Licence: 24 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from jianguanthu/amor. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jianguanthu/amor official repository 23 samples, 18 ran (8 instrument-failed) · 5 unverified
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
code/modeling_llama.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 30d7eec482ebf6b1 · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded, date not recorded
Generator in 95 papers code/manager.py ran no licence file found · pointer only · 3dbe593f2d6f3b4e · report fixture: returned Generator · level recorded 2026-09-22
LlamaAttention in 15 papers code/manager.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6bfe6fa28a5de901 · report fixture: returned LlamaAttention · level recorded 2026-09-22
LlamaDynamicNTKScalingRotaryEmbedding in 6 papers code/manager.py ran · metamorphic tier: deterministic no licence file found · pointer only · 572dde6105d00036 · report fixture: returned LlamaDynamicNTKScalingRotaryEmbedding · level recorded 2026-09-22
LlamaLinearScalingRotaryEmbedding in 6 papers code/manager.py ran fingerprinted no licence file found · pointer only · 06c2cf625cad2b53 · report fixture: signature x:Tensor/4/float, seq_len:int/0/int · returned tuple · level recorded 2026-09-24
LlamaMLP in 13 papers code/manager.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 8e8d8d9e109e9f1e · report fixture: returned LlamaMLP · level recorded 2026-09-22
LlamaRMSNorm in 9 papers code/manager.py ran · metamorphic tier: deterministic no licence file found · pointer only · 50ff7976d78544ac · report fixture: returned LlamaRMSNorm · level recorded 2026-09-22
LlamaRotaryEmbedding in 13 papers code/manager.py ran · metamorphic tier: deterministic no licence file found · pointer only · 88c615c48b7dd37b · report fixture: returned LlamaRotaryEmbedding · level recorded 2026-09-22
State in 13 papers code/manager.py ran no licence file found · pointer only · 5fc26624516c1588 · report fixture: returned State · level recorded 2026-09-22
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
code/modeling_llama.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · f725bc2d76076485 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, cos:Tensor/4/float, sin:Tensor/4/float, position_ids:Tensor/2/int · returned tuple · level recorded, date not recorded
encode_with_prompt_completion_format in 25 papers code/finetune.py ran no licence file found · pointer only · 99e4a58eb23854c4 · report fixture: signature example:dict/0/?, tokenizer:callable/0/?, max_seq_length:int/0/int · returned dict · level recorded 2026-09-24
get_decompose_prompt code/prompts.py ran · our draft was wrong fingerprinted no licence file found · pointer only · bd4037a865476156 · report fixture: signature task:str/0/str, history:str/0/str · returned str · level recorded 2026-09-22
get_finish_prompt code/manager.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 229b36214feed61d · report fixture: signature task:str/0/str, psgs:str/0/str, history:str/0/str · returned str · level recorded 2026-09-22
get_history_str code/get_reward.py ran · our draft was wrong no licence file found · pointer only · fe65d70569706d67 · report fixture: signature history_qa:list/1/tuple · returned str · level recorded 2026-09-24
get_relevance_prompt code/manager.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 5b8b14beaf8deb74 · report fixture: signature task:str/0/str, history:str/0/str, query:str/0/str, docs:str/0/str · returned str · level recorded 2026-09-22
get_solve_prompt code/manager.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 76fe6fab3919e7d6 · report fixture: signature task:str/0/str, history:str/0/str, query:str/0/str, docs:str/0/str · returned str · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
code/modeling_llama.py ran · our draft was wrong fingerprinted no licence file found · pointer only · b99eea6376d1e212 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
text_toolkits code/manager.py ran no licence file found · pointer only · 8fd91ae45180bf3e · report fixture: returned text_toolkits · level recorded 2026-09-22
LLama code/manager.py unverified no licence file found · pointer only · 3df7b70913f4ced7 · report
LlamaDecoderLayer in 11 papers code/manager.py unverified no licence file found · pointer only · 358cf499b8ba9ff5 · report
LlamaModel in 9 papers code/manager.py unverified no licence file found · pointer only · 04e5aaed2ab55a45 · report
LlamaMoeSparseMoeBlock code/manager.py unverified no licence file found · pointer only · e1590868abc435b3 · report
Manager code/manager.py unverified no licence file found · pointer only · 0b69caf4cf9368d9 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 9a65a30d006fc96e · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, cos:Tensor/3/float, sin:Tensor/3/float, position_ids:Tensor/2/int · returned tuple · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AMOR (graph method: AMOR). 23 bricks; individually on a fixture: 18 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. Manager entry · level 0 · unverified · 0b69caf4cf9368d9
  2. LLama model · level 0 · unverified · 3df7b70913f4ced7
  3. State helper · level 1 · ran · 5fc26624516c1588
  4. get_decompose_prompt helper · level 1 · ran · our draft was wrong · bd4037a865476156
  5. get_finish_prompt helper · level 1 · ran · our draft was wrong · 229b36214feed61d
  6. get_relevance_prompt helper · level 1 · ran · our draft was wrong · 5b8b14beaf8deb74
  7. get_solve_prompt helper · level 1 · ran · our draft was wrong · 76fe6fab3919e7d6
  8. text_toolkits helper · level 1 · ran · 8fd91ae45180bf3e
  9. Generator helper · level 1 · ran · 3dbe593f2d6f3b4e
  10. LlamaAttention helper · level 1 · ran · 6bfe6fa28a5de901
  11. LlamaDecoderLayer helper · level 0 · unverified · 358cf499b8ba9ff5
  12. LlamaMLP helper · level 1 · ran · 8e8d8d9e109e9f1e
  13. LlamaMoeSparseMoeBlock helper · level 0 · unverified · e1590868abc435b3
  14. LlamaRMSNorm helper · level 1 · ran · 50ff7976d78544ac
  15. LlamaRotaryEmbedding helper · level 1 · ran · 88c615c48b7dd37b
  16. _expand_mask helper · level 1 · ran · our draft was wrong · 61ecf291f8900bce
  17. _make_causal_mask helper · level 1 · ran; the contract check could not run · 72d28356d328b1e1
  18. apply_rotary_pos_emb helper · level 1 · ran; the contract check could not run (RAISES) · 9a65a30d006fc96e
  19. repeat_kv helper · level 2 · ran; the contract check could not run · 3c76e52815c5401d
  20. rotate_half helper · level 1 · ran · our draft was wrong · e03d53ba9d4f9ae5
  21. LlamaDynamicNTKScalingRotaryEmbedding helper · level 1 · ran · 572dde6105d00036
  22. LlamaLinearScalingRotaryEmbedding helper · level 1 · ran · 06c2cf625cad2b53
  23. LlamaModel helper · level 0 · unverified · 04e5aaed2ab55a45

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2402.01469") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections