Papers › ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path...

ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback

23 Sep 2024arXiv:2409.14826archive 2025-07-28

Qinzhuo Wu, Wei Liu, Jian Luan, Bin Wang

Recently, tool-augmented LLMs have gained increasing attention. Given an instruction, tool-augmented LLMs can interact with various external tools in multiple rounds and provide a final answer. However, previous LLMs were trained on overly detailed instructions, which included API names or parameters, while real users would not explicitly mention these API details. This leads to a gap between trained LLMs and real-world scenarios. In addition, most works ignore whether the interaction process follows the instruction. To address these issues, we constructed a training dataset called MGToolBench, which contains statement and category-level instructions to better reflect real-world scenarios. In addition, we propose ToolPlanner, a two-stage reinforcement learning framework that utilizes path planning and two feedback mechanisms to enhance the LLM's task completion and instruction-following capabilities. Experimental results show that ToolPlanner significantly improves the Match Rate, Pass Rate and Win Rate by 26.8%, 20.2%, and 5.6% compared to the SOTA model. Human evaluation verifies that the multi-granularity instructions can better align with users' usage habits. Our data and code will be released upon acceptance.

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 8 code samples harvested from 1 repository linked to this paper: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 5 ran (4 with no instrument failure; 1 where Syntology's instrument failed). 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

xiaomi/toolplanner officialmentioned in papermentioned on GitHubpytorchSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 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

8 samples harvested: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
3ran
3unverified

Licence: 8 of the 8 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 xiaomi/toolplanner. “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”. “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.

xiaomi/toolplanner official repository 8 samples, 5 ran (1 instrument-failed) · 3 unverified
DFS_Step_tree_search toolbench/inference/Algorithms/DFS_Step.py ran licence not identified · pointer only · b1e1fe068fc2f11a · report fixture: returned DFS_Step_tree_search · level recorded 2026-09-22
base_env toolbench/inference/Algorithms/DFS_Step.py ran licence not identified · pointer only · 35b5c9b21d0c9954 · report fixture: returned base_env · level recorded 2026-09-22
base_search_method toolbench/inference/Algorithms/DFS_Step.py ran licence not identified · pointer only · 5c99801254076057 · report fixture: returned base_search_method · level recorded 2026-09-22
rank2symmetry toolbench/inference/Algorithms/DFS_Step.py ran · honoured contract licence not identified · pointer only · 2206745a8fe3a359 · report fixture: signature llm_interface:MockLLMInterface/0/?, LLM_rank_args:dict/0/?, cand1:str/0/str, cand2:str/0/str · returned tuple · level recorded 2026-09-22
sum_based_rankn toolbench/inference/Algorithms/DFS_Step.py ran · our draft was wrong licence not identified · pointer only · d03e6ec849359801 · report fixture: signature llm_interface:MockLLMInterface/0/?, LLM_rank_args:dict/0/?, candidates:list/1/MockCandidate · returned tuple · level recorded 2026-09-22
my_tree toolbench/inference/Algorithms/DFS_Step.py unverified licence not identified · pointer only · 0957e73e8af3f90d · report
rank2_subfix toolbench/inference/Algorithms/DFS_Step.py unverified licence not identified · pointer only · c9bb8ee513bdcc44 · report
tree_node toolbench/inference/Algorithms/DFS_Step.py unverified licence not identified · pointer only · 46bbbd8e7baddca1 · report

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 ToolPlanner (graph method: ToolPlanner). 8 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. DFS_Step_tree_search entry · level 1 · ran · b1e1fe068fc2f11a
  2. base_search_method helper · level 1 · ran · 5c99801254076057
  3. my_tree helper · level 0 · unverified · 0957e73e8af3f90d
  4. rank2_subfix helper · level 0 · unverified · c9bb8ee513bdcc44
  5. sum_based_rankn helper · level 1 · ran · our draft was wrong · d03e6ec849359801
  6. tree_node helper · level 0 · unverified · 46bbbd8e7baddca1
  7. base_env helper · level 1 · ran · 35b5c9b21d0c9954
  8. rank2symmetry helper · level 1 · ran · honoured contract · 2206745a8fe3a359

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="2409.14826") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Instruction Following

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGN

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