Papers › ReAct: Synergizing Reasoning and Acting in Language Models

ReAct: Synergizing Reasoning and Acting in Language Models

6 Oct 2022arXiv:2210.03629archive 2025-07-28

Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao

While large language models (LLMs) have demonstrated impressive capabilities across tasks in language understanding and interactive decision making, their abilities for reasoning (e.g. chain-of-thought prompting) and acting (e.g. action plan generation) have primarily been studied as separate topics. In this paper, we explore the use of LLMs to generate both reasoning traces and task-specific actions in an interleaved manner, allowing for greater synergy between the two: reasoning traces help the model induce, track, and update action plans as well as handle exceptions, while actions allow it to interface with external sources, such as knowledge bases or environments, to gather additional information. We apply our approach, named ReAct, to a diverse set of language and decision making tasks and demonstrate its effectiveness over state-of-the-art baselines, as well as improved human interpretability and trustworthiness over methods without reasoning or acting components. Concretely, on question answering (HotpotQA) and fact verification (Fever), ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API, and generates human-like task-solving trajectories that are more interpretable than baselines without reasoning traces. On two interactive decision making benchmarks (ALFWorld and WebShop), ReAct outperforms imitation and reinforcement learning methods by an absolute success rate of 34% and 10% respectively, while being prompted with only one or two in-context examples. Project site with code: https://react-lm.github.io

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 34 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 31 samples from 2 repositories, 12 ran (9 with no instrument failure; 3 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.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ysymyth/ReAct officialmentioned on GitHubMITSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
billxbf/rewoo mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models (arXiv:2305.18323; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hkust-nlp/agentboard mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents (arXiv:2401.13178; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
infiagent/infiagent mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks (arXiv:2401.05507; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
liyuan24/nanodeepresearch mentioned on GitHubSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
sierra-research/tau-bench mentioned on GitHubSyntology: 26 samples, 9 ran (3 instrument-failed) · 17 unverified report
thudm/agenttuning mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AgentTuning: Enabling Generalized Agent Abilities for LLMs (arXiv:2310.12823; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
vortezwohl/Autono mentioned on GitHubGPL-3.0Syntology: not harvested report
yenchehsiao/autonomousllmagentwithadaptingplanning mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

34 samples harvested: 15 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 19 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
5ran · our draft was wrong
9ran
19unverified

Licence: 6 of the 34 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

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.

ysymyth/ReAct official repository 3 samples, 3 ran (2 instrument-failed) · 0 unverified
clean_str in 51 papers wikienv.py ran · our draft was wrong fingerprinted MIT (permissive) · 961911bec23c09ff · report fixture: signature p:str/0/str · returned str · level recorded 2026-09-22
f1_score in 121 papers wrappers.py ran · honoured contract MIT (permissive) · 32a5f1733d9a8971 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned tuple · level recorded 2026-09-22
normalize_answer in 304 papers wrappers.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · dae7ab386661a4f4 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
liyuan24/nanodeepresearch community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
AgentState agent/react_agent.py ran no licence file found · pointer only · 67368f282ad305f4 · report fixture: returned AgentState · level recorded 2026-09-22
State in 13 papers agent/react_agent.py ran no licence file found · pointer only · b31daddc6c61beaf · report fixture: returned State · level recorded 2026-09-22
Tool agent/react_agent.py ran no licence file found · pointer only · c1d21e714eedd29c · report fixture: returned Tool · level recorded 2026-09-22
ReactAgent agent/react_agent.py unverified no licence file found · pointer only · 3b3b1888dc5abd89 · report
load_prompt in 25 papers agent/react_agent.py unverified no licence file found · pointer only · cb56e34b15e5e739 · report
sierra-research/tau-bench community (archive-listed) 26 samples, 9 ran (3 instrument-failed) · 17 unverified
Action in 10 papers tau_bench/agents/chat_react_agent.py ran · metamorphic tier: deterministic MIT (permissive) · 69febc56d55428d1 · report fixture: returned Action · level recorded 2026-09-22
HumanUserSimulationEnv tau_bench/agents/chat_react_agent.py ran MIT (permissive) · c06bc83fe26205ee · report fixture: returned HumanUserSimulationEnv · level recorded 2026-09-22
RewardActionInfo tau_bench/agents/chat_react_agent.py ran · metamorphic tier: deterministic MIT (permissive) · 57d96bea80ca4d0f · report fixture: returned RewardActionInfo · level recorded 2026-09-22
RewardOutputInfo tau_bench/agents/chat_react_agent.py ran · metamorphic tier: deterministic MIT (permissive) · 3cbe32095b32f8a4 · report fixture: returned RewardOutputInfo · level recorded 2026-09-22
SolveResult tau_bench/agents/chat_react_agent.py ran · metamorphic tier: deterministic MIT (permissive) · 585b61f32e449f1f · report fixture: returned SolveResult · level recorded 2026-09-22
Tool tau_bench/agents/chat_react_agent.py ran MIT (permissive) · ea6a9a1ba41d476e · report fixture: returned Tool · level recorded 2026-09-22
consistent_hash tau_bench/agents/chat_react_agent.py ran · our draft was wrong fingerprinted MIT (permissive) · 525653e8db7bd970 · report fixture: signature value:str/0/str · returned str · level recorded 2026-09-22
map_role_label tau_bench/agents/chat_react_agent.py ran · our draft was wrong fingerprinted MIT (permissive) · 6a6bfc18b5ee6f7d · report fixture: signature role:str/0/str · returned str · level recorded 2026-09-22
to_hashable in 8 papers tau_bench/agents/chat_react_agent.py ran · our draft was wrong MIT (permissive) · 290b5b60a6956be6 · report fixture: signature item:dict/0/? · returned tuple · level recorded 2026-09-22
Agent in 42 papers tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · bdaf067f70d6cb83 · report
BaseUserSimulationEnv tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · e1bd2b500ed5d45e · report
ChatReActAgent tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · e480e41efb54cc05 · report
Env in 5 papers tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 970c4a357bfe3ed9 · report
EnvInfo tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 747fe2940f9b3de2 · report
EnvResetResponse tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · fdcd7a0695b2e849 · report
EnvResponse tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · a73129421afbde3a · report
LLMUserSimulationEnv tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 95c8661758537c4a · report
ReactUserSimulationEnv tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 82d74b8e85fde515 · report
ReflectionUserSimulationEnv tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 00d88099b2fae6a1 · report
RewardResult tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 8452d36949e4cc0d · report
Task in 17 papers tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · c6504ae4ebf5bcab · report
UserStrategy tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 32835ca402509b76 · report
VerifyUserSimulationEnv tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 4c54d2533220cb6d · report
load_user tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · 6ec1d4d5147ad9d7 · report
reflect in 11 papers tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · b0d8172e1c1ba444 · report
verify in 8 papers tau_bench/agents/chat_react_agent.py unverified MIT (permissive) · e0ead272d4fc4589 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for ReAct (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for ReAct (graph method: ReAct). 26 bricks; individually on a fixture: 9 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 17 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ChatReActAgent entry · level 0 · unverified · e480e41efb54cc05
  2. Action helper · level 1 · ran · 69febc56d55428d1
  3. Agent helper · level 0 · unverified · bdaf067f70d6cb83
  4. Env helper · level 0 · unverified · 970c4a357bfe3ed9
  5. SolveResult helper · level 1 · ran · 585b61f32e449f1f
  6. EnvInfo helper · level 0 · unverified · 747fe2940f9b3de2
  7. EnvResetResponse helper · level 0 · unverified · fdcd7a0695b2e849
  8. EnvResponse helper · level 0 · unverified · a73129421afbde3a
  9. RewardActionInfo helper · level 1 · ran · 57d96bea80ca4d0f
  10. RewardOutputInfo helper · level 1 · ran · 3cbe32095b32f8a4
  11. RewardResult helper · level 0 · unverified · 8452d36949e4cc0d
  12. Task helper · level 0 · unverified · c6504ae4ebf5bcab
  13. Tool helper · level 1 · ran · ea6a9a1ba41d476e
  14. UserStrategy helper · level 0 · unverified · 32835ca402509b76
  15. consistent_hash helper · level 1 · ran · our draft was wrong · 525653e8db7bd970
  16. load_user helper · level 0 · unverified · 6ec1d4d5147ad9d7
  17. to_hashable helper · level 1 · ran · our draft was wrong · 290b5b60a6956be6
  18. BaseUserSimulationEnv helper · level 0 · unverified · e1bd2b500ed5d45e
  19. HumanUserSimulationEnv helper · level 1 · ran · c06bc83fe26205ee
  20. LLMUserSimulationEnv helper · level 0 · unverified · 95c8661758537c4a
  21. ReactUserSimulationEnv helper · level 0 · unverified · 82d74b8e85fde515
  22. ReflectionUserSimulationEnv helper · level 0 · unverified · 00d88099b2fae6a1
  23. VerifyUserSimulationEnv helper · level 0 · unverified · 4c54d2533220cb6d
  24. reflect helper · level 0 · unverified · b0d8172e1c1ba444
  25. verify helper · level 0 · unverified · e0ead272d4fc4589
  26. map_role_label helper · level 1 · ran · our draft was wrong · 6a6bfc18b5ee6f7d

harvested Assembly for ReAct (graph method: ReAct). 5 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. ReactAgent entry · level 0 · unverified · 3b3b1888dc5abd89
  2. AgentState helper · level 1 · ran · 67368f282ad305f4
  3. State helper · level 1 · ran · b31daddc6c61beaf
  4. Tool helper · level 1 · ran · c1d21e714eedd29c
  5. load_prompt helper · level 0 · unverified · cb56e34b15e5e739

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="2210.03629") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Decision MakingFact VerificationHallucinationQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering WebQuestions React EM 38.3 #20 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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