agential-ai/agential issues and pull requests

#267 - CLIN Agent

Pull Request - State: closed - Opened by alckasoc about 1 month ago - 1 comment
Labels: enhancement

#266 - [Feature Request]: Standard way to Load states dict and dump states dict (like torch)

Issue - State: open - Opened by alckasoc about 1 month ago
Labels: enhancement

#265 - [Feature Request]: LLM-as-a-Judge Evaluation?

Issue - State: closed - Opened by alckasoc 2 months ago
Labels: enhancement

#264 - [Feature Request]: Evaluation Metrics

Issue - State: closed - Opened by alckasoc 3 months ago
Labels: enhancement

#263 - Evaluation Metrics, Fix-ups, Output Parsing for Evaluation

Pull Request - State: closed - Opened by alckasoc 3 months ago - 4 comments
Labels: enhancement, design

#262 - [Feature Request]: Evaluation Harness

Issue - State: closed - Opened by alckasoc 3 months ago
Labels: enhancement

#261 - Simple Baselines (CoT, Vanilla, Retries, Warming), Renaming Agent Classes, Adding Prompting component & core module

Pull Request - State: closed - Opened by alckasoc 3 months ago - 1 comment
Labels: enhancement, add-benchmark

#260 - Bump aiohttp from 3.9.5 to 3.10.2

Pull Request - State: closed - Opened by dependabot[bot] 3 months ago
Labels: dependencies

#259 - [Bug]: my zone

Issue - State: closed - Opened by Dila333 3 months ago
Labels: bug

#257 - [Feature Request]: Stabilize Output Parsing for Code benchmarks (specifically HEval)

Issue - State: closed - Opened by alckasoc 3 months ago
Labels: enhancement

#256 - Yet Another Rigorous, Robust Refactor (YARRR)

Pull Request - State: closed - Opened by alckasoc 3 months ago - 1 comment
Labels: enhancement, design

#255 - [Feature Request]: Standardized Output Fix for ExpeL, LATS, More Coverage

Issue - State: closed - Opened by alckasoc 3 months ago
Labels: enhancement

#254 - [Feature Request]: Standardize Base Agent

Issue - State: closed - Opened by alckasoc 3 months ago
Labels: enhancement

#253 - [Feature Request]: Isolate Agents in their own Modules

Issue - State: closed - Opened by alckasoc 3 months ago
Labels: enhancement

#252 - Migrating Away from LangChain -> LiteLLM & Logging for Token Usage, Cost, and Latency

Pull Request - State: closed - Opened by alckasoc 4 months ago - 2 comments
Labels: enhancement, design

#251 - [Feature Request]: Migrate Prompt creation and LLM Calling Away from LangChain

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#250 - Bump setuptools from 69.0.3 to 70.0.0

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago
Labels: dependencies

#249 - Bump torch from 2.1.2 to 2.2.0

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago
Labels: dependencies

#248 - Math & Code for LATS

Pull Request - State: closed - Opened by alckasoc 4 months ago - 1 comment
Labels: enhancement, add-benchmark

#247 - [Feature Request]: Add simple baselines

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#246 - [Feature Request]: Log token usage/costs/time for all agents

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#245 - [Feature Request]: Implement LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#244 - Language Agent Tree Search (LATS), QA (HotpotQA, FEVER, AmbigNQ, TriviaQA) for LATS, Notebook for QA LATS, Strategies Module QA for LATS/Structured Outputs

Pull Request - State: closed - Opened by alckasoc 4 months ago - 3 comments
Labels: enhancement

#243 - [Feature Request]: ExpeL Structured Outputs

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#242 - [Feature Request]: ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, Priority: High, method

#241 - [Feature Request]: MBPP for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#240 - [Feature Request]: HumanEval for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#239 - [Feature Request]: TabMWP for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#238 - [Feature Request]: SVAMP for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#237 - [Feature Request]: GSM8K for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#236 - [Feature Request]: FEVER for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#235 - [Feature Request]: TriviaQA for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#234 - [Feature Request]: AmbigNQ for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#233 - [Feature Request]: HotpotQA for ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#232 - [Feature Request]: Refactor ExpeL

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#231 - Refactor ExpeL for Strategies & Factory Modules, QA/Math/Code for ExpeL, Structured Output for ExpeL, Notebook for ExpeL, Trim Base Classes

Pull Request - State: closed - Opened by alckasoc 4 months ago - 2 comments
Labels: enhancement, design

#230 - [Feature Request]: Standardize error types in Reflexion with CRITIC/SR

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#229 - [Feature Request]: Standardize CRITIC/Self-Refine Few-shots for Math

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#228 - Standardize CRITIC/Self-Refine Few-shots for Math, Standardize error types in Reflexion with CRITIC/SR, Code for Self-Refine (HumanEval, MBPP)

Pull Request - State: closed - Opened by alckasoc 4 months ago - 2 comments
Labels: enhancement, add-benchmark

#227 - QA for Self-Refine (HotpotQA, FEVER, AmbigNQ, TriviaQA)

Pull Request - State: closed - Opened by alckasoc 4 months ago - 2 comments
Labels: enhancement, add-benchmark

#226 - [Feature Request]: Refactor Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement

#225 - Self-Refine, Refactoring Self-Refine, Math for Self-Refine (GSM8K, SVAMP, TabMWP)

Pull Request - State: closed - Opened by alckasoc 4 months ago - 2 comments

#224 - [Feature Request]: MBPP for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#223 - [Feature Request]: HumanEval for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#222 - [Feature Request]: TabMWP for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#221 - [Feature Request]: SVAMP for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#220 - [Feature Request]: GSM8K for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#219 - [Feature Request]: AmbigNQ for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#218 - [Feature Request]: FEVER for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#217 - [Feature Request]: TriviaQA for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#216 - [Feature Request]: HotpotQA for LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#215 - [Feature Request]: LATS

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, Priority: High, method

#214 - [Feature Request]: MBPP for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#213 - [Feature Request]: HumanEval for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#212 - [Feature Request]: TabMWP for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#211 - [Feature Request]: SVAMP for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#210 - [Feature Request]: GSM8K for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#209 - [Feature Request]: AmbigNQ for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#208 - [Feature Request]: FEVER for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#207 - [Feature Request]: TriviaQA for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#206 - [Feature Request]: HotpotQA for Self-Refine

Issue - State: closed - Opened by alckasoc 4 months ago
Labels: enhancement, add-benchmark

#205 - Bump certifi from 2024.2.2 to 2024.7.4 in /docs

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago - 1 comment
Labels: dependencies

#204 - Bump certifi from 2023.11.17 to 2024.7.4

Pull Request - State: closed - Opened by dependabot[bot] 4 months ago - 1 comment
Labels: dependencies

#203 - Universal Selector

Pull Request - State: closed - Opened by alckasoc 4 months ago - 2 comments
Labels: enhancement, design

#202 - NO MORE FEWSHOT EXAMPLES PLEASEEEEEEEE

Pull Request - State: closed - Opened by alckasoc 5 months ago - 2 comments
Labels: enhancement

#201 - TSOM

Pull Request - State: closed - Opened by alckasoc 5 months ago - 2 comments
Labels: enhancement, design

#200 - Bump urllib3 from 2.2.1 to 2.2.2 in /docs

Pull Request - State: closed - Opened by dependabot[bot] 5 months ago - 1 comment
Labels: dependencies

#199 - Bump urllib3 from 2.1.0 to 2.2.2

Pull Request - State: closed - Opened by dependabot[bot] 5 months ago - 1 comment
Labels: dependencies

#198 - Structured Outputs for Reflexion with Pydantic, Outputs Module

Pull Request - State: closed - Opened by alckasoc 5 months ago - 2 comments
Labels: design

#197 - Structured Outputs for ReAct with Pydantic

Pull Request - State: closed - Opened by emmalin-7 5 months ago - 2 comments
Labels: design

#196 - Let's get this done

Pull Request - State: closed - Opened by alckasoc 5 months ago - 2 comments
Labels: enhancement, design

#195 - [Feature Request]: Easier Way to Integrate new benchmarks and new modes

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement, Priority: Low

#194 - [Feature Request]: Diversifying prompts/benchmark ReAct few-shot example lengths

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement

#193 - [Feature Request]: Reflexion, Standardizing Reflection Few-Shots

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement

#192 - add universal selector

Pull Request - State: closed - Opened by berniewu2 5 months ago - 1 comment

#191 - Code for Reflexion (HumanEval, MBPP)

Pull Request - State: closed - Opened by alckasoc 5 months ago - 2 comments
Labels: add-benchmark

#190 - [Feature Request]: MATH Benchmark

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement, Priority: Low

#189 - [Feature Request]: Re-introduce Self-Refine

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement, Priority: High

#188 - [Feature Request]: Standardize Output Dictionaries for ReAct, CRITIC, and Reflexion

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement, design

#187 - Standardizing Critique Prompts for CRITIC Benchmarks

Pull Request - State: closed - Opened by tedasdf 5 months ago - 2 comments

#186 - Standardize Output Dictionaries, Mock API Calls, Math (GSM8K, SVAMP, TabMWP) for Reflexion

Pull Request - State: closed - Opened by alckasoc 5 months ago - 4 comments
Labels: enhancement, add-benchmark

#185 - [Feature Request]: CRITIC, Standardizing Critique Few-Shots

Issue - State: closed - Opened by alckasoc 5 months ago
Labels: enhancement, design, add-benchmark

#184 - Update base.py

Pull Request - State: closed - Opened by emmalin-7 5 months ago - 1 comment

#183 - Structured Outputs with Pydantic for CRITIC (QA, Math, Code)

Pull Request - State: closed - Opened by emmalin-7 5 months ago - 1 comment
Labels: enhancement, design

#182 - add benchmark

Pull Request - State: closed - Opened by tedasdf 5 months ago - 2 comments

#181 - Update code.py

Pull Request - State: closed - Opened by emmalin-7 5 months ago - 1 comment

#180 - adding pydantic to critic

Pull Request - State: closed - Opened by emmalin-7 6 months ago - 2 comments

#179 - [Feature Request]: Add Ability to log/save/output all llm inputs/outputs

Issue - State: closed - Opened by alckasoc 6 months ago
Labels: enhancement

#178 - [Feature Request]: Towards Structured, Organized Modules

Issue - State: closed - Opened by alckasoc 6 months ago
Labels: enhancement, design

#170 - [Feature Request]: Refactor ReflexionCoT & ReflexionReAct

Issue - State: closed - Opened by alckasoc 6 months ago
Labels: enhancement

#169 - Refactoring ReflexionCoT/ReflexionReAct (a bit of ExpeL), QA (FEVER, AmbigNQ, TriviaQA) for Reflexion, RIP Self-Refine

Pull Request - State: closed - Opened by alckasoc 6 months ago - 6 comments
Labels: enhancement, add-benchmark

GitHub / agential-ai/agential issues and pull requests